Expose more information on server process pages

LICENSE

@@ -309,4 +309,12 @@ Files (in server/monitor/src/main/resources/):
     Copyright (c) 2008-2024 SpryMedia Ltd
     Licensed under the MIT license (see above)
 
+## DataTables ColReorder 1.7.0 (https://datatables.net)
+
+Files (in server/monitor/src/main/resources/):
+* org/apache/accumulo/monitor/resources/external/datatables/**/*
+
+    Copyright (c) 2010-2015 SpryMedia Limited
+    Licensed under the MIT license (see above)
+
 **********

server/base/src/main/java/org/apache/accumulo/server/AbstractServer.java

@@ -21,6 +21,9 @@
 import static java.util.concurrent.TimeUnit.MILLISECONDS;
 
 import java.net.UnknownHostException;
+import java.util.EnumMap;
+import java.util.List;
+import java.util.Map;
 import java.util.OptionalInt;
 import java.util.concurrent.ScheduledFuture;
 import java.util.concurrent.atomic.AtomicBoolean;
@@ -96,6 +99,11 @@ public static void startServer(AbstractServer server, Logger LOG) throws Excepti
   private final AtomicBoolean shutdownComplete = new AtomicBoolean(false);
   private final AtomicBoolean closed = new AtomicBoolean(false);
 
+  // Map of MetricSource to list of excluded metrics for that type
+  // Metrics in the List will not be included in the response
+  // for the server type in the getMetrics call.
+  private final Map<MetricSource,List<String>> excludedMetrics = new EnumMap<>(MetricSource.class);
+
   protected AbstractServer(ServerId.Type serverType, ServerOpts opts,
       BiFunction<SiteConfiguration,ResourceGroupId,ServerContext> serverContextFactory,
       String[] args) {
@@ -177,6 +185,12 @@ protected AbstractServer(ServerId.Type serverType, ServerOpts opts,
       default:
         throw new IllegalArgumentException("Unhandled server type: " + serverType);
     }
+    excludedMetrics.put(MetricSource.COMPACTOR,
+        List.of("accumulo.compaction.minc.paused", "accumulo.recoveries.avg.progress",
+            "accumulo.recoveries.in.progress", "accumulo.recoveries.runtime.longest"));
+    excludedMetrics.put(MetricSource.SCAN_SERVER, List.of("accumulo.recoveries.avg.progress",
+        "accumulo.recoveries.in.progress", "accumulo.recoveries.runtime.longest"));
+    excludedMetrics.put(MetricSource.TABLET_SERVER, List.of("accumulo.compaction.majc.paused"));
   }
 
   /**
@@ -401,12 +415,15 @@ public MetricResponse getMetrics(TInfo tinfo, TCredentials credentials) throws T
     response.setTimestamp(System.currentTimeMillis());
 
     if (context.getMetricsInfo().isMetricsEnabled()) {
+      final List<String> exclusions = excludedMetrics.get(metricSource);
       Metrics.globalRegistry.getMeters().forEach(m -> {
         if (m.getId().getName().startsWith("accumulo.")) {
-          m.match(response::writeMeter, response::writeMeter, response::writeTimer,
-              response::writeDistributionSummary, response::writeLongTaskTimer,
-              response::writeMeter, response::writeMeter, response::writeFunctionTimer,
-              response::writeMeter);
+          if (exclusions == null || !exclusions.contains(m.getId().getName())) {
+            m.match(response::writeMeter, response::writeMeter, response::writeTimer,
+                response::writeDistributionSummary, response::writeLongTaskTimer,
+                response::writeMeter, response::writeMeter, response::writeFunctionTimer,
+                response::writeMeter);
+          }
         }
       });
     }

