From a2e0a73b14e96df0cf8b28444090330caaeeb233 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 10:49:32 -0300 Subject: [PATCH 01/26] feat: implement PatternFly 6.3.1 UI revolution - Replace Bootstrap with PatternFly 6.3.1 components - Create Workload Scanner as initial screen - Implement Historical Analysis with breadcrumb navigation - Add proper PatternFly styling and components - Maintain all existing functionality with new UI --- app/static/index-backup.html | 2321 ++++++++++++++++++++++++ app/static/index-patternfly.html | 701 ++++++++ app/static/index.html | 2810 +++++++----------------------- 3 files changed, 3617 insertions(+), 2215 deletions(-) create mode 100644 app/static/index-backup.html create mode 100644 app/static/index-patternfly.html diff --git a/app/static/index-backup.html b/app/static/index-backup.html new file mode 100644 index 0000000..f6aa8d5 --- /dev/null +++ b/app/static/index-backup.html @@ -0,0 +1,2321 @@ + + + + + + OpenShift Resource Governance Tool + + + + +
+
+

Resource Governance

+
+ +
+ + +
+ + + + +
+

OpenShift Resource Governance Tool

+
+ + +
+ +
+ +
+

🎯 Resource Governance Dashboard

+ + +
+
🟢
+
+

Cluster Healthy

+

All systems operational

+
+
+ + +
+
+
-
+
Total Pods
+
+
+
-
+
Namespaces
+
+
+
-
+
Nodes
+
+
+
-
+
Critical Issues
+
+
+ + +
+

📊 Cluster Overcommit Summary

+
+
+
-
+
CPU Overcommit ℹ️
+
+
+
-
+
Memory Overcommit ℹ️
+
+
+
-
+
Namespaces in Overcommit
+
+
+
-
+
Resource Utilization ℹ️
+
+
+
+
+ + +
+

🔍 Problem Summary

+

Identify namespaces with resource configuration issues and take action

+ + +
+
+ + +
+
+ + +
+
+ + +
+ +
+ + +
+ + + + + + + + + + + + + + + +
NamespacePodsIssuesSeverityActions
Loading data...
+
+
+ + +
+

⚡ Quick Actions

+
+ + + + +
+
+
+ + + + + + + + + +
+
+ + + + diff --git a/app/static/index-patternfly.html b/app/static/index-patternfly.html new file mode 100644 index 0000000..110111a --- /dev/null +++ b/app/static/index-patternfly.html @@ -0,0 +1,701 @@ + + + + + + OpenShift Resource Governance Tool + + + + + + + + + + + + +
+ +
+ +
+
+
+ +
+
+ PatternFly +
+
+
+
+
+ +
+
+ +
+
+
+
+ + +
+
+ +
+
+ + +
+ +
+
+ +
+ +
+
+ +
+
+

Workload Scanner

+

Identify and analyze workloads with resource configuration issues

+
+
+ + +
+
+ +
+
+ + +
+
+
+
+

Workloads with Issues

+
+
+ +
+
+
+
+ +
+
+
+
+
+
+
+ + + +
+
+
+ + + + + + + + + + + diff --git a/app/static/index.html b/app/static/index.html index f6aa8d5..110111a 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -4,1250 +4,672 @@ OpenShift Resource Governance Tool + + + + + + + + + - -
-
-

Resource Governance

-
- -
+
+ +
+ +
+
+
+ +
+
+ PatternFly +
+
+
+
+
+ +
+
+ +
+
+
+
- -
- - + +
+
+ +
+
- -
-

OpenShift Resource Governance Tool

-
- - -
- -
- -
-

🎯 Resource Governance Dashboard

+ +
+ +
+
+ +
- -
-
🟢
-
-

Cluster Healthy

-

All systems operational

+
+
+ +
+
+

Workload Scanner

+

Identify and analyze workloads with resource configuration issues

+
+
+ + +
+
+ +
+
+ + +
+
+
+
+

Workloads with Issues

+
+
+ +
+
+
+
+ +
+
+
+
+
- -
-
-
-
-
Total Pods
-
-
-
-
-
Namespaces
-
-
-
-
-
Nodes
-
-
-
-
-
Critical Issues
-
+ +
- - -
-

🔍 Problem Summary

-

Identify namespaces with resource configuration issues and take action

- -
-
- - +
+
+ +
+
+

Historical Analysis

+

Resource consumption analysis and historical data

+
+
+ + +
+
+
+
+

Available Workloads

+
+
+ +
+
+
+
+ +
+
+
+
+ + +
-
- - -
-
- - -
-
- - -
- - - - - - - - - - - - - - - -
NamespacePodsIssuesSeverityActions
Loading data...
-
-
- - -
-

⚡ Quick Actions

-
- - - - -
-
-
- - - - - - - - - + +
+ + + + + + + From 43c618cbc420c1af855527b05e3e8b3f663a2947 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 10:51:33 -0300 Subject: [PATCH 02/26] fix: add historical analysis endpoints and fix FontAwesome - Add /api/v1/historical-analysis endpoint for workload list - Add /api/v1/historical-analysis/{namespace}/{workload} for details - Fix FontAwesome CDN to use working version - Update todo list with progress --- app/api/routes.py | 89 +++++++++++++++++++++++++++++++++++++++++++ app/static/index.html | 2 +- 2 files changed, 90 insertions(+), 1 deletion(-) diff --git a/app/api/routes.py b/app/api/routes.py index b8e501a..45b342a 100644 --- a/app/api/routes.py +++ b/app/api/routes.py @@ -1199,6 +1199,95 @@ async def get_smart_recommendations( logger.error(f"Error getting smart recommendations: {e}") raise HTTPException(status_code=500, detail=str(e)) +@api_router.get("/historical-analysis") +async def get_historical_analysis( + k8s_client=Depends(get_k8s_client), + prometheus_client=Depends(get_prometheus_client) +): + """Get historical analysis for all workloads""" + try: + # Get all pods + pods = await k8s_client.get_all_pods() + + # Group pods by workload + workloads = {} + for pod in pods: + workload_name = pod.metadata.labels.get('app', pod.metadata.labels.get('name', 'unknown')) + namespace = pod.metadata.namespace + + if workload_name not in workloads: + workloads[workload_name] = { + 'name': workload_name, + 'namespace': namespace, + 'pods': [] + } + workloads[workload_name]['pods'].append(pod) + + # Convert to list and add basic info + workload_list = [] + for workload_name, workload_data in workloads.items(): + workload_list.append({ + 'name': workload_name, + 'namespace': workload_data['namespace'], + 'pod_count': len(workload_data['pods']), + 'cpu_usage': 'N/A', # Will be populated by Prometheus queries + 'memory_usage': 'N/A', # Will be populated by Prometheus queries + 'last_updated': datetime.now().isoformat() + }) + + return { + "workloads": workload_list, + "total_workloads": len(workload_list), + "timestamp": datetime.now().isoformat() + } + + except Exception as e: + logger.error(f"Error getting historical analysis: {str(e)}") + raise HTTPException(status_code=500, detail=f"Error getting historical analysis: {str(e)}") + +@api_router.get("/historical-analysis/{namespace}/{workload}") +async def get_workload_historical_details( + namespace: str, + workload: str, + k8s_client=Depends(get_k8s_client), + prometheus_client=Depends(get_prometheus_client) +): + """Get detailed historical analysis for a specific workload""" + try: + # Get pods for this workload + pods = await k8s_client.get_pods_by_selector( + namespace=namespace, + selector={'app': workload} + ) + + if not pods: + raise HTTPException(status_code=404, detail=f"Workload {workload} not found in namespace {namespace}") + + # Get historical data from Prometheus + historical_service = HistoricalAnalysisService() + + # Get CPU and memory usage over time + cpu_data = await historical_service.get_cpu_usage_history(namespace, workload) + memory_data = await historical_service.get_memory_usage_history(namespace, workload) + + # Generate recommendations + recommendations = await historical_service.generate_recommendations(namespace, workload) + + return { + "workload": workload, + "namespace": namespace, + "cpu_data": cpu_data, + "memory_data": memory_data, + "recommendations": recommendations, + "timestamp": datetime.now().isoformat() + } + + except HTTPException: + raise + except Exception as e: + logger.error(f"Error getting workload historical details: {str(e)}") + raise HTTPException(status_code=500, detail=f"Error getting workload details: {str(e)}") + @api_router.get("/health") async def health_check(): """API health check""" diff --git a/app/static/index.html b/app/static/index.html index 110111a..8c68f70 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -300,7 +300,7 @@ - + + + diff --git a/app/static/index-patternfly-backup.html b/app/static/index-patternfly-backup.html new file mode 100644 index 0000000..8c68f70 --- /dev/null +++ b/app/static/index-patternfly-backup.html @@ -0,0 +1,701 @@ + + + + + + OpenShift Resource Governance Tool + + + + + + + + + + + + +
+ +
+ +
+
+
+ +
+
+ PatternFly +
+
+
+
+
+ +
+
+ +
+
+
+
+ + +
+
+ +
+
+ + +
+ +
+
+ +
+ +
+
+ +
+
+

