diff --git a/.github/workflows/build-and-push.yml b/.github/workflows/build-and-push.yml
new file mode 100644
index 0000000..417b368
--- /dev/null
+++ b/.github/workflows/build-and-push.yml
@@ -0,0 +1,34 @@
+name: Build and Push Docker Image
+
+on:
+ push:
+ paths:
+ - 'frontend/**'
+
+jobs:
+ build:
+ runs-on: ubuntu-latest
+
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v4
+
+ - name: Set up QEMU
+ uses: docker/setup-qemu-action@v3
+
+ - name: Set up Docker Buildx
+ uses: docker/setup-buildx-action@v3
+
+ - name: Log in to Docker Hub
+ uses: docker/login-action@v3
+ with:
+ username: ${{ secrets.DOCKER_USERNAME }}
+ password: ${{ secrets.DOCKER_PASSWORD }}
+
+ - name: Build and push Docker image
+ uses: docker/build-push-action@v5
+ with:
+ context: ./frontend
+ platforms: linux/amd64,linux/arm64
+ push: true
+ tags: morauen/oxn-frontend:latest
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index aca3bd2..ee712ff 100644
--- a/.gitignore
+++ b/.gitignore
@@ -25,3 +25,15 @@ evaluation.py
*.pickle
kubevpn.exe
venv
+
+# terraform
+terraform.tfstate
+terraform.tfstate.backup
+.terraform.lock.hcl
+.terraform
+
+# logs
+*.log
+
+# Cluster configuration
+config/.cluster-prefix
\ No newline at end of file
diff --git a/backend/db.sqlite3 b/backend/db.sqlite3
new file mode 100644
index 0000000..e69de29
diff --git a/backend/manage.py b/backend/manage.py
new file mode 100644
index 0000000..8926ee0
--- /dev/null
+++ b/backend/manage.py
@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+ """Run administrative tasks."""
+ os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'oxn_backend.settings')
+ try:
+ from django.core.management import execute_from_command_line
+ except ImportError as exc:
+ raise ImportError(
+ "Couldn't import Django. Are you sure it's installed and "
+ "available on your PYTHONPATH environment variable? Did you "
+ "forget to activate a virtual environment?"
+ ) from exc
+ execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+ main()
diff --git a/backend/oxn_backend/__init__.py b/backend/oxn_backend/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/backend/oxn_backend/asgi.py b/backend/oxn_backend/asgi.py
new file mode 100644
index 0000000..8d4f159
--- /dev/null
+++ b/backend/oxn_backend/asgi.py
@@ -0,0 +1,16 @@
+"""
+ASGI config for oxn_backend project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'oxn_backend.settings')
+
+application = get_asgi_application()
diff --git a/backend/oxn_backend/settings.py b/backend/oxn_backend/settings.py
new file mode 100644
index 0000000..b275b12
--- /dev/null
+++ b/backend/oxn_backend/settings.py
@@ -0,0 +1,124 @@
+"""
+Django settings for oxn_backend project.
+
+Generated by 'django-admin startproject' using Django 5.1.3.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/5.1/ref/settings/
+"""
+
+from pathlib import Path
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/5.1/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'django-insecure-3ex&@i1%1418$p_nw@(vas8z03maau+z29++c*v$x9=wu-&qjk'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+ 'django.contrib.admin',
+ 'django.contrib.auth',
+ 'django.contrib.contenttypes',
+ 'django.contrib.sessions',
+ 'django.contrib.messages',
+ 'django.contrib.staticfiles',
+ 'oxn_logic'
+]
+
+MIDDLEWARE = [
+ 'django.middleware.security.SecurityMiddleware',
+ 'django.contrib.sessions.middleware.SessionMiddleware',
+ 'django.middleware.common.CommonMiddleware',
+ 'django.middleware.csrf.CsrfViewMiddleware',
+ 'django.contrib.auth.middleware.AuthenticationMiddleware',
+ 'django.contrib.messages.middleware.MessageMiddleware',
+ 'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'oxn_backend.urls'
+
+TEMPLATES = [
+ {
+ 'BACKEND': 'django.template.backends.django.DjangoTemplates',
+ 'DIRS': [],
+ 'APP_DIRS': True,
+ 'OPTIONS': {
+ 'context_processors': [
+ 'django.template.context_processors.debug',
+ 'django.template.context_processors.request',
+ 'django.contrib.auth.context_processors.auth',
+ 'django.contrib.messages.context_processors.messages',
+ ],
+ },
+ },
+]
+
+WSGI_APPLICATION = 'oxn_backend.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/5.1/ref/settings/#databases
+
+DATABASES = {
+ 'default': {
+ 'ENGINE': 'django.db.backends.sqlite3',
+ 'NAME': BASE_DIR / 'db.sqlite3',
+ }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/5.1/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+ {
+ 'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+ },
+ {
+ 'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+ },
+ {
+ 'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+ },
+ {
+ 'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+ },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/5.1/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/5.1/howto/static-files/
+
+STATIC_URL = 'static/'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/5.1/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
diff --git a/backend/oxn_backend/urls.py b/backend/oxn_backend/urls.py
new file mode 100644
index 0000000..f154947
--- /dev/null
+++ b/backend/oxn_backend/urls.py
@@ -0,0 +1,24 @@
+"""
+URL configuration for oxn_backend project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+ https://docs.djangoproject.com/en/5.1/topics/http/urls/
+Examples:
+Function views
+ 1. Add an import: from my_app import views
+ 2. Add a URL to urlpatterns: path('', views.home, name='home')
+Class-based views
+ 1. Add an import: from other_app.views import Home
+ 2. Add a URL to urlpatterns: path('', Home.as_view(), name='home')
+Including another URLconf
+ 1. Import the include() function: from django.urls import include, path
+ 2. Add a URL to urlpatterns: path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path, include
+
+
+
+urlpatterns = [
+ path('', include('oxn_logic.urls'))
+]
diff --git a/backend/oxn_backend/wsgi.py b/backend/oxn_backend/wsgi.py
new file mode 100644
index 0000000..98eb892
--- /dev/null
+++ b/backend/oxn_backend/wsgi.py
@@ -0,0 +1,16 @@
+"""
+WSGI config for oxn_backend project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'oxn_backend.settings')
+
+application = get_wsgi_application()
diff --git a/backend/oxn_logic/__init__.py b/backend/oxn_logic/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/backend/oxn_logic/admin.py b/backend/oxn_logic/admin.py
new file mode 100644
index 0000000..8c38f3f
--- /dev/null
+++ b/backend/oxn_logic/admin.py
@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.