server/monitor/pom.xml

@@ -54,6 +54,10 @@
       <groupId>com.github.ben-manes.caffeine</groupId>
       <artifactId>caffeine</artifactId>
     </dependency>
+    <dependency>
+      <groupId>com.google.code.gson</groupId>
+      <artifactId>gson</artifactId>
+    </dependency>
     <dependency>
       <groupId>com.google.guava</groupId>
       <artifactId>guava</artifactId>
@@ -216,6 +220,26 @@
   <build>
     <pluginManagement>
       <plugins>
+        <plugin>
+          <groupId>org.codehaus.mojo</groupId>
+          <artifactId>exec-maven-plugin</artifactId>
+          <executions>
+            <execution>
+              <id>metrics-javascript</id>
+              <goals>
+                <goal>java</goal>
+              </goals>
+              <phase>prepare-package</phase>
+              <configuration>
+                <mainClass>org.apache.accumulo.monitor.next.views.ColumnJsGen</mainClass>
+                <classpathScope>compile</classpathScope>
+                <arguments>
+                  <argument>${project.build.directory}/classes/org/apache/accumulo/monitor/resources/js/columns.js</argument>
+                </arguments>
+              </configuration>
+            </execution>
+          </executions>
+        </plugin>
         <plugin>
           <groupId>com.mycila</groupId>
           <artifactId>license-maven-plugin</artifactId>

server/monitor/src/main/java/org/apache/accumulo/monitor/next/Endpoints.java

@@ -33,6 +33,7 @@
 import jakarta.inject.Inject;
 import jakarta.servlet.http.HttpServletRequest;
 import jakarta.ws.rs.GET;
+import jakarta.ws.rs.MatrixParam;
 import jakarta.ws.rs.NotFoundException;
 import jakarta.ws.rs.Path;
 import jakarta.ws.rs.PathParam;
@@ -54,20 +55,25 @@
 import org.apache.accumulo.monitor.next.deployment.DeploymentOverview;
 import org.apache.accumulo.monitor.next.ec.CompactorsSummary;
 import org.apache.accumulo.monitor.next.ec.CoordinatorSummary;
-import org.apache.accumulo.monitor.next.sservers.ScanServerView;
+import org.apache.accumulo.monitor.next.views.ServersView;
 
 import io.micrometer.core.instrument.Meter.Id;
 import io.micrometer.core.instrument.cumulative.CumulativeDistributionSummary;
 
 @Path("/")
 public class Endpoints {
   /**
-   * A {@code String} constant representing supplied resource group in path parameter.
+   * A {@code String} constant representing the supplied resource group in path parameter.
    */
   private static final String GROUP_PARAM_KEY = "group";
 
   /**
-   * A {@code String} constant representing supplied tableId in path parameter.
+   * A {@code String} constant representing the supplied server type in path parameter.
+   */
+  private static final String SERVER_TYPE_KEY = "serverType";
+
+  /**
+   * A {@code String} constant representing the supplied tableId in path parameter.
    */
   private static final String TABLEID_PARAM_KEY = "tableId";
 
@@ -271,11 +277,17 @@ public Map<Id,CumulativeDistributionSummary> getScanServerAllMetricSummary() {
   }
 
   @GET
-  @Path("sservers/view")
+  @Path("servers/view")
   @Produces(MediaType.APPLICATION_JSON)
-  @Description("Returns a UI-ready view model for the Scan Server status page")
-  public ScanServerView getScanServerPageView() {
-    return monitor.getInformationFetcher().getSummaryForEndpoint().getScanServerView();
+  @Description("Returns a UI-ready view model for server processes. Add ';serverType=<ServerId.Type>' to URL")
+  public ServersView getServerProcessView(@MatrixParam(SERVER_TYPE_KEY) ServerId.Type serverType) {
+    ServersView view =
+        monitor.getInformationFetcher().getSummaryForEndpoint().getServerProcessView(serverType);
+    if (view == null) {
+      throw new NotFoundException(
+          "ServersView object for server type " + serverType.name() + " not found");
+    }
+    return view;
   }
 
   @GET

server/monitor/src/main/java/org/apache/accumulo/monitor/next/InformationFetcher.java

@@ -211,7 +211,7 @@ public void newConnectionEvent() {
   }
 
   // Protect against NPE and wait for initial data gathering
-  public SystemInformation getSummary() throws InterruptedException {
+  private SystemInformation getSummary() throws InterruptedException {
     while (summaryRef.get() == null) {
       Thread.sleep(100);
     }
@@ -254,7 +254,7 @@ public void onRemoval(@Nullable ServerId server, @Nullable MetricResponse respon
   @Override
   public void run() {
 