Workload Scanner

+

Identify and analyze workloads with resource configuration issues

+
+
+ + +
+
+ +
+
+ + +
+
+
+
+

Workloads with Issues

+
+
+ +
+
+
+
+ +
+
+
+
+
+
+
+ + + +
+
+
+ + + + + + + + + + + diff --git a/app/static/index.html b/app/static/index.html index 8c68f70..e2214d7 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -5,304 +5,729 @@ OpenShift Resource Governance Tool + + + + + - - + + - + -
- -
- -
-
-
- -
-
- PatternFly -
-
-
-
-
- -
-
- -
-
-
-
+ +
+
+ + +
+
+
+ +
+
+ + 46 +
+
+ +
+
+ +
+
+ + anobre + +
+
+
- -
-
- + + + + +
+ +
+
+

Workload Scanner

+

Identify and analyze workloads with resource configuration issues

+
+ + +
+
+
+ +
+
-
+
Total Workloads
+
+
+
+ +
+
-
+
Namespaces
+
+
+
+ +
+
-
+
Critical Issues
+
+
+
+ +
+
-
+
Warnings
+ + +
+
+

Workloads with Issues

+ +
+
+ +
+
+
- -
- -
-
- + +
+
+

Historical Analysis

+

Resource consumption analysis and historical data

+
+ + +
+
+

Available Workloads

+ +
+
+ - -
-
- -
-
-

Workload Scanner

-

Identify and analyze workloads with resource configuration issues

-
-
- - -
-
- -
-
- - -
-
-
-
-

Workloads with Issues

-
-
- -
-
-
-
- -
-
-
-
-
-
-
+
+
+ + +
+
+

Workload Details

+ +
+
+ +
+
+ + - - - -
-
- - - - - - - - + From b2b47c4f1c3f7fbf9f295e066fee91b1b876f03a Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 11:31:47 -0300 Subject: [PATCH 07/26] feat: rebrand application to UWRU Scanner - Change application name to UWRU Scanner (User Workloads and Resource Usage Scanner) - Update title, header logo, and all references - Update FastAPI app metadata and health check - Update README.md with new branding - Maintain OpenShift Console visual identity --- README.md | 4 ++-- app/main.py | 12 ++++++------ app/static/index.html | 10 +++++----- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index e799043..ba96ca9 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ -# OpenShift Resource Governance Tool +# UWRU Scanner - User Workloads and Resource Usage Scanner -A resource governance tool for OpenShift clusters that goes beyond what Metrics Server and VPA offer, providing validations, reports and consolidated recommendations. +A comprehensive tool for analyzing user workloads and resource usage in OpenShift clusters that goes beyond what Metrics Server and VPA offer, providing validations, reports and consolidated recommendations. ## 🚀 Features diff --git a/app/main.py b/app/main.py index a6a0f2a..1f55bdf 100644 --- a/app/main.py +++ b/app/main.py @@ -1,6 +1,6 @@ """ -OpenShift Resource Governance Tool -Application for resource governance in OpenShift cluster +UWRU Scanner - User Workloads and Resource Usage Scanner +Application for analyzing user workloads and resource usage in OpenShift clusters """ import os import logging @@ -25,7 +25,7 @@ logger = logging.getLogger(__name__) @asynccontextmanager async def lifespan(app: FastAPI): """Application initialization and cleanup""" - logger.info("Starting OpenShift Resource Governance Tool") + logger.info("Starting UWRU Scanner - User Workloads and Resource Usage Scanner") # Initialize clients app.state.k8s_client = K8sClient() @@ -45,8 +45,8 @@ async def lifespan(app: FastAPI): # Create FastAPI application app = FastAPI( - title="OpenShift Resource Governance Tool", - description="Resource governance tool for OpenShift clusters", + title="UWRU Scanner - User Workloads and Resource Usage Scanner", + description="User Workloads and Resource Usage Scanner for OpenShift clusters", version="1.0.0", lifespan=lifespan ) @@ -77,7 +77,7 @@ async def health_check(): """Health check endpoint""" return { "status": "healthy", - "service": "openshift-resource-governance", + "service": "uwru-scanner", "version": "1.0.0" } diff --git a/app/static/index.html b/app/static/index.html index e2214d7..8497f21 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -3,7 +3,7 @@ - OpenShift Resource Governance Tool + UWRU Scanner - User Workloads and Resource Usage Scanner @@ -525,7 +525,7 @@ - +
@@ -568,7 +568,7 @@
  • - Workload Scanner + UWRU Scanner
  • @@ -633,8 +633,8 @@
    -

    Workload Scanner

    -

    Identify and analyze workloads with resource configuration issues

    +

    UWRU Scanner

    +

    User Workloads and Resource Usage Scanner - Identify and analyze workloads with resource configuration issues

    From 53ea0709572d9ebd419df2e7524308dad84c40cf Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 11:46:10 -0300 Subject: [PATCH 08/26] feat: remove sidebar toggle button and ensure data loading - Remove hamburger menu button from header - Remove sidebar toggle JavaScript functionality - Keep data loading functionality intact - Maintain OpenShift Console visual identity --- app/static/index.html | 100 +++++++++++++++++++----------------------- 1 file changed, 46 insertions(+), 54 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index 8497f21..9c5c52a 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -482,12 +482,12 @@ animation: spin 1s linear infinite; margin-right: 12px; } - + @keyframes spin { 0% { transform: rotate(0deg); } 100% { transform: rotate(360deg); } } - + /* Responsive */ @media (max-width: 768px) { .openshift-sidebar { @@ -498,11 +498,11 @@ .openshift-sidebar.open { transform: translateX(0); } - + .main-content { margin-left: 0; } - + .dashboard-grid { grid-template-columns: 1fr; } @@ -522,9 +522,6 @@
    -
    @@ -605,8 +602,8 @@
    • -
    - +
    +

    Observe

      @@ -635,40 +632,40 @@

      UWRU Scanner

      User Workloads and Resource Usage Scanner - Identify and analyze workloads with resource configuration issues

      -
      - +
    +
    -
    +
    -
    Total Workloads
    -
    -
    +
    +
    -
    -
    Namespaces
    -
    -
    +
    Namespaces
    +
    +
    -
    +
    -
    -
    Critical Issues
    -
    -
    +
    Critical Issues
    +
    +
    -
    +
    -
    Warnings
    +
    -
    - +
    @@ -677,14 +674,14 @@ Refresh -
    +
    +
    -
    - @@ -692,8 +689,8 @@