diff --git a/backend/oxn_logic/apps.py b/backend/oxn_logic/apps.py
new file mode 100644
index 0000000..3bc9e14
--- /dev/null
+++ b/backend/oxn_logic/apps.py
@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class OxnLogicConfig(AppConfig):
+ default_auto_field = 'django.db.models.BigAutoField'
+ name = 'oxn_logic'
diff --git a/backend/oxn_logic/migrations/__init__.py b/backend/oxn_logic/migrations/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/backend/oxn_logic/models.py b/backend/oxn_logic/models.py
new file mode 100644
index 0000000..71a8362
--- /dev/null
+++ b/backend/oxn_logic/models.py
@@ -0,0 +1,3 @@
+from django.db import models
+
+# Create your models here.
diff --git a/backend/oxn_logic/tests.py b/backend/oxn_logic/tests.py
new file mode 100644
index 0000000..7ce503c
--- /dev/null
+++ b/backend/oxn_logic/tests.py
@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.
diff --git a/backend/oxn_logic/urls.py b/backend/oxn_logic/urls.py
new file mode 100644
index 0000000..3d38d29
--- /dev/null
+++ b/backend/oxn_logic/urls.py
@@ -0,0 +1,6 @@
+from django.urls import path
+from . import views
+
+urlpatterns = [
+ path('api/helloworld', views.hello_world, name='hello_world'),
+]
\ No newline at end of file
diff --git a/backend/oxn_logic/views.py b/backend/oxn_logic/views.py
new file mode 100644
index 0000000..015afbe
--- /dev/null
+++ b/backend/oxn_logic/views.py
@@ -0,0 +1,7 @@
+from django.shortcuts import render
+from django.http import HttpResponse
+
+# Create your views here.
+
+def hello_world(request):
+ return HttpResponse("Hello world")
diff --git a/backend/readme.md b/backend/readme.md
new file mode 100644
index 0000000..2b8253b
--- /dev/null
+++ b/backend/readme.md
@@ -0,0 +1,12 @@
+# This is the backend Documentation for OXN
+
+1. make sure Django is included into the setup.cfg
+
+2. How to add routes:
+
+ 1. to add routes update the oxn_logic.views.py file with the code
+ 2. map the code to some url in the oxn_logic.urls.py file
+
+3. run the server on localhost from backend directory
+
+ python manage.py runserver
\ No newline at end of file
diff --git a/documentation/Architecute-building-blocks.drawio b/documentation/Architecute-building-blocks.drawio
new file mode 100644
index 0000000..00fa54f
--- /dev/null
+++ b/documentation/Architecute-building-blocks.drawio
@@ -0,0 +1,125 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/experiments/recommendation_delay90_A.yml b/experiments/OLD_recommendation_delay90_A.yml
similarity index 100%
rename from experiments/recommendation_delay90_A.yml
rename to experiments/OLD_recommendation_delay90_A.yml
diff --git a/experiments/recommendation_delay90_B.yml b/experiments/OLD_recommendation_delay90_B.yml
similarity index 100%
rename from experiments/recommendation_delay90_B.yml
rename to experiments/OLD_recommendation_delay90_B.yml
diff --git a/experiments/recommendation_delay90_C.yml b/experiments/OLD_recommendation_delay90_C.yml
similarity index 100%
rename from experiments/recommendation_delay90_C.yml
rename to experiments/OLD_recommendation_delay90_C.yml
diff --git a/experiments/recommendation_delay90_baseline.yml b/experiments/OLD_recommendation_delay90_baseline.yml
similarity index 100%
rename from experiments/recommendation_delay90_baseline.yml
rename to experiments/OLD_recommendation_delay90_baseline.yml
diff --git a/experiments/recommendation_loss15_A.yml b/experiments/OLD_recommendation_loss15_A.yml
similarity index 100%
rename from experiments/recommendation_loss15_A.yml
rename to experiments/OLD_recommendation_loss15_A.yml
diff --git a/experiments/recommendation_loss15_B.yml b/experiments/OLD_recommendation_loss15_B.yml
similarity index 100%
rename from experiments/recommendation_loss15_B.yml
rename to experiments/OLD_recommendation_loss15_B.yml
diff --git a/experiments/recommendation_loss15_C.yml b/experiments/OLD_recommendation_loss15_C.yml
similarity index 100%
rename from experiments/recommendation_loss15_C.yml
rename to experiments/OLD_recommendation_loss15_C.yml
diff --git a/experiments/recommendation_loss15_baseline.yml b/experiments/OLD_recommendation_loss15_baseline.yml
similarity index 100%
rename from experiments/recommendation_loss15_baseline.yml
rename to experiments/OLD_recommendation_loss15_baseline.yml
diff --git a/experiments/recommendation_pause_baseline.yml b/experiments/OLD_recommendation_pause_baseline.yml
similarity index 100%
rename from experiments/recommendation_pause_baseline.yml
rename to experiments/OLD_recommendation_pause_baseline.yml
diff --git a/experiments/test.yml b/experiments/OLD_test.yml
similarity index 98%
rename from experiments/test.yml
rename to experiments/OLD_test.yml
index 537cf75..8c49521 100644
--- a/experiments/test.yml
+++ b/experiments/OLD_test.yml
@@ -177,8 +177,8 @@ experiment:
max_users: 500
spawn_rate: 10
locust_files: [
- { path: locust/locust_basic_interaction.py },
- { path: locust/locust_otel_demo.py },
+ { path: /opt/oxn/locust/locust_basic_interaction.py },
+ { path: /opt/oxn/locust/locust_otel_demo.py },
]
target:
name: astronomy-shop-frontendproxy
diff --git a/experiments/big.yml b/experiments/big.yml
new file mode 100644
index 0000000..c15ed29
--- /dev/null
+++ b/experiments/big.yml
