Merge pull request #482 from ClusterCockpit/dev

Dev

configs/tagger/apps/vasp.txt

@@ -1,2 +1,3 @@
-vasp
-VASP
+vasp_gam
+vasp_ncl
+vasp_std

internal/api/node.go

@@ -15,6 +15,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	"github.com/ClusterCockpit/cc-backend/pkg/metricstore"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
@@ -81,6 +82,8 @@ func (api *RestAPI) updateNodeStates(rw http.ResponseWriter, r *http.Request) {
 	m := make(map[string][]string)
 	healthStates := make(map[string]schema.MonitoringState)
 
+	startMs := time.Now()
+
 	for _, node := range req.Nodes {
 		if sc, err := archive.GetSubClusterByNode(req.Cluster, node.Hostname); err == nil {
 			m[sc] = append(m[sc], node.Hostname)
@@ -97,6 +100,9 @@ func (api *RestAPI) updateNodeStates(rw http.ResponseWriter, r *http.Request) {
 		}
 	}
 
+	cclog.Infof("Timer updateNodeStates, MemStore HealthCheck: %s", time.Since(startMs))
+	startDb := time.Now()
+
 	for _, node := range req.Nodes {
 		state := determineState(node.States)
 		healthState := schema.MonitoringStateFailed
@@ -115,4 +121,6 @@ func (api *RestAPI) updateNodeStates(rw http.ResponseWriter, r *http.Request) {
 
 		repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState)
 	}
+
+	cclog.Infof("Timer updateNodeStates, SQLite Inserts: %s", time.Since(startDb))
 }

internal/api/rest.go

@@ -81,7 +81,7 @@ func (api *RestAPI) MountAPIRoutes(r *mux.Router) {
 	// Cluster List
 	r.HandleFunc("/clusters/", api.getClusters).Methods(http.MethodGet)
 	// Slurm node state
-	r.HandleFunc("/nodestates/", api.updateNodeStates).Methods(http.MethodPost, http.MethodPut)
+	r.HandleFunc("/nodestate/", api.updateNodeStates).Methods(http.MethodPost, http.MethodPut)
 	// Job Handler
 	if config.Keys.APISubjects == nil {
 		cclog.Info("Enabling REST start/stop job API")

internal/repository/node.go

@@ -198,7 +198,6 @@ func (r *NodeRepository) UpdateNodeState(hostname string, cluster string, nodeSt
 			}
 
 			cclog.Debugf("Added node '%s' to database", hostname)
-			return nil
 		} else {
 			cclog.Warnf("Error while querying node '%v' from database", id)
 			return err

pkg/metricstore/healthcheck.go

@@ -11,6 +11,7 @@ import (
 	"slices"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
@@ -244,7 +245,16 @@ func (m *MemoryStore) HealthCheck(cluster string,
 
 		missingCount = len(missingList)
 		degradedCount = len(degradedList)
-		healthyCount = len(expectedMetrics) - (missingCount + degradedCount)
+		uniqueList := mergeList(missingList, degradedList)
+		healthyCount = len(expectedMetrics) - len(uniqueList)
+
+		// Debug log missing and degraded metrics
+		if missingCount > 0 {
+			cclog.ComponentDebug("metricstore", "HealthCheck: node", hostname, "missing metrics:", missingList)
+		}
+		if degradedCount > 0 {
+			cclog.ComponentDebug("metricstore", "HealthCheck: node", hostname, "degraded metrics:", degradedList)
+		}
 
 		// Determine overall health status
 		if missingCount > 0 || degradedCount > 0 {

web/frontend/src/List.root.svelte

@@ -319,11 +319,11 @@
         <tr>
           <td>
             {#if type == "USER"}
-              <a href="/monitoring/user/{row.id}"
+              <a href="/monitoring/user/{row.id}{fetchRunning ? '?state=running' : ''}"
                 >{scrambleNames ? scramble(row.id) : row.id}</a
               >
             {:else if type == "PROJECT"}
-              <a href="/monitoring/jobs/?project={row.id}"
+              <a href="/monitoring/jobs/?project={row.id}{fetchRunning ? '&state=running' : ''}"
                 >{scrambleNames ? scramble(row.id) : row.id}</a
               >
             {:else}

web/frontend/src/User.root.svelte

@@ -19,7 +19,8 @@
     Spinner,
     Input,
     InputGroup,
-    InputGroupText
+    InputGroupText,
+    Tooltip
   } from "@sveltestrap/sveltestrap";
   import {
     queryStore,
@@ -32,6 +33,10 @@
     scramble,
     scrambleNames,
   } from "./generic/utils.js";
+  import {
+    formatNumber,
+    formatDurationTime
+  } from "./generic/units.js";
   import JobList from "./generic/JobList.svelte";
   import JobCompare from "./generic/JobCompare.svelte";
   import Filters from "./generic/Filters.svelte";
@@ -56,6 +61,7 @@
   const durationBinOptions = ["1m","10m","1h","6h","12h"];
   const metricBinOptions = [10, 20, 50, 100];
   const matchedJobCompareLimit = 500;
+  const shortDuration = ccconfig.jobList_hideShortRunningJobs; // Always configured
 