    Historical Analysis

    Resource consumption analysis and historical data

    -
    - + +
    @@ -701,8 +698,8 @@ -
    + +
    - +
    @@ -719,7 +716,7 @@ Close -
    +
    @@ -732,7 +729,7 @@ // Global variables let currentData = null; let currentSection = 'workload-scanner'; - + // Initialize the application document.addEventListener('DOMContentLoaded', function() { initializeApp(); @@ -756,12 +753,7 @@ showSection(section); }); }); - - // Sidebar toggle - document.getElementById('sidebar-toggle').addEventListener('click', function() { - const sidebar = document.getElementById('sidebar'); - sidebar.classList.toggle('open'); - }); + // Close workload details document.getElementById('close-workload-details').addEventListener('click', function() { @@ -789,12 +781,12 @@ document.querySelector(`.sidebar-nav-link[data-section="${section}"]`).classList.add('active'); currentSection = section; - + // Load section data if (section === 'workload-scanner') { loadWorkloadScanner(); } else if (section === 'historical-analysis') { - loadHistoricalAnalysis(); + loadHistoricalAnalysis(); } } @@ -860,7 +852,7 @@ `; return; } - + const tableHTML = ` @@ -878,8 +870,8 @@ - - + + - + + `).join('')}
    ${namespace.namespace} ${Object.keys(namespace.pods || {}).length}${namespace.total_validations || 0}${Object.keys(namespace.pods || {}).length}${namespace.total_validations || 0} ${getSeverityText(namespace)} @@ -890,8 +882,8 @@ Analyze -
    @@ -990,19 +982,19 @@

    CPU usage data will be displayed here

    -
    - + +

    Memory Usage

    -
    +

    Memory usage data will be displayed here

    +
    - - `; + `; } function analyzeWorkload(namespace) { @@ -1043,8 +1035,8 @@

    Error

    ${message}

    - - `; + + `; } From 05a54b785543a077af3c4e774ee75792cb8a34a8 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 11:54:07 -0300 Subject: [PATCH 09/26] feat: implement accordion for historical analysis with real data - Add expandable rows in historical analysis table - Implement accordion functionality with chevron icons - Load real CPU and memory data from API endpoint - Display current, average, and peak usage with progress bars - Show recommendations based on historical data - Improve UX with inline details instead of separate cards --- app/static/index.html | 228 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 217 insertions(+), 11 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index 9c5c52a..f64c56a 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -516,6 +516,33 @@ .section-hidden { display: none !important; } + + /* Accordion Styles */ + .expand-button { + background: none; + border: none; + color: var(--pf-global--Color--100); + cursor: pointer; + padding: 8px; + border-radius: 4px; + transition: all 0.2s ease; + } + + .expand-button:hover { + background-color: rgba(255, 255, 255, 0.1); + } + + .workload-details-row { + background-color: #1A1A1A; + } + + .workload-details-container { + padding: 0; + } + + .workload-row:hover { + background-color: rgba(255, 255, 255, 0.02); + } @@ -910,6 +937,7 @@ + @@ -920,8 +948,13 @@ - ${data.workloads.map(workload => ` - + ${data.workloads.map((workload, index) => ` + + @@ -931,12 +964,22 @@ + + + `).join('')}
    Workload Namespace Pods
    + + ${workload.name} ${workload.memory_usage || 'N/A'} ${workload.last_updated ? new Date(workload.last_updated).toLocaleString() : 'N/A'} -
    @@ -970,6 +1013,169 @@ } } + function toggleWorkloadDetails(index) { + const detailsRow = document.getElementById(`details-${index}`); + const expandBtn = document.getElementById(`expand-btn-${index}`); + const icon = expandBtn.querySelector('i'); + + if (detailsRow.style.display === 'none') { + detailsRow.style.display = 'table-row'; + icon.classList.remove('fa-chevron-right'); + icon.classList.add('fa-chevron-down'); + } else { + detailsRow.style.display = 'none'; + icon.classList.remove('fa-chevron-down'); + icon.classList.add('fa-chevron-right'); + } + } + + async function loadWorkloadDetails(workloadName, namespace, index) { + const container = document.getElementById(`details-content-${index}`); + + try { + container.innerHTML = ` + + `; + + const response = await fetch(`/api/v1/historical-analysis/${namespace}/${workloadName}`); + const data = await response.json(); + + updateWorkloadDetailsAccordion(data, index); + + } catch (error) { + console.error('Error loading workload details:', error); + container.innerHTML = ` +
    + +

    Error

    +

    Failed to load workload details

    +
    + `; + } + } + + function updateWorkloadDetailsAccordion(data, index) { + const container = document.getElementById(`details-content-${index}`); + + // Parse CPU and Memory data + const cpuData = data.cpu_data || {}; + const memoryData = data.memory_data || {}; + const recommendations = data.recommendations || []; + + container.innerHTML = ` +
    +
    +
    +
    +

    + + CPU Usage +

    +
    +
    + ${cpuData.current ? ` +
    +
    + Current Usage: + ${cpuData.current} cores +
    +
    +
    +
    +
    + ` : ''} + ${cpuData.average ? ` +
    +
    + Average (24h): + ${cpuData.average} cores +
    +
    + ` : ''} + ${cpuData.peak ? ` +
    +
    + Peak (24h): + ${cpuData.peak} cores +
    +
    + ` : ''} + ${!cpuData.current && !cpuData.average && !cpuData.peak ? ` +
    + +

    CPU usage data not available

    +
    + ` : ''} +
    +
    + +
    +
    +

    + + Memory Usage +

    +
    +
    + ${memoryData.current ? ` +
    +
    + Current Usage: + ${memoryData.current} +
    +
    +
    +
    +
    + ` : ''} + ${memoryData.average ? ` +
    +
    + Average (24h): + ${memoryData.average} +
    +
    + ` : ''} + ${memoryData.peak ? ` +
    +
    + Peak (24h): + ${memoryData.peak} +
    +
    + ` : ''} + ${!memoryData.current && !memoryData.average && !memoryData.peak ? ` +
    + +

    Memory usage data not available

    +
    + ` : ''} +
    +
    +
    + + ${recommendations.length > 0 ? ` +
    +
    +

    + + Recommendations +

    +
    +
    +
      + ${recommendations.map(rec => `
    • ${rec}
      • `).join('')} +
    +
    +
    + ` : ''} +
    + `; + } + function updateWorkloadDetails(data) { const container = document.getElementById('workload-details-content'); @@ -982,21 +1188,21 @@