@@ -0,0 +1,180 @@
+# yaml-language-server: $schema=./experiment_schema.json
+experiment:
+ name: big
+ version: 0.0.1
+ orchestrator: kubernetes
+ services:
+ jaeger:
+ name: astronomy-shop-jaeger-query
+ namespace: system-under-evaluation
+ prometheus:
+ [
+ {
+ name: astronomy-shop-prometheus-server,
+ namespace: system-under-evaluation,
+ target: sue,
+ },
+ {
+ name: kube-prometheus-kube-prome-prometheus,
+ namespace: oxn-external-monitoring,
+ target: oxn,
+ },
+ ]
+ responses:
+ - name: frontend_traces
+ type: trace
+ service_name: frontend
+ left_window: 10s
+ right_window: 10s
+ limit: 1
+ - name: system_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation"}[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: recommendation_deployment_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation", pod=~"astronomy-shop-recommendationservice.*"}[90s])) by (pod)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: frontend_http_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_duration_milliseconds_bucket{job="opentelemetry-demo/frontend"}[90s])) by (http_method, http_status_code, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cart_service_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket{job="opentelemetry-demo/cartservice"}[90s])) by (http_route, le)) * 1000
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: product_catalog_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(rpc_server_duration_milliseconds_bucket{job="opentelemetry-demo/productcatalogservice"}[90s])) by (rpc_method, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_status
+ type: metric
+ metric_name: sum by (phase) (kube_pod_status_phase{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_restarts
+ type: metric
+ metric_name: sum(kube_pod_container_status_restarts_total{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: terminated_pods
+ type: metric
+ metric_name: sum(kube_pod_container_status_terminated{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: failed_spans
+ type: metric
+ metric_name: sum(rate(otelcol_exporter_send_failed_spans[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_bytes
+ type: metric
+ metric_name: sum(rate(node_network_receive_bytes_total[1m]) + rate(node_network_transmit_bytes_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_drops
+ type: metric
+ metric_name: sum(rate(node_network_receive_drop_total[1m]) + rate(node_network_transmit_drop_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_errors
+ type: metric
+ metric_name: sum(rate(node_network_receive_errs_total[1m]) + rate(node_network_transmit_errs_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_retransmissions
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_RetransSegs[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_udp_errors
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_InErrs[1m]) + rate(node_netstat_Udp_InErrors[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: node_load
+ type: metric
+ metric_name: node_load1
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: memory_available
+ type: metric
+ metric_name: node_memory_MemAvailable_bytes
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cpu_usage
+ type: metric
+ metric_name: sum(rate(node_cpu_seconds_total{mode!="idle"}[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_connections
+ type: metric
+ metric_name: node_netstat_Tcp_CurrEstab
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ treatments:
+ - empty_treatment:
+ action: empty
+ params: { duration: 1m }
+ sue:
+ compose: opentelemetry-demo/docker-compose.yml
+ exclude: [loadgenerator]
+ required:
+ [
+ {
+ namespace: system-under-evaluation,
+ name: astronomy-shop-prometheus-server,
+ },
+ ]
+ loadgen:
+ run_time: 20m
+ max_users: 500
+ spawn_rate: 50
+ locust_files:
+ - "/opt/oxn/locust/locust_basic_interaction.py"
+ - "/opt/oxn/locust/locust_otel_demo.py"
+ target:
+ name: astronomy-shop-frontendproxy
+ namespace: system-under-evaluation
+ port: 8080
diff --git a/experiments/debug_Experiment_packet_loss.yml b/experiments/debug_Experiment_packet_loss.yml
new file mode 100644
index 0000000..85c4a79
--- /dev/null
+++ b/experiments/debug_Experiment_packet_loss.yml
@@ -0,0 +1,48 @@
+# injects a 120s pause in the recomendation service
+experiment:
+ responses:
+ - frontend_traces:
+ type: trace
+ service_name: frontend
+ left_window: 240s
+ right_window: 240s
+ limit: 100000
+ - recommendation_traces:
+ type: trace
+ service_name: recommendationservice
+ left_window: 240s
+ right_window: 240s
+ limit: 100000
+ - system_CPU:
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{container_label_com_docker_compose_project="opentelemetry-demo"}[1m]))
+ left_window: 240s
+ right_window: 240s
+ step: 1
+ - recommendations_total:
+ type: metric
+ metric_name: increase(app_recommendations_counter_total[90s])
+ left_window: 240s
+ right_window: 240s
+ step: 1
+ treatments:
+ - packet_loss_treatment:
+ action: pause
+ params: {
+ service_name: recommendation-service,
+ duration: 30s,
+ }
+ sue:
+ compose: opentelemetry-demo/docker-compose.yml
+ exclude: [loadgenerator]
+ loadgen:
+ run_time: 1m
+ stages:
+ - {duration: 600, users: 50, spawn_rate: 25}
+ tasks:
+ - { endpoint: /, verb: get, weight: 1, params: { } }
+ - { endpoint: /api/products/0PUK6V6EV0, verb: get, weight: 10, params: { } }
+ - { endpoint: /api/recommendations, verb: get, weight: 3, params: { "productIds": ["1YMWWN1N4O"]}}
+ - { endpoint: /api/cart, verb: get, weight: 3, params: { } }
+ - { endpoint: /api/data, verb: get, weight: 3, params: { "contextKeys": [ "accessories" ] } }
+ - { endpoint: /api/cart, verb: post, weight: 2, params: { "item": {"productId":"6E92ZMYYFZ", "quantity":2, }, "userId":'ab2d0fc0-7224-11ec-8ef2-b658b885fb3',} }
\ No newline at end of file
diff --git a/experiments/experiment_new.yml b/experiments/experiment_new.yml
new file mode 100644
index 0000000..91c400b
--- /dev/null
+++ b/experiments/experiment_new.yml
@@ -0,0 +1,227 @@
+# yaml-language-server: $schema=experiment_schema.json
+experiment:
+ name: "latest"
+ version: 0.0.1
+ orchestrator: kubernetes
+ services:
+ jaeger:
+ name: astronomy-shop-jaeger-query
+ namespace: system-under-evaluation
+ prometheus:
+ [
+ {
+ name: astronomy-shop-prometheus-server,
+ namespace: system-under-evaluation,
+ target: sue,
+ },
+ {
+ name: kube-prometheus-kube-prome-prometheus,
+ namespace: oxn-external-monitoring,
+ target: oxn,
+ },
+ ]
+ responses:
+ - name: frontend_traces
+ type: trace
+ service_name: frontend
+ left_window: 10s
+ right_window: 10s
+ limit: 1
+ - name: system_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation"}[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: recommendation_deployment_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation", pod=~"astronomy-shop-recommendationservice.*"}[90s])) by (pod)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: frontend_http_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_duration_milliseconds_bucket{job="opentelemetry-demo/frontend"}[90s])) by (http_method, http_status_code, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cart_service_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket{job="opentelemetry-demo/cartservice"}[90s])) by (http_route, le)) * 1000
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: product_catalog_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(rpc_server_duration_milliseconds_bucket{job="opentelemetry-demo/productcatalogservice"}[90s])) by (rpc_method, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_status
+ type: metric
+ metric_name: sum by (phase) (kube_pod_status_phase{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_restarts
+ type: metric
+ metric_name: sum(kube_pod_container_status_restarts_total{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: terminated_pods
+ type: metric
+ metric_name: sum(kube_pod_container_status_terminated{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: failed_spans
+ type: metric
+ metric_name: sum(rate(otelcol_exporter_send_failed_spans[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_bytes
+ type: metric
+ metric_name: sum(rate(node_network_receive_bytes_total[1m]) + rate(node_network_transmit_bytes_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_drops
+ type: metric
+ metric_name: sum(rate(node_network_receive_drop_total[1m]) + rate(node_network_transmit_drop_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_errors
+ type: metric
+ metric_name: sum(rate(node_network_receive_errs_total[1m]) + rate(node_network_transmit_errs_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_retransmissions
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_RetransSegs[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_udp_errors
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_InErrs[1m]) + rate(node_netstat_Udp_InErrors[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: node_load
+ type: metric
+ metric_name: node_load1
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: memory_available
+ type: metric
+ metric_name: node_memory_MemAvailable_bytes
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cpu_usage
+ type: metric
+ metric_name: sum(rate(node_cpu_seconds_total{mode!="idle"}[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_connections
+ type: metric
+ metric_name: node_netstat_Tcp_CurrEstab
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ treatments:
+ - add_security_context:
+ action: security_context_kubernetes
+ params:
+ {
+ namespace: system-under-evaluation,
+ label_selector: app.kubernetes.io/component,
+ label: recommendationservice,
+ capabilities: { add: ["NET_ADMIN"] },
+ }
+ - delay_treatment:
+ action: delay
+ params: {
+ namespace: system-under-evaluation,
+ label_selector: app.kubernetes.io/name,
+ label: astronomy-shop-recommendationservice,
+ #service_name: node-exporter,
+ delay_time: 45ms,
+ delay_jitter: 45ms,
+ duration: 2m,
+ interface: eth0,
+ }
+ - probabilistic_head_sampling_rate:
+ action: kube_probl
+ params: { sampling_percentage: 5.0, hash_seed: 22 }
+ - package_lost_treatment:
+ action: kubernetes_loss
+ params:
+ {
+ namespace: system-under-evaluation,
+ label_selector: app.kubernetes.io/name,
+ label: astronomy-shop-recommendationservice,
+ loss_percentage: 15.0,
+ duration: 1m,
+ interface: eth0,
+ }
+ - empty_treatment:
+ action: empty
+ params: { duration: 5m }
+ - increase_otel_metric_interval:
+ action: kubernetes_otel_metrics_interval
+ params:
+ {
+ namespace: system-under-evaluation,
+ label_selector: app.kubernetes.io/component,
+ label: recommendationservice,
+ interval: 15s,
+ }
+ - prometheus_scrape_interval:
+ action: kubernetes_prometheus_interval
+ params: { interval: 5s, evaluation_interval: 5s, scrape_timeout: 3s }
+ sue:
+ compose: opentelemetry-demo/docker-compose.yml
+ exclude: [loadgenerator]
+ required: [
+ {
+ namespace: system-under-evaluation,
+ name: astronomy-shop-prometheus-server,
+ },
+ ] # {namespace: monitoring, name: not-running-service}
+ #required: [{namespace: monitoring, name: grafana}, {namespace: monitoring, name: node-exporter}]
+ loadgen:
+ run_time: 5m
+ max_users: 50
+ spawn_rate: 10
+ locust_files:
+ - "/opt/oxn/locust/locust_basic_interaction.py"
+ - "/opt/oxn/locust/locust_otel_demo.py"
+ target:
+ name: astronomy-shop-frontendproxy
+ namespace: system-under-evaluation
+ port: 8080
diff --git a/experiments/experiment_schema.json b/experiments/experiment_schema.json
new file mode 100644
index 0000000..ec33296
--- /dev/null
+++ b/experiments/experiment_schema.json
@@ -0,0 +1,255 @@
+{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "type": "object",
+ "properties": {
+ "experiment": {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "version": {
+ "type": "string"
+ },
+ "orchestrator": {
+ "type": "string"
+ },
+ "services": {
+ "type": "object",
+ "properties": {
+ "jaeger": {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "namespace": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "name",
+ "namespace"
+ ]
+ },
+ "prometheus": {
+ "type": "array",
+ "items": {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "namespace": {
+ "type": "string"
+ },
+ "target": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "name",
+ "namespace",
+ "target"
+ ]
+ }
+ }
+ },
+ "required": [
+ "jaeger",
+ "prometheus"
+ ]
+ },
+ "responses": {
+ "type": "array",
+ "items": {
+ "oneOf": [
+ {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "target": {
+ "type": "string"
+ },
+ "metric_name": {
+ "type": "string"
+ },
+ "type": {
+ "const": "metric"
+ },
+ "step": {
+ "type": "integer"
+ },
+ "left_window": {
+ "type": "string"
+ },
+ "right_window": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "name",
+ "target",
+ "metric_name",
+ "type",
+ "step",
+ "left_window",
+ "right_window"
+ ]
+ },
+ {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "type": {
+ "const": "trace"
+ },
+ "service_name": {
+ "type": "string"
+ },
+ "left_window": {
+ "type": "string"
+ },
+ "right_window": {
+ "type": "string"
+ },
+ "limit": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "name",
+ "type",
+ "service_name",
+ "left_window",
+ "right_window"
+ ]
+ }
+ ]
+ }
+ },
+ "treatments": {
+ "type": "array",
+ "items": {
+ "type": "object",
+ "patternProperties": {
+ "^.*$": {
+ "type": "object",
+ "properties": {
+ "action": {
+ "type": "string"
+ },
+ "params": {
+ "type": "object"
+ }
+ },
+ "required": [
+ "action",
+ "params"
+ ]
+ }
+ },
+ "additionalProperties": false
+ }
+ },
+ "sue": {
+ "type": "object",
+ "properties": {
+ "compose": {
+ "type": "string"
+ },
+ "exclude": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ }
+ },
+ "include": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ }
+ },
+ "required": {
+ "type": "array",
+ "items": {
+ "type": "object",
+ "properties": {
+ "namespace": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "namespace",
+ "name"
+ ]
+ }
+ }
+ },
+ "required": [
+ "compose"
+ ]
+ },
+ "loadgen": {
+ "type": "object",
+ "properties": {
+ "run_time": {
+ "type": "string"
+ },
+ "max_users": {
+ "type": "integer"
+ },
+ "spawn_rate": {
+ "type": "integer"
+ },
+ "locust_files": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ }
+ },
+ "target": {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "namespace": {
+ "type": "string"
+ },
+ "port": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "name",
+ "namespace",
+ "port"
+ ]
+ }
+ },
+ "required": [
+ "run_time"
+ ]
+ }
+ },
+ "required": [
+ "version",
+ "orchestrator",
+ "responses",
+ "sue",
+ "loadgen"
+ ]
+ }
+ },
+ "required": [
+ "experiment"
+ ]
+}
\ No newline at end of file
diff --git a/experiments/latest.yml b/experiments/latest.yml
new file mode 100644
index 0000000..8594a3f
--- /dev/null
+++ b/experiments/latest.yml
@@ -0,0 +1,245 @@
+# yaml-language-server: $schema=experiment_schema.json
+experiment:
+ name: "latest"
+ version: 0.0.1
+ orchestrator: kubernetes
+ services:
+ jaeger:
+ name: astronomy-shop-jaeger-query
+ namespace: system-under-evaluation
+ prometheus:
+ [
+ {
+ name: astronomy-shop-prometheus-server,
+ namespace: system-under-evaluation,
+ target: sue,
+ },
+ {
+ name: kube-prometheus-kube-prome-prometheus,
+ namespace: oxn-external-monitoring,
+ target: oxn,
+ },
+ ]
+ responses:
+ - name: frontend_traces
+ type: trace
+ service_name: frontend
+ left_window: 10s
+ right_window: 10s
+ limit: 1