-    long refreshTime = 0;
+    long lastRunTime = 0;
 
     while (true) {
 
@@ -263,7 +263,7 @@ public void run() {
       // If a connection has not been made in a while, stale data may be displayed.
       // Only refresh every 5s (old monitor logic).
       while (!newConnectionEvent.get() && connectionCount.get() == 0
-          && NanoTime.millisElapsed(refreshTime, NanoTime.now()) > 5000) {
+          && NanoTime.millisElapsed(lastRunTime, NanoTime.now()) > 5000) {
         try {
           Thread.sleep(100);
         } catch (InterruptedException e) {
@@ -275,7 +275,7 @@ public void run() {
       // reset the connection event flag
       newConnectionEvent.compareAndExchange(true, false);
 
-      LOG.info("Fetching metrics from servers");
+      LOG.info("Fetching information from servers");
 
       final List<Future<?>> futures = new ArrayList<>();
       final SystemInformation summary = new SystemInformation(allMetrics, this.ctx);
@@ -315,13 +315,18 @@ public void run() {
         }
       }));
 
-      long monitorFetchTimeout =
+      final long monitorFetchTimeout =
           ctx.getConfiguration().getTimeInMillis(Property.MONITOR_FETCH_TIMEOUT);
-      long allFuturesAdded = NanoTime.now();
+      final long allFuturesAdded = NanoTime.now();
       boolean tookToLong = false;
       while (!futures.isEmpty()) {
 
         if (NanoTime.millisElapsed(allFuturesAdded, NanoTime.now()) > monitorFetchTimeout) {
+          LOG.warn(
+              "Fetching information for Monitor has taken longer {}. Cancelling all"
+                  + " remaining tasks and monitor will display old information. Resolve issue"
+                  + " causing this or increase property {}.",
+              monitorFetchTimeout, Property.MONITOR_FETCH_TIMEOUT.getKey());
           tookToLong = true;
         }
 
@@ -344,26 +349,31 @@ public void run() {
         }
       }
 
-      summary.finish();
-
-      refreshTime = NanoTime.now();
-      LOG.info("Finished fetching metrics from servers");
-      LOG.info(
-          "All: {}, Manager: {}, Garbage Collector: {}, Compactors: {}, Scan Servers: {}, Tablet Servers: {}",
-          allMetrics.estimatedSize(), summary.getManager() != null,
-          summary.getGarbageCollector() != null,
-          summary.getCompactorAllMetricSummary().isEmpty() ? 0
-              : summary.getCompactorAllMetricSummary().entrySet().iterator().next().getValue()
-                  .count(),
-          summary.getSServerAllMetricSummary().isEmpty() ? 0
-              : summary.getSServerAllMetricSummary().entrySet().iterator().next().getValue()
-                  .count(),
-          summary.getTServerAllMetricSummary().isEmpty() ? 0 : summary.getTServerAllMetricSummary()
-              .entrySet().iterator().next().getValue().count());
-
-      SystemInformation oldSummary = summaryRef.getAndSet(summary);
-      if (oldSummary != null) {
-        oldSummary.clear();
+      lastRunTime = NanoTime.now();
+
+      if (tookToLong) {
+        summary.clear();
+      } else {
+        summary.finish();
+
+        LOG.info("Finished fetching metrics from servers");
+        LOG.info(
+            "All: {}, Manager: {}, Garbage Collector: {}, Compactors: {}, Scan Servers: {}, Tablet Servers: {}",
+            allMetrics.estimatedSize(), summary.getManager() != null,
+            summary.getGarbageCollector() != null,
+            summary.getCompactorAllMetricSummary().isEmpty() ? 0
+                : summary.getCompactorAllMetricSummary().entrySet().iterator().next().getValue()
+                    .count(),
+            summary.getSServerAllMetricSummary().isEmpty() ? 0
+                : summary.getSServerAllMetricSummary().entrySet().iterator().next().getValue()
+                    .count(),
+            summary.getTServerAllMetricSummary().isEmpty() ? 0 : summary
+                .getTServerAllMetricSummary().entrySet().iterator().next().getValue().count());
+
+        SystemInformation oldSummary = summaryRef.getAndSet(summary);
+        if (oldSummary != null) {
+          oldSummary.clear();
+        }
       }
     }