    CPU usage data will be displayed here

    -
    - + +

    Memory Usage

    -
    +

    Memory usage data will be displayed here

    -
    + `; - } - + } + function analyzeWorkload(namespace) { console.log('Analyzing workload:', namespace); // TODO: Implement workload analysis From 187b67e86a0550eb907e52e1fc663ca3a4907e87 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 13:59:17 -0300 Subject: [PATCH 10/26] feat: restore workload validation analysis functionality - Add analyzeNamespace function with detailed pod analysis - Implement modal for showing requests/limits validation details - Add container resource analysis with requests/limits display - Show validation issues with severity indicators - Add proper modal styling with OpenShift theme - Restore functionality to view detailed workload configurations --- app/static/index.html | 250 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 242 insertions(+), 8 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index f64c56a..417274d 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -543,6 +543,102 @@ .workload-row:hover { background-color: rgba(255, 255, 255, 0.02); } + + /* Modal Styles */ + .modal { + display: none; + position: fixed; + z-index: 1000; + left: 0; + top: 0; + width: 100%; + height: 100%; + background-color: rgba(0, 0, 0, 0.8); + overflow-y: auto; + } + + .modal-content { + background-color: var(--pf-global--BackgroundColor--100); + margin: 2% auto; + padding: 0; + border-radius: 8px; + box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5); + animation: modalSlideIn 0.3s ease-out; + } + + @keyframes modalSlideIn { + from { + opacity: 0; + transform: translateY(-50px); + } + to { + opacity: 1; + transform: translateY(0); + } + } + + .modal-header { + background: linear-gradient(135deg, #2B2B2B 0%, #1E1E1E 100%); + color: var(--pf-global--Color--100); + padding: 20px 24px; + border-bottom: 1px solid #404040; + display: flex; + justify-content: space-between; + align-items: center; + border-radius: 8px 8px 0 0; + } + + .modal-header h2 { + margin: 0; + font-size: 20px; + font-weight: 600; + } + + .close { + color: var(--pf-global--Color--300); + font-size: 28px; + font-weight: bold; + cursor: pointer; + transition: color 0.2s ease; + } + + .close:hover { + color: var(--pf-global--Color--100); + } + + .modal-body { + padding: 24px; + max-height: 70vh; + overflow-y: auto; + } + + .status-indicator { + padding: 4px 8px; + border-radius: 4px; + font-size: 12px; + font-weight: 600; + text-transform: uppercase; + } + + .status-indicator.danger { + background-color: var(--pf-global--danger-color--100); + color: white; + } + + .status-indicator.warning { + background-color: var(--pf-global--warning-color--100); + color: black; + } + + .status-indicator.info { + background-color: var(--pf-global--info-color--100); + color: white; + } + + .status-indicator.success { + background-color: var(--pf-global--success-color--100); + color: white; + } @@ -897,20 +993,20 @@ ${namespace.namespace} - ${Object.keys(namespace.pods || {}).length} - ${namespace.total_validations || 0} + ${Object.keys(namespace.pods || {}).length} + ${namespace.total_validations || 0} ${getSeverityText(namespace)} - - - + + `).join('')} @@ -1203,9 +1299,147 @@ `; } - function analyzeWorkload(namespace) { - console.log('Analyzing workload:', namespace); - // TODO: Implement workload analysis + function analyzeNamespace(namespaceName) { + if (!currentData || !currentData.validations || !currentData.validations.namespaces) return; + + const namespace = currentData.validations.namespaces.find(ns => ns.namespace === namespaceName); + if (!namespace) return; + + // Show details in modal + showNamespaceDetails(namespaceName); + } + + function showNamespaceDetails(namespaceName) { + // Create modal if it doesn't exist + let modal = document.getElementById('namespaceModal'); + if (!modal) { + modal = document.createElement('div'); + modal.id = 'namespaceModal'; + modal.className = 'modal'; + modal.innerHTML = ` +
    +
    +

    📋 Namespace Analysis - ${namespaceName}

    + × +
    +
    +
    + `; + document.body.appendChild(modal); + + // Add close functionality + modal.querySelector('.close').onclick = () => modal.style.display = 'none'; + modal.onclick = (e) => { + if (e.target === modal) modal.style.display = 'none'; + }; + } + + // Create detailed content + const namespace = currentData.validations.namespaces.find(ns => ns.namespace === namespaceName); + if (!namespace) return; + + let content = ` +
    +
    +

    📊 Summary

    +
    +
    + Pods: ${Object.keys(namespace.pods || {}).length} +
    +
    + Total Issues: ${namespace.total_validations || 0} +
    +
    + Errors: ${namespace.severity_breakdown?.error || 0} +
    +
    + Warnings: ${namespace.severity_breakdown?.warning || 0} +
    +
    +
    +
    +

    🔍 Pod Analysis

    + `; + + // Add details for each pod + Object.values(namespace.pods || {}).forEach(pod => { + content += ` +
    +

    📦 ${pod.pod_name}

    +
    +
    Status: ${pod.phase}
    +
    Node: ${pod.node_name}
    +
    +
    +
    Containers:
    + `; + + pod.containers.forEach(container => { + const hasRequests = Object.keys(container.resources?.requests || {}).length > 0; + const hasLimits = Object.keys(container.resources?.limits || {}).length > 0; + + content += ` +
    +
    ${container.name}
    +

    Image: ${container.image}

    +
    +
    + Requests: + ${hasRequests ? + `${JSON.stringify(container.resources.requests)}` : + '❌ Not defined' + } +
    +
    + Limits: + ${hasLimits ? + `${JSON.stringify(container.resources.limits)}` : + '❌ Not defined' + } +
    +
    +
    + `; + }); + + content += ` +
    +
    +
    Issues Found:
    + `; + + if (pod.validations && pod.validations.length > 0) { + pod.validations.forEach(validation => { + const severityClass = validation.severity === 'error' ? 'danger' : + validation.severity === 'warning' ? 'warning' : 'info'; + const severityColor = validation.severity === 'error' ? 'var(--pf-global--danger-color--100)' : + validation.severity === 'warning' ? 'var(--pf-global--warning-color--100)' : 'var(--pf-global--info-color--100)'; + + content += ` +
    +

    ${validation.rule_name}: ${validation.message}

    +

    Recommendation: ${validation.recommendation}

    +
    + `; + }); + } else { + content += `

    ✅ No issues found for this pod.