+ - name: system_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation"}[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: recommendation_deployment_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation", pod=~"astronomy-shop-recommendationservice.*"}[90s])) by (pod)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: frontend_http_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_duration_milliseconds_bucket{job="opentelemetry-demo/frontend"}[90s])) by (http_method, http_status_code, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cart_service_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket{job="opentelemetry-demo/cartservice"}[90s])) by (http_route, le)) * 1000
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: product_catalog_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(rpc_server_duration_milliseconds_bucket{job="opentelemetry-demo/productcatalogservice"}[90s])) by (rpc_method, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_status
+ type: metric
+ metric_name: sum by (phase) (kube_pod_status_phase{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_restarts
+ type: metric
+ metric_name: sum(kube_pod_container_status_restarts_total{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: terminated_pods
+ type: metric
+ metric_name: sum(kube_pod_container_status_terminated{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: failed_spans
+ type: metric
+ metric_name: sum(rate(otelcol_exporter_send_failed_spans[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_bytes
+ type: metric
+ metric_name: sum(rate(node_network_receive_bytes_total[1m]) + rate(node_network_transmit_bytes_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_drops
+ type: metric
+ metric_name: sum(rate(node_network_receive_drop_total[1m]) + rate(node_network_transmit_drop_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_errors
+ type: metric
+ metric_name: sum(rate(node_network_receive_errs_total[1m]) + rate(node_network_transmit_errs_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_retransmissions
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_RetransSegs[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_udp_errors
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_InErrs[1m]) + rate(node_netstat_Udp_InErrors[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: node_load
+ type: metric
+ metric_name: node_load1
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: memory_available
+ type: metric
+ metric_name: node_memory_MemAvailable_bytes
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cpu_usage
+ type: metric
+ metric_name: sum(rate(node_cpu_seconds_total{mode!="idle"}[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_connections
+ type: metric
+ metric_name: node_netstat_Tcp_CurrEstab
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ treatments:
+ - empty_treatment:
+ action: empty
+ params: { duration: 5m }
+ #- stop_loadgen_deployment:
+ # action: scale_deployment
+ # params: {
+ # namespace: system-under-evaluation,
+ # label_selector: app.kubernetes.io/component,
+ # label: loadgenerator,
+ # scale_to: 0,
+ # }
+ #- add_security_context:
+ # action: security_context_kubernetes
+ # params: {
+ # namespace: system-under-evaluation,
+ # label_selector: app.kubernetes.io/component,
+ # label: recommendationservice,
+ # capabilities: { add: ["NET_ADMIN"] },
+ # }
+ # - delay_treatment:
+ # action: delay
+ # params: {
+ # namespace: system-under-evaluation,
+ # label_selector: app.kubernetes.io/name,
+ # label: astronomy-shop-recommendationservice,
+ # #service_name: node-exporter,
+ # delay_time: 45ms,
+ # delay_jitter: 45ms,
+ # duration: 2m,
+ # interface: eth0,
+ # }
+ # - probabilistic_head_sampling_rate:
+ # action: kube_probl
+ # params: {
+ # sampling_percentage: 5.0,
+ # hash_seed: 22,
+ # }
+ #- package_lost_treatment:
+ # action: kubernetes_loss
+ # params: {
+ # namespace: system-under-evaluation,
+ # label_selector: app.kubernetes.io/name,
+ # label: astronomy-shop-recommendationservice,
+ # loss_percentage: 15.0,
+ # duration: 10m,
+ # interface: eth0,
+ # }
+ #- empty_treatment:
+ # action: empty
+ # params: {
+ # duration: 5m,
+ # }
+ #- increase_otel_metric_interval:
+ # action: kubernetes_otel_metrics_interval
+ # params: {
+ # namespace: system-under-evaluation,
+ # label_selector: app.kubernetes.io/component,
+ # label: recommendationservice,
+ # interval: 15s,
+ # }
+ #reloading the prometheus config is not as trivial as it seems to be
+ #- prometheus_scrape_interval:
+ # action: kubernetes_prometheus_interval
+ # params: {
+ # interval: 5s,
+ # evaluation_interval: 5s,
+ # scrape_timeout: 3s,
+ # }
+ sue:
+ compose: opentelemetry-demo/docker-compose.yml
+ exclude: [loadgenerator]
+ required: [
+ {
+ namespace: system-under-evaluation,
+ name: astronomy-shop-prometheus-server,
+ },
+ ] # {namespace: monitoring, name: not-running-service}
+ #required: [{namespace: monitoring, name: grafana}, {namespace: monitoring, name: node-exporter}]
+ loadgen:
+ run_time: 5m
+ max_users: 50
+ spawn_rate: 10
+ locust_files:
+ - "/opt/oxn/locust/locust_basic_interaction.py"
+ - "/opt/oxn/locust/locust_otel_demo.py"
+ target:
+ name: astronomy-shop-frontendproxy
+ namespace: system-under-evaluation
+ port: 8080
diff --git a/experiments/short.yml b/experiments/short.yml
new file mode 100644
index 0000000..ff40bc9
--- /dev/null
+++ b/experiments/short.yml
@@ -0,0 +1,180 @@
+# yaml-language-server: $schema=experiment_schema.json