   /* State Init */
   // List & Control Vars
@@ -108,6 +114,7 @@
             shortJobs
             totalWalltime
             totalCoreHours
+            totalAccHours
             histDuration {
               count
               value
@@ -133,6 +140,7 @@
       variables: { jobFilters, selectedHistograms, numDurationBins, numMetricBins },
     })
   );
+  const hasAccHours = $derived($stats?.data?.jobsStatistics[0]?.totalAccHours != 0);
 
   /* Functions */
   function resetJobSelection() {
@@ -290,20 +298,54 @@
             {/if}
             <tr>
               <th scope="row">Total Jobs</th>
-              <td>{$stats.data.jobsStatistics[0].totalJobs}</td>
+              <td>
+                <span style="cursor: help;" title="{$stats.data.jobsStatistics[0].totalJobs} Jobs">
+                  {formatNumber($stats.data.jobsStatistics[0].totalJobs)} Jobs
+                </span>
+              </td>
             </tr>
             <tr>
-              <th scope="row">Short Jobs</th>
-              <td>{$stats.data.jobsStatistics[0].shortJobs}</td>
+              <th scope="row">        
+                <span class="mr-1">
+                  Short Jobs
+                 <Icon name="info-circle" id="shortjobs-info" style="margin-left:5px; cursor:help;"/>
+                </span>
+                <Tooltip target={`shortjobs-info`} placement="right">
+                  Job duration less than {formatDurationTime(shortDuration)}
+                </Tooltip>
+              </th>
+              <td>
+                <span style="cursor: help;" title="{$stats.data.jobsStatistics[0].shortJobs} Jobs">
+                  {formatNumber($stats.data.jobsStatistics[0].shortJobs)} Jobs
+                </span>
+              </td>
             </tr>
             <tr>
               <th scope="row">Total Walltime</th>
-              <td>{$stats.data.jobsStatistics[0].totalWalltime}</td>
+              <td>
+                <span style="cursor: help;" title="{$stats.data.jobsStatistics[0].totalWalltime} Hours">
+                  {formatNumber($stats.data.jobsStatistics[0].totalWalltime)} Hours
+                </span>
+              </td>
             </tr>
             <tr>
               <th scope="row">Total Core Hours</th>
-              <td>{$stats.data.jobsStatistics[0].totalCoreHours}</td>
+              <td>
+                <span style="cursor: help;" title="{$stats.data.jobsStatistics[0].totalCoreHours} Hours">
+                  {formatNumber($stats.data.jobsStatistics[0].totalCoreHours)} Hours
+                </span>
+              </td>
             </tr>
+            {#if hasAccHours}
+              <tr>
+                <th scope="row">Total Accelerator Hours</th>
+                <td>
+                  <span style="cursor: help;" title="{$stats.data.jobsStatistics[0].totalAccHours} Hours">
+                    {formatNumber($stats.data.jobsStatistics[0].totalAccHours)} Hours
+                  </span>
+                </td>
+              </tr>
+            {/if}
           </tbody>
         </Table>
       </Col>
@@ -316,6 +358,7 @@
             xunit="Runtime"
             ylabel="Number of Jobs"
             yunit="Jobs"
+            height={hasAccHours ? 290 : 250}
             usesBins
             xtime
           />
@@ -330,6 +373,7 @@
             xunit="Nodes"
             ylabel="Number of Jobs"
             yunit="Jobs"
+            height={hasAccHours ? 290 : 250}
           />
         {/key}
       </Col>

web/frontend/src/generic/joblist/JobListRow.svelte

@@ -79,7 +79,6 @@
 
   /* Derived */
   const jobId = $derived(job?.id);
-  const refinedData = $derived($metricsQuery?.data?.jobMetrics ? sortAndSelectScope($metricsQuery.data.jobMetrics) : []);
   const scopes = $derived.by(() => {
     if (job.numNodes == 1) {
       if (job.numAcc >= 1) return ["core", "accelerator"];
@@ -95,6 +94,7 @@
       variables: { id: jobId, metrics, scopes, selectedResolution },
     })
   );
+  const refinedData = $derived($metricsQuery?.data?.jobMetrics ? sortAndSelectScope($metricsQuery.data.jobMetrics) : []);
 
   /* Effects */
   $effect(() => {

web/frontend/src/generic/units.js

@@ -32,10 +32,6 @@ export function scaleNumber(x, p = '') {
     }
 }
 
-export function roundTwoDigits(x) {
-    return Math.round(x * 100) / 100
-}
-
 export function scaleNumbers(x, y, p = '') {
     const oldPower  = power[prefix.indexOf(p)]
     const rawXValue = x * oldPower 
@@ -77,6 +73,10 @@ export function formatUnixTime(t, withDate = false) {
     }
 }
 
+export function roundTwoDigits(x) {
+    return Math.round(x * 100) / 100
+}
+
 // const equalsCheck = (a, b) => {
 //   return JSON.stringify(a) === JSON.stringify(b);
 // }