    `; + } + + content += ` +
    +
    + `; + }); + + content += ` +
    +
    + `; + + // Populate and show modal + document.getElementById('modalBody').innerHTML = content; + modal.style.display = 'block'; } function getSeverityClass(namespace) { From 6d5da374e620d476c0f3b67aa512165bed53167f Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 14:01:44 -0300 Subject: [PATCH 11/26] fix: adapt interface to work with current API format - Update updateWorkloadsTable to group validations by namespace - Fix analyzeNamespace to work with validation array format - Group validations by namespace and pod for proper display - Show actual validation data instead of 'No Issues Found' - Maintain compatibility with existing modal functionality --- app/static/index.html | 80 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 69 insertions(+), 11 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index 417274d..e796b77 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -965,7 +965,36 @@ function updateWorkloadsTable(data) { const container = document.getElementById('workloads-table-container'); - if (!data.namespaces || data.namespaces.length === 0) { + // Group validations by namespace + const namespaceGroups = {}; + if (data.validations && data.validations.length > 0) { + data.validations.forEach(validation => { + const namespace = validation.namespace; + if (!namespaceGroups[namespace]) { + namespaceGroups[namespace] = { + namespace: namespace, + validations: [], + pods: new Set(), + severity_breakdown: { error: 0, warning: 0, info: 0 } + }; + } + namespaceGroups[namespace].validations.push(validation); + namespaceGroups[namespace].pods.add(validation.pod_name); + + // Count severity + if (validation.severity === 'error') { + namespaceGroups[namespace].severity_breakdown.error++; + } else if (validation.severity === 'warning') { + namespaceGroups[namespace].severity_breakdown.warning++; + } else if (validation.severity === 'info') { + namespaceGroups[namespace].severity_breakdown.info++; + } + }); + } + + const namespaces = Object.values(namespaceGroups); + + if (namespaces.length === 0) { container.innerHTML = `
    @@ -988,13 +1017,13 @@ - ${data.namespaces.map(namespace => ` + ${namespaces.map(namespace => ` ${namespace.namespace} - ${Object.keys(namespace.pods || {}).length} - ${namespace.total_validations || 0} + ${namespace.pods.size} + ${namespace.validations.length} ${getSeverityText(namespace)} @@ -1300,16 +1329,46 @@ } function analyzeNamespace(namespaceName) { - if (!currentData || !currentData.validations || !currentData.validations.namespaces) return; + if (!currentData || !currentData.validations || !currentData.validations.validations) return; - const namespace = currentData.validations.namespaces.find(ns => ns.namespace === namespaceName); - if (!namespace) return; + // Filter validations for this namespace + const namespaceValidations = currentData.validations.validations.filter(v => v.namespace === namespaceName); + if (namespaceValidations.length === 0) return; + + // Group by pod + const podGroups = {}; + namespaceValidations.forEach(validation => { + const podName = validation.pod_name; + if (!podGroups[podName]) { + podGroups[podName] = { + pod_name: podName, + namespace: namespaceName, + phase: 'Running', // Default phase + node_name: 'Unknown', // Default node + containers: [], + validations: [] + }; + } + podGroups[podName].validations.push(validation); + }); + + // Create namespace object for compatibility + const namespace = { + namespace: namespaceName, + pods: podGroups, + validations: namespaceValidations, + severity_breakdown: { + error: namespaceValidations.filter(v => v.severity === 'error').length, + warning: namespaceValidations.filter(v => v.severity === 'warning').length, + info: namespaceValidations.filter(v => v.severity === 'info').length + } + }; // Show details in modal - showNamespaceDetails(namespaceName); + showNamespaceDetails(namespaceName, namespace); } - function showNamespaceDetails(namespaceName) { + function showNamespaceDetails(namespaceName, namespace) { // Create modal if it doesn't exist let modal = document.getElementById('namespaceModal'); if (!modal) { @@ -1334,8 +1393,7 @@ }; } - // Create detailed content - const namespace = currentData.validations.namespaces.find(ns => ns.namespace === namespaceName); + // Use the passed namespace object if (!namespace) return; let content = ` From 8e6dc0df9b34cecb1086718e2de366bdedb0473b Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 15:31:53 -0300 Subject: [PATCH 12/26] fix: correct total issues count in modal - Fix modal to show correct total issues count from validations array - Use namespace.validations.length instead of namespace.total_validations - Ensure consistency between table and modal data display --- app/static/index.html | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/static/index.html b/app/static/index.html index e796b77..fef19bc 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -1405,7 +1405,7 @@ Pods: ${Object.keys(namespace.pods || {}).length}
    - Total Issues: ${namespace.total_validations || 0} + Total Issues: ${namespace.validations?.length || 0}
    Errors: ${namespace.severity_breakdown?.error || 0} From e1dae22e98430d2bd38be6f48eb859f72efff494 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 15:45:09 -0300 Subject: [PATCH 13/26] feat: implement Chart.js graphs for Historical Analysis - Add Chart.js 4.4.0 and date adapter for time series graphs - Implement createCPUChart and createMemoryChart functions - Update updateWorkloadDetailsAccordion to show interactive graphs - Add getCurrentValue, getAverageValue, getPeakValue helper functions - Display CPU and Memory usage over 24h with real-time data - Show current, average, and peak values below graphs - Use working Prometheus queries from metrics endpoint --- app/services/historical_analysis.py | 170 +++++++++++++++++ app/static/index.html | 283 ++++++++++++++++++++-------- 2 files changed, 377 insertions(+), 76 deletions(-) diff --git a/app/services/historical_analysis.py b/app/services/historical_analysis.py index e96df59..61a8e9f 100644 --- a/app/services/historical_analysis.py +++ b/app/services/historical_analysis.py @@ -1332,3 +1332,173 @@ class HistoricalAnalysisService: 'error': str(e), 'recommendations': [] } + + async def get_cpu_usage_history(self, namespace: str, workload: str, time_range: str = "24h") -> Dict[str, Any]: + """Get CPU usage history for a workload using working Prometheus queries""" + try: + # Use the working query from the metrics endpoint + cpu_usage_query = f'rate(container_cpu_usage_seconds_total{{namespace="{namespace}", pod=~"{workload}.*"}}[5m])' + + # Calculate time range + end_time = datetime.now() + start_time = end_time - timedelta(seconds=self.time_ranges.get(time_range, 86400)) + + # Query Prometheus + data = await self._query_prometheus(cpu_usage_query, start_time, end_time) + + if not data: + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": [], + "message": "No CPU usage data available" + } + + # Format data for Chart.js + chart_data = [] + for point in data: + if len(point) >= 2 and point[1] != 'NaN': + timestamp = int(point[0] * 1000) # Convert to milliseconds + value = self._safe_float(point[1]) + chart_data.append({ + "x": timestamp, + "y": value + }) + + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": chart_data, + "query": cpu_usage_query + } + + except Exception as e: + logger.error(f"Error getting CPU usage history: {str(e)}") + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": [], + "error": str(e) + } + + async def get_memory_usage_history(self, namespace: str, workload: str, time_range: str = "24h") -> Dict[str, Any]: + """Get memory usage history for a workload using working Prometheus queries""" + try: + # Use the working query from the metrics endpoint + memory_usage_query = f'container_memory_working_set_bytes{{namespace="{namespace}", pod=~"{workload}.*", container!="", image!=""}}' + + # Calculate time range + end_time = datetime.now() + start_time = end_time - timedelta(seconds=self.time_ranges.get(time_range, 86400)) + + # Query Prometheus + data = await self._query_prometheus(memory_usage_query, start_time, end_time) + + if not data: + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": [], + "message": "No memory usage data available" + } + + # Format data for Chart.js (convert bytes to MB) + chart_data = [] + for point in data: + if len(point) >= 2 and point[1] != 'NaN': + timestamp = int(point[0] * 1000) # Convert to milliseconds + value = self._safe_float(point[1]) / (1024 * 1024) # Convert to MB + chart_data.append({ + "x": timestamp, + "y": value + }) + + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": chart_data, + "query": memory_usage_query + } + + except Exception as e: + logger.error(f"Error getting memory usage history: {str(e)}") + return { + "workload": workload, + "namespace": namespace, + "time_range": time_range, + "data": [], + "error": str(e) + } + + async def generate_recommendations(self, namespace: str, workload: str) -> List[Dict[str, Any]]: + """Generate recommendations based on historical data""" + try: + # Get current usage data + cpu_data = await self.get_cpu_usage_history(namespace, workload, "24h") + memory_data = await self.get_memory_usage_history(namespace, workload, "24h") + + recommendations = [] + + # Analyze CPU data + if cpu_data.get("data"): + cpu_values = [point["y"] for point in cpu_data["data"]] + if cpu_values: + avg_cpu = sum(cpu_values) / len(cpu_values) + max_cpu = max(cpu_values) + + if avg_cpu < 0.1: # Less than 100m + recommendations.append({ + "type": "cpu_optimization", + "severity": "info", + "message": f"CPU usage is very low (avg: {avg_cpu:.3f} cores). Consider reducing CPU requests.", + "current_usage": f"{avg_cpu:.3f} cores", + "recommendation": "Reduce CPU requests to match actual usage" + }) + elif max_cpu > 0.8: # More than 800m + recommendations.append({ + "type": "cpu_scaling", + "severity": "warning", + "message": f"CPU usage peaks at {max_cpu:.3f} cores. Consider increasing CPU limits.", + "current_usage": f"{max_cpu:.3f} cores", + "recommendation": "Increase CPU limits to handle peak usage" + }) + + # Analyze memory data + if memory_data.get("data"): + memory_values = [point["y"] for point in memory_data["data"]] + if memory_values: + avg_memory = sum(memory_values) / len(memory_values) + max_memory = max(memory_values) + + if avg_memory < 100: # Less than 100MB + recommendations.append({ + "type": "memory_optimization", + "severity": "info", + "message": f"Memory usage is very low (avg: {avg_memory:.1f} MB). Consider reducing memory requests.", + "current_usage": f"{avg_memory:.1f} MB", + "recommendation": "Reduce memory requests to match actual usage" + }) + elif max_memory > 1000: # More than 1GB + recommendations.append({ + "type": "memory_scaling", + "severity": "warning", + "message": f"Memory usage peaks at {max_memory:.1f} MB. Consider increasing memory limits.", + "current_usage": f"{max_memory:.1f} MB", + "recommendation": "Increase memory limits to handle peak usage" + }) + + return recommendations + + except Exception as e: + logger.error(f"Error generating recommendations: {str(e)}") + return [{ + "type": "error", + "severity": "error", + "message": f"Error generating recommendations: {str(e)}", + "recommendation": "Check Prometheus connectivity and workload configuration" + }] diff --git a/app/static/index.html b/app/static/index.html index fef19bc..437199d 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -17,6 +17,10 @@ + + + + @@ -1044,24 +1216,79 @@

    Smart Recommendations

    AI-powered recommendations for resource optimization and VPA activation

    -
    +
    -

    Recommendations

    -
    -
    +
    + + +
    +
    +
    +
    +
    +
    +
    + + +
    +
    + +
    +
    +
    +
    +
    + + +
    - @@ -1254,6 +1481,7 @@ // Store recommendations globally for button functions window.currentRecommendations = data.recommendations || []; + window.selectedRecommendations = new Set(); if (!data || !data.recommendations || data.recommendations.length === 0) { container.innerHTML = ` @@ -1261,77 +1489,245 @@

    No Recommendations Available

    No smart recommendations found for the current cluster state.