+experiment:
+ name: k8s-test-successful
+ version: 0.0.1
+ orchestrator: kubernetes
+ services:
+ jaeger:
+ name: astronomy-shop-jaeger-query
+ namespace: system-under-evaluation
+ prometheus:
+ [
+ {
+ name: astronomy-shop-prometheus-server,
+ namespace: system-under-evaluation,
+ target: sue,
+ },
+ {
+ name: kube-prometheus-kube-prome-prometheus,
+ namespace: oxn-external-monitoring,
+ target: oxn,
+ },
+ ]
+ responses:
+ - name: frontend_traces
+ type: trace
+ service_name: frontend
+ left_window: 10s
+ right_window: 10s
+ limit: 1
+ - name: system_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation"}[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: recommendation_deployment_CPU
+ type: metric
+ metric_name: sum(rate(container_cpu_usage_seconds_total{namespace="system-under-evaluation", pod=~"astronomy-shop-recommendationservice.*"}[90s])) by (pod)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: oxn
+ - name: frontend_http_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_duration_milliseconds_bucket{job="opentelemetry-demo/frontend"}[90s])) by (http_method, http_status_code, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cart_service_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(http_server_request_duration_seconds_bucket{job="opentelemetry-demo/cartservice"}[90s])) by (http_route, le)) * 1000
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: product_catalog_latency
+ type: metric
+ metric_name: histogram_quantile(0.95, sum(rate(rpc_server_duration_milliseconds_bucket{job="opentelemetry-demo/productcatalogservice"}[90s])) by (rpc_method, le))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_status
+ type: metric
+ metric_name: sum by (phase) (kube_pod_status_phase{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: pod_restarts
+ type: metric
+ metric_name: sum(kube_pod_container_status_restarts_total{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: terminated_pods
+ type: metric
+ metric_name: sum(kube_pod_container_status_terminated{namespace="system-under-evaluation"})
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: failed_spans
+ type: metric
+ metric_name: sum(rate(otelcol_exporter_send_failed_spans[1m]))
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_bytes
+ type: metric
+ metric_name: sum(rate(node_network_receive_bytes_total[1m]) + rate(node_network_transmit_bytes_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_drops
+ type: metric
+ metric_name: sum(rate(node_network_receive_drop_total[1m]) + rate(node_network_transmit_drop_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: network_errors
+ type: metric
+ metric_name: sum(rate(node_network_receive_errs_total[1m]) + rate(node_network_transmit_errs_total[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_retransmissions
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_RetransSegs[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_udp_errors
+ type: metric
+ metric_name: sum(rate(node_netstat_Tcp_InErrs[1m]) + rate(node_netstat_Udp_InErrors[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: node_load
+ type: metric
+ metric_name: node_load1
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: memory_available
+ type: metric
+ metric_name: node_memory_MemAvailable_bytes
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: cpu_usage
+ type: metric
+ metric_name: sum(rate(node_cpu_seconds_total{mode!="idle"}[1m])) by (instance)
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ - name: tcp_connections
+ type: metric
+ metric_name: node_netstat_Tcp_CurrEstab
+ left_window: 10s
+ right_window: 10s
+ step: 1
+ target: sue
+ treatments:
+ - empty_treatment:
+ action: empty
+ params: { duration: 1m }
+ sue:
+ compose: opentelemetry-demo/docker-compose.yml
+ exclude: [loadgenerator]
+ required:
+ [
+ {
+ namespace: system-under-evaluation,
+ name: astronomy-shop-prometheus-server,
+ },
+ ]
+ loadgen:
+ run_time: 2m
+ max_users: 10
+ spawn_rate: 5
+ locust_files:
+ - "/opt/oxn/locust/locust_basic_interaction.py"
+ - "/opt/oxn/locust/locust_otel_demo.py"
+ target:
+ name: astronomy-shop-frontendproxy
+ namespace: system-under-evaluation
+ port: 8080
diff --git a/frontend/.eslintrc.json b/frontend/.eslintrc.json
new file mode 100644
index 0000000..3722418
--- /dev/null
+++ b/frontend/.eslintrc.json
@@ -0,0 +1,3 @@
+{
+ "extends": ["next/core-web-vitals", "next/typescript"]
+}
diff --git a/frontend/.gitignore b/frontend/.gitignore
new file mode 100644
index 0000000..fd3dbb5
--- /dev/null
+++ b/frontend/.gitignore
@@ -0,0 +1,36 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.js
+.yarn/install-state.gz
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# local env files
+.env*.local
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts
diff --git a/frontend/Dockerfile b/frontend/Dockerfile
new file mode 100644
index 0000000..d7bd896
--- /dev/null
+++ b/frontend/Dockerfile
@@ -0,0 +1,66 @@
+# syntax=docker.io/docker/dockerfile:1
+
+FROM node:18-alpine AS base
+
+# Install dependencies only when needed
+FROM base AS deps
+# Check https://github.com/nodejs/docker-node/tree/b4117f9333da4138b03a546ec926ef50a31506c3#nodealpine to understand why libc6-compat might be needed.