    - + `; + updateBulkSelectUI(); return; } - const recommendationsHtml = data.recommendations.map(rec => ` -
    -
    -

    - - ${rec.title} -

    - ${rec.priority.toUpperCase()} -
    -
    -

    ${rec.description}

    - - ${rec.workload_list && rec.workload_list.length > 0 ? ` -
    - Affected Workloads: -
      - ${rec.workload_list.map(workload => { - // Extract priority from workload string (e.g., "example (shishika01) - HIGH") - const priorityMatch = workload.match(/\s-\s(\w+)$/); - const priority = priorityMatch ? priorityMatch[1].toLowerCase() : 'low'; - const priorityColor = getPriorityColor(priority); - return `
    • ${workload}
      • `; - }).join('')} -
    -
    - ` : ''} - - ${rec.implementation_steps && rec.implementation_steps.length > 0 ? ` -
    - Implementation Steps: -
      - ${rec.implementation_steps.map(step => `
    1. ${step}
      2. `).join('')} -
    -
    - ` : ''} - -
    - ${rec.vpa_yaml ? ` - - ` : ''} - - ${rec.kubectl_commands && rec.kubectl_commands.length > 0 ? ` - - ` : ''} - - - - + // Update bulk select counters + document.getElementById('total-recommendations').textContent = data.recommendations.length; + document.getElementById('page-recommendations').textContent = data.recommendations.length; + + const recommendationsHtml = data.recommendations.map((rec, index) => ` +
    +
    +
    +
    +

    ${rec.title}

    +
    + +
    +
    + +
    +

    ${rec.description}

    + +
    +
    + + ${rec.workload_name || 'N/A'} +
    +
    + + ${rec.namespace || 'N/A'} +
    +
    + + ${rec.recommendation_type} +
    +
    + ${rec.priority.toUpperCase()} +
    +
    +
    + +
    + ${rec.vpa_yaml ? ` + + ` : ''} + + + +
    `).join(''); container.innerHTML = recommendationsHtml; + updateBulkSelectUI(); + } + + // Bulk Select Functions + function toggleBulkSelect() { + const menu = document.getElementById('bulk-select-menu'); + const toggle = document.getElementById('bulk-select-toggle'); + const isOpen = menu.style.display !== 'none'; + + menu.style.display = isOpen ? 'none' : 'block'; + toggle.setAttribute('aria-expanded', !isOpen); + } + + function toggleRecommendationSelection(index) { + const checkbox = document.getElementById(`checkbox-${index}`); + const card = document.getElementById(`recommendation-${index}`); + + if (checkbox.checked) { + window.selectedRecommendations.add(index); + card.classList.add('selected'); + } else { + window.selectedRecommendations.delete(index); + card.classList.remove('selected'); + } + + updateBulkSelectUI(); + } + + function selectAllRecommendations() { + const checkboxes = document.querySelectorAll('.recommendation-checkbox'); + checkboxes.forEach((checkbox, index) => { + checkbox.checked = true; + window.selectedRecommendations.add(index); + document.getElementById(`recommendation-${index}`).classList.add('selected'); + }); + updateBulkSelectUI(); + toggleBulkSelect(); + } + + function selectPageRecommendations() { + const checkboxes = document.querySelectorAll('.recommendation-checkbox'); + checkboxes.forEach((checkbox, index) => { + checkbox.checked = true; + window.selectedRecommendations.add(index); + document.getElementById(`recommendation-${index}`).classList.add('selected'); + }); + updateBulkSelectUI(); + toggleBulkSelect(); + } + + function deselectAllRecommendations() { + const checkboxes = document.querySelectorAll('.recommendation-checkbox'); + checkboxes.forEach((checkbox, index) => { + checkbox.checked = false; + window.selectedRecommendations.delete(index); + document.getElementById(`recommendation-${index}`).classList.remove('selected'); + }); + updateBulkSelectUI(); + toggleBulkSelect(); + } + + function updateBulkSelectUI() { + const selectedCount = window.selectedRecommendations ? window.selectedRecommendations.size : 0; + const totalCount = window.currentRecommendations ? window.currentRecommendations.length : 0; + + document.getElementById('bulk-select-text').textContent = `${selectedCount} selected`; + document.getElementById('selected-count').textContent = selectedCount; + + const bulkActions = document.getElementById('bulk-actions'); + if (selectedCount > 0) { + bulkActions.style.display = 'flex'; + } else { + bulkActions.style.display = 'none'; + } + } + + async function applySelectedRecommendations() { + if (!window.selectedRecommendations || window.selectedRecommendations.size === 0) { + alert('No recommendations selected'); + return; + } + + const selectedIndices = Array.from(window.selectedRecommendations); + const selectedRecommendations = selectedIndices.map(index => window.currentRecommendations[index]); + + try { + showLoading('smart-recommendations-container'); + + const results = []; + for (const rec of selectedRecommendations) { + try { + const response = await fetch('/api/v1/recommendations/apply', { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + }, + body: JSON.stringify({ + ...rec, + dry_run: false + }) + }); + + if (response.ok) { + const result = await response.json(); + results.push({ success: true, recommendation: rec.title, result }); + } else { + results.push({ success: false, recommendation: rec.title, error: 'Failed to apply' }); + } + } catch (error) { + results.push({ success: false, recommendation: rec.title, error: error.message }); + } + } + + // Show results + const successCount = results.filter(r => r.success).length; + const failCount = results.filter(r => !r.success).length; + + alert(`Applied ${successCount} recommendations successfully. ${failCount} failed.`); + + // Refresh recommendations + loadSmartRecommendations(); + + } catch (error) { + console.error('Error applying selected recommendations:', error); + alert('Error applying recommendations: ' + error.message); + } + } + + async function previewSelectedRecommendations() { + if (!window.selectedRecommendations || window.selectedRecommendations.size === 0) { + alert('No recommendations selected'); + return; + } + + const selectedIndices = Array.from(window.selectedRecommendations); + const selectedRecommendations = selectedIndices.map(index => window.currentRecommendations[index]); + + try { + const results = []; + for (const rec of selectedRecommendations) { + try { + const response = await fetch('/api/v1/recommendations/apply', { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + }, + body: JSON.stringify({ + ...rec, + dry_run: true + }) + }); + + if (response.ok) { + const result = await response.json(); + results.push({ success: true, recommendation: rec, result }); + } else { + results.push({ success: false, recommendation: rec, error: 'Failed to preview' }); + } + } catch (error) { + results.push({ success: false, recommendation: rec, error: error.message }); + } + } + + showRecommendationPreview(results); + + } catch (error) { + console.error('Error previewing selected recommendations:', error); + alert('Error previewing recommendations: ' + error.message); + } } // Load VPA management From c2338eefae13459563c4ac146df88da2119776a6 Mon Sep 17 00:00:00 2001 From: andersonid Date: Thu, 2 Oct 2025 19:23:51 -0300 Subject: [PATCH 22/26] fix: create individual cards per workload instead of aggregated card - Use data.categories instead of data.recommendations for individual workloads - Create separate ServiceCard for each workload with specific recommendations - Add priority scoring based on workload priority_score - Add detailed metadata: score, impact, age, VPA readiness - Generate specific titles and descriptions per workload type - Support different recommendation types: vpa_activation, resource_config, ratio_adjustment --- app/static/index.html | 145 +++++++++++++++++++++++++++--------------- 1 file changed, 92 insertions(+), 53 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index e3224ac..8ce718f 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -1480,10 +1480,10 @@ const container = document.getElementById('smart-recommendations-container'); // Store recommendations globally for button functions - window.currentRecommendations = data.recommendations || []; + window.currentRecommendations = data.categories || []; window.selectedRecommendations = new Set(); - if (!data || !data.recommendations || data.recommendations.length === 0) { + if (!data || !data.categories || data.categories.length === 0) { container.innerHTML = `
    @@ -1496,67 +1496,106 @@ } // Update bulk select counters - document.getElementById('total-recommendations').textContent = data.recommendations.length; - document.getElementById('page-recommendations').textContent = data.recommendations.length; + document.getElementById('total-recommendations').textContent = data.categories.length; + document.getElementById('page-recommendations').textContent = data.categories.length; - const recommendationsHtml = data.recommendations.map((rec, index) => ` -
    -
    -
    - + const recommendationsHtml = data.categories.map((workload, index) => { + // Determine priority based on priority_score + let priority = 'low'; + if (workload.priority_score >= 6) priority = 'high'; + else if (workload.priority_score >= 4) priority = 'medium'; + + // Determine recommendation type based on resource config status + let recommendationType = 'vpa_activation'; + let title = `Activate VPA for ${workload.workload_name}`; + let description = `Enable VPA for ${workload.workload_name} to get automatic resource recommendations based on usage patterns.`; + + if (workload.resource_config_status === 'missing_requests') { + recommendationType = 'resource_config'; + title = `Configure Resources for ${workload.workload_name}`; + description = `Add missing resource requests and limits for ${workload.workload_name} to improve resource management.`; + } else if (workload.resource_config_status === 'suboptimal_ratio') { + recommendationType = 'ratio_adjustment'; + title = `Optimize Resource Ratios for ${workload.workload_name}`; + description = `Adjust CPU to memory ratio for ${workload.workload_name} to optimize resource allocation.`; + } + + return ` +
    +
    +
    + +
    +

    ${title}

    +
    + +
    -

    ${rec.title}

    -
    - -
    -
    - -
    -

    ${rec.description}

    -
    -
    - - ${rec.workload_name || 'N/A'} +
    +

    ${description}

    + +
    +
    + + ${workload.workload_name} +
    +
    + + ${workload.namespace} +
    +
    + + ${recommendationType} +
    +
    + ${priority.toUpperCase()} +
    -
    - - ${rec.namespace || 'N/A'} -
    -
    - - ${rec.recommendation_type} -
    -
    - ${rec.priority.toUpperCase()} + +
    +
    + + Score: ${workload.priority_score}/10 +
    +
    + + Impact: ${workload.estimated_impact} +
    +
    + + Age: ${workload.age_days} days +
    +
    + + VPA Ready +
    -
    - -
    - ${rec.vpa_yaml ? ` - - ` : ''} - - - - + + + + +
    -
    - `).join(''); + `; + }).join(''); container.innerHTML = recommendationsHtml; updateBulkSelectUI(); From c81ba36b26eaa3f6f253cbdf6eac509e7e3af4a9 Mon Sep 17 00:00:00 2001 From: andersonid Date: Fri, 3 Oct 2025 06:37:35 -0300 Subject: [PATCH 23/26] fix: correct route name and health check endpoints in deployment - Fix route name mismatch: script was looking for 'resource-governance' but route is named 'resource-governance-route' - Fix health check endpoints: use /health instead of /api/v1/health for liveness/readiness probes - Add better error handling and route verification in deploy script - Add sleep delay to ensure route is ready before URL extraction - Show available routes if expected route is not found --- k8s/deployment.yaml | 4 ++-- scripts/deploy-complete.sh | 15 +++++++++++++-- 2 files changed, 15 insertions(+), 4 deletions(-) diff --git a/k8s/deployment.yaml b/k8s/deployment.yaml index 0b5e0c2..aa33a95 100644 --- a/k8s/deployment.yaml +++ b/k8s/deployment.yaml @@ -38,7 +38,7 @@ spec: protocol: TCP livenessProbe: httpGet: - path: /api/v1/health + path: /health port: 8080 initialDelaySeconds: 30 periodSeconds: 10 @@ -46,7 +46,7 @@ spec: failureThreshold: 3 readinessProbe: httpGet: - path: /api/v1/health + path: /health port: 8080 initialDelaySeconds: 15 # Aguarda mais tempo para inicializar periodSeconds: 5 diff --git a/scripts/deploy-complete.sh b/scripts/deploy-complete.sh index 144daaa..89156fa 100755 --- a/scripts/deploy-complete.sh +++ b/scripts/deploy-complete.sh @@ -88,11 +88,22 @@ fi # Obter URL da aplicação echo -e "${YELLOW}🌍 Getting application URL...${NC}" -ROUTE_URL=$(oc get route resource-governance -n $NAMESPACE -o jsonpath='{.spec.host}') + +# Aguardar um pouco para garantir que a rota esteja pronta +sleep 5 + +# Verificar se a rota existe +if oc get route resource-governance-route -n $NAMESPACE > /dev/null 2>&1; then + ROUTE_URL=$(oc get route resource-governance-route -n $NAMESPACE -o jsonpath='{.spec.host}') +else + echo -e "${YELLOW}⚠️ Route not found, checking available routes...${NC}" + oc get routes -n $NAMESPACE + ROUTE_URL="" +fi if [ -n "$ROUTE_URL" ]; then echo -e "${GREEN}✅ Application deployed successfully!${NC}" echo -e "${GREEN}🌐 URL: https://$ROUTE_URL${NC}" - echo -e "${GREEN}📊 Health check: https://$ROUTE_URL/api/v1/health${NC}" + echo -e "${GREEN}📊 Health check: https://$ROUTE_URL/health${NC}" else echo -e "${YELLOW}⚠️ Route not found, checking service...${NC}" oc get svc -n $NAMESPACE From 756cc439972ee09fe02a3dea8658633b099709a7 Mon Sep 17 00:00:00 2001 From: andersonid Date: Fri, 3 Oct 2025 07:04:58 -0300 Subject: [PATCH 24/26] cleanup: remove all Docker Hub references and update to Quay.io - Update deployment.yaml to reference Quay.io instead of Docker Hub - Remove Docker Hub references from README.md - Update build-and-push.sh to show Quay.io registry info - Update release.sh to reference Quay.io repository - Update push-to-internal-registry.sh to use Quay.io image - Clean up all Docker Hub comments and references - Registry is now exclusively Quay.io: quay.io/rh_ee_anobre/resource-governance --- README.md | 8 ++++---- k8s/deployment.yaml | 4 ++-- scripts/build-and-push.sh | 13 +++++++------ scripts/push-to-internal-registry.sh | 2 +- scripts/release.sh | 6 +++--- 5 files changed, 17 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index ba96ca9..acbb65d 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ A comprehensive tool for analyzing user workloads and resource usage in OpenShif - Prometheus (native in OCP) - VPA (optional, for recommendations) - Python 3.11+ -- Podman (preferred) or Docker +- Podman (preferred) - OpenShift CLI (oc) ## 🛠️ Installation @@ -290,13 +290,13 @@ podman build -t resource-governance . podman run -p 8080:8080 resource-governance ``` -### Run with Docker +### Run with Podman (Alternative) ```bash # Build -docker build -t resource-governance . +podman build -t resource-governance . # Run -docker run -p 8080:8080 resource-governance +podman run -p 8080:8080 resource-governance ``` ### Tests diff --git a/k8s/deployment.yaml b/k8s/deployment.yaml index aa33a95..0a7ea20 100644 --- a/k8s/deployment.yaml +++ b/k8s/deployment.yaml @@ -25,12 +25,12 @@ spec: spec: serviceAccountName: resource-governance-sa # imagePullSecrets: - # - name: docker-hub-secret + # - name: quay-secret # Only needed for private repositories securityContext: runAsNonRoot: true containers: - name: resource-governance - image: andersonid/resource-governance:latest + image: quay.io/rh_ee_anobre/resource-governance:latest imagePullPolicy: Always ports: - containerPort: 8080 diff --git a/scripts/build-and-push.sh b/scripts/build-and-push.sh index c1d8da9..e185cf2 100755 --- a/scripts/build-and-push.sh +++ b/scripts/build-and-push.sh @@ -13,7 +13,7 @@ NC='\033[0m' # No Color # Configurações IMAGE_NAME="resource-governance" TAG="${1:-latest}" -REGISTRY="${2:-andersonid}" +REGISTRY="${2:-quay.io/rh_ee_anobre}" FULL_IMAGE_NAME="${REGISTRY}/${IMAGE_NAME}:${TAG}" echo -e "${BLUE}🚀 Building and Pushing OpenShift Resource Governance Tool${NC}" @@ -49,9 +49,9 @@ else exit 1 fi -# Login no Docker Hub -echo -e "${YELLOW}🔐 Logging into Docker Hub...