+RUN apk add --no-cache libc6-compat
+WORKDIR /app
+
+# Install dependencies based on the preferred package manager
+COPY package.json yarn.lock* package-lock.json* pnpm-lock.yaml* .npmrc* ./
+RUN \
+ if [ -f yarn.lock ]; then yarn --frozen-lockfile; \
+ elif [ -f package-lock.json ]; then npm ci; \
+ elif [ -f pnpm-lock.yaml ]; then corepack enable pnpm && pnpm i --frozen-lockfile; \
+ else echo "Lockfile not found." && exit 1; \
+ fi
+
+
+# Rebuild the source code only when needed
+FROM base AS builder
+WORKDIR /app
+COPY --from=deps /app/node_modules ./node_modules
+COPY . .
+
+# Next.js collects completely anonymous telemetry data about general usage.
+# Learn more here: https://nextjs.org/telemetry
+# Uncomment the following line in case you want to disable telemetry during the build.
+ENV NEXT_TELEMETRY_DISABLED=1
+
+RUN \
+ if [ -f yarn.lock ]; then yarn run build; \
+ elif [ -f package-lock.json ]; then npm run build; \
+ elif [ -f pnpm-lock.yaml ]; then corepack enable pnpm && pnpm run build; \
+ else echo "Lockfile not found." && exit 1; \
+ fi
+
+# Production image, copy all the files and run next
+FROM base AS runner
+WORKDIR /app
+
+ENV NODE_ENV=production
+# Uncomment the following line in case you want to disable telemetry during runtime.
+# ENV NEXT_TELEMETRY_DISABLED=1
+
+RUN addgroup --system --gid 1001 nodejs
+RUN adduser --system --uid 1001 nextjs
+
+COPY --from=builder /app/public ./public
+
+# Automatically leverage output traces to reduce image size
+# https://nextjs.org/docs/advanced-features/output-file-tracing
+COPY --from=builder --chown=nextjs:nodejs /app/.next/standalone ./
+COPY --from=builder --chown=nextjs:nodejs /app/.next/static ./.next/static
+
+USER nextjs
+
+EXPOSE 3000
+
+ENV PORT=3000
+
+# server.js is created by next build from the standalone output
+# https://nextjs.org/docs/pages/api-reference/next-config-js/output
+ENV HOSTNAME="0.0.0.0"
+CMD ["node", "server.js"]
\ No newline at end of file
diff --git a/frontend/README.md b/frontend/README.md
new file mode 100644
index 0000000..6a31951
--- /dev/null
+++ b/frontend/README.md
@@ -0,0 +1,15 @@
+## Getting Started
+
+First, install dependencies:
+
+```bash
+npm install
+```
+
+Then, run the development server:
+
+```bash
+npm run dev
+```
+
+Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
diff --git a/frontend/app/error.tsx b/frontend/app/error.tsx
new file mode 100644
index 0000000..5521b61
--- /dev/null
+++ b/frontend/app/error.tsx
@@ -0,0 +1,18 @@
+'use client'
+import { Button } from "@/components/ui/button";
+
+export default function ErrorPage({ error, reset }: { error: Error; reset: () => void }) {
+
+ return (
+
+
Something went wrong
+
{error?.message || 'An unexpected error has occurred.'}
+
+
+ All the experiments setups will be included here...
+
+ )
+}
\ No newline at end of file
diff --git a/frontend/app/favicon.ico b/frontend/app/favicon.ico
new file mode 100644
index 0000000..718d6fe
Binary files /dev/null and b/frontend/app/favicon.ico differ
diff --git a/frontend/app/layout.tsx b/frontend/app/layout.tsx
new file mode 100644
index 0000000..57e6550
--- /dev/null
+++ b/frontend/app/layout.tsx
@@ -0,0 +1,36 @@
+import type { Metadata } from "next";
+import { ThemeProvider } from "@/context/theme-provider";
+import "@/styles/globals.css"
+import Layout from "@/components/layout";
+
+export const metadata: Metadata = {
+ title: "OXN++ Dashboard",
+ description: "A user-friendly interface for configuring, monitoring, and analyzing observability experiments in cloud-native applications.",
+ keywords: ["OXN", "Observability", "Microservices", "Dashboard", "Cloud-Native", "Fault Injection", "Performance Monitoring"],
+ authors: [],
+ applicationName: "OXN++",
+};
+
+export default function RootLayout({
+ children,
+}: Readonly<{
+ children: React.ReactNode;
+}>) {
+ return (
+
+
+