${NC}" -podman login docker.io +# Login no Quay.io +echo -e "${YELLOW}🔐 Logging into Quay.io...${NC}" +podman login -u="rh_ee_anobre+oru" -p="EJNIJD7FPO5IN33ZGQZ4OM8BIB3LICASBVRGOJCX4WP84Y0ZG5SMQLTZ0S6DOZEC" quay.io if [ $? -eq 0 ]; then echo -e "${GREEN}✅ Login successful!${NC}" @@ -61,7 +61,7 @@ else fi # Push da imagem -echo -e "${YELLOW}📤 Pushing image to Docker Hub...${NC}" +echo -e "${YELLOW}📤 Pushing image to Quay.io...${NC}" podman push "${FULL_IMAGE_NAME}" if [ $? -eq 0 ]; then @@ -76,5 +76,6 @@ echo -e "${BLUE}📊 Image information:${NC}" podman images "${FULL_IMAGE_NAME}" echo -e "${GREEN}🎉 Build and push completed successfully!${NC}" -echo -e "${BLUE}🌐 Image available at: https://hub.docker.com/r/${REGISTRY}/${IMAGE_NAME}${NC}" +echo -e "${BLUE}🌐 Image available at: https://quay.io/repository/${REGISTRY#quay.io/}/${IMAGE_NAME}${NC}" echo -e "${BLUE}🚀 Ready for deployment!${NC}" +echo -e "${BLUE}📋 Registry: Quay.io (public repository)${NC}" diff --git a/scripts/push-to-internal-registry.sh b/scripts/push-to-internal-registry.sh index 52b0632..042ad65 100755 --- a/scripts/push-to-internal-registry.sh +++ b/scripts/push-to-internal-registry.sh @@ -35,7 +35,7 @@ echo -e "${BLUE}📦 Registry URL: $REGISTRY_URL${NC}" # Tag da imagem FULL_IMAGE_NAME="$REGISTRY_URL/$NAMESPACE/$IMAGE_NAME:$TAG" echo -e "${YELLOW}🏷️ Criando tag: $FULL_IMAGE_NAME${NC}" -podman tag andersonid/resource-governance:simple $FULL_IMAGE_NAME +podman tag quay.io/rh_ee_anobre/resource-governance:latest $FULL_IMAGE_NAME # Push da imagem echo -e "${YELLOW}📤 Fazendo push da imagem...${NC}" diff --git a/scripts/release.sh b/scripts/release.sh index 013ab98..23e0f83 100755 --- a/scripts/release.sh +++ b/scripts/release.sh @@ -120,11 +120,11 @@ create_release() { echo "" echo "Useful links:" echo " GitHub: https://github.com/andersonid/openshift-resource-governance/releases/tag/$tag" - echo " Docker Hub: https://hub.docker.com/r/andersonid/resource-governance/tags" + echo " Quay.io: https://quay.io/repository/rh_ee_anobre/resource-governance" echo "" echo "GitHub Actions will automatically:" - echo " 1. Build Docker image" - echo " 2. Push to Docker Hub" + echo " 1. Build container image" + echo " 2. Push to Quay.io" echo " 3. Create GitHub release" echo "" echo "Wait a few minutes and check:" From b1c1a952d10154725ab30e1bd11983e5f532fb3a Mon Sep 17 00:00:00 2001 From: andersonid Date: Fri, 3 Oct 2025 07:11:57 -0300 Subject: [PATCH 25/26] update: change app title to ORU Scanner and update home page title - Change browser title to 'ORU Scanner - OpenShift Resource Usage Scanner' - Update header logo to 'ORU Scanner' - Change home page title to 'OpenShift Resource Usage Scanner - Dashboard' - Simplify page description for better clarity --- app/static/index.html | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index 8ce718f..7656693 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -3,7 +3,7 @@ - UWRU Scanner - User Workloads and Resource Usage Scanner + ORU Scanner - OpenShift Resource Usage Scanner @@ -1008,7 +1008,7 @@
    - +
    @@ -1116,8 +1116,8 @@
    -

    UWRU Scanner

    -

    User Workloads and Resource Usage Scanner - Identify and analyze workloads with resource configuration issues

    +

    OpenShift Resource Usage Scanner - Dashboard

    +

    Identify and analyze workloads with resource configuration issues

    From 2e9ed3e7b35e070f337e8777fbb96f64650429a8 Mon Sep 17 00:00:00 2001 From: andersonid Date: Fri, 3 Oct 2025 07:18:45 -0300 Subject: [PATCH 26/26] fix: format Resource Utilization to show only 1 decimal place - Update resource utilization display to use .toFixed(1) for better readability - Apply formatting to both main dashboard and modal details - Change from 266.04049998033537% to 266.0% for human readability - Improve user experience with cleaner number formatting --- app/static/index.html | 4 ++-- k8s/route.yaml | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/app/static/index.html b/app/static/index.html index 7656693..7595341 100644 --- a/app/static/index.html +++ b/app/static/index.html @@ -2165,7 +2165,7 @@ document.getElementById('cpu-overcommit').textContent = `${data.overcommit.cpu_overcommit_percent || 0}%`; document.getElementById('memory-overcommit').textContent = `${data.overcommit.memory_overcommit_percent || 0}%`; document.getElementById('namespaces-in-overcommit').textContent = data.overcommit.namespaces_in_overcommit || 0; - document.getElementById('resource-utilization').textContent = `${data.overcommit.resource_utilization || 0}%`; + document.getElementById('resource-utilization').textContent = `${(data.overcommit.resource_utilization || 0).toFixed(1)}%`; // Store overcommit data for modal display window.overcommitData = data.overcommit; @@ -2640,7 +2640,7 @@ Formula: (Total Usage ÷ Total Requests) × 100
    - Current Value: ${window.overcommitData?.resource_utilization || 0}% (real-time data from Prometheus) + Current Value: ${(window.overcommitData?.resource_utilization || 0).toFixed(1)}% (real-time data from Prometheus)
    Data Source: diff --git a/k8s/route.yaml b/k8s/route.yaml index c637038..21bbcb5 100644 --- a/k8s/route.yaml +++ b/k8s/route.yaml @@ -10,6 +10,7 @@ metadata: haproxy.router.openshift.io/timeout: "300s" haproxy.router.openshift.io/rate-limit: "100" spec: + host: oru.apps.shrocp4upi419ovn.lab.upshift.rdu2.redhat.com to: kind: Service name: resource-governance-service