Merge branch 'main' into 4973-new-monitor-metrics

assemble/bin/accumulo-service

@@ -60,14 +60,14 @@ function rotate_log() {
 
 function get_group() {
   # Find the group parameter if any
-  GROUP_PATTERN="^(compactor.group|sserver.group|tserver.group)=(.*)$"
-  group="default"
+  local group="default"
+  local param
   for param in "$@"; do
-    if [[ $param =~ $GROUP_PATTERN ]]; then
-      group="${BASH_REMATCH[2]}"
+    if [[ $param =~ ^[a-z]*[.]group=(.*)$ ]]; then
+      group="${BASH_REMATCH[1]}"
     fi
   done
-  echo "${group}"
+  echo "$group"
 }
 
 function start_service() {
@@ -111,7 +111,7 @@ function start_service() {
     rotate_log "$outfile"
     rotate_log "$errfile"
 
-    nohup "${bin}/accumulo" "$service_type" "$@" "${PROPERTY_OVERRIDES[@]}" >"$outfile" 2>"$errfile" </dev/null &
+    nohup "${bin}/accumulo" "$service_type" "$@" >"$outfile" 2>"$errfile" </dev/null &
     echo "$!" >"${pid_file}"
 
   done

assemble/conf/accumulo-env.sh

@@ -104,7 +104,7 @@ case "${ACCUMULO_RESOURCE_GROUP:-default}" in
     esac
     ;;
   *)
-    echo "ACCUMULO_RESOURCE_GROUP named $ACCUMULO_RESOURCE_GROUP is not configured"
+    echo "ACCUMULO_RESOURCE_GROUP named $ACCUMULO_RESOURCE_GROUP is not configured in accumulo-env.sh"
     exit 1
     ;;
 esac

core/src/main/java/org/apache/accumulo/core/conf/Property.java

@@ -426,7 +426,7 @@ public enum Property {
   MANAGER_FATE_METRICS_MIN_UPDATE_INTERVAL("manager.fate.metrics.min.update.interval", "60s",
       PropertyType.TIMEDURATION, "Limit calls from metric sinks to zookeeper to update interval.",
       "1.9.3"),
-  MANAGER_FATE_THREADPOOL_SIZE("manager.fate.threadpool.size", "4", PropertyType.COUNT,
+  MANAGER_FATE_THREADPOOL_SIZE("manager.fate.threadpool.size", "64", PropertyType.COUNT,
       "The number of threads used to run fault-tolerant executions (FATE)."
           + " These are primarily table operations like merge.",
       "1.4.3"),
@@ -480,57 +480,44 @@ public enum Property {
           + " as un-splittable.",
       "3.1.0"),
   // properties that are specific to scan server behavior
-  @Experimental
   SSERV_PREFIX("sserver.", null, PropertyType.PREFIX,
       "Properties in this category affect the behavior of the scan servers.", "2.1.0"),
-  @Experimental
   SSERV_DATACACHE_SIZE("sserver.cache.data.size", "10%", PropertyType.MEMORY,
       "Specifies the size of the cache for RFile data blocks on each scan server.", "2.1.0"),
-  @Experimental
   SSERV_INDEXCACHE_SIZE("sserver.cache.index.size", "25%", PropertyType.MEMORY,
       "Specifies the size of the cache for RFile index blocks on each scan server.", "2.1.0"),
-  @Experimental
   SSERV_SUMMARYCACHE_SIZE("sserver.cache.summary.size", "10%", PropertyType.MEMORY,
       "Specifies the size of the cache for summary data on each scan server.", "2.1.0"),
-  @Experimental
   SSERV_DEFAULT_BLOCKSIZE("sserver.default.blocksize", "1M", PropertyType.BYTES,
       "Specifies a default blocksize for the scan server caches.", "2.1.0"),
-  @Experimental
   SSERV_GROUP_NAME("sserver.group", ScanServerSelector.DEFAULT_SCAN_SERVER_GROUP_NAME,
       PropertyType.STRING,
       "Resource group name for this ScanServer. Resource groups support at least two use cases:"
           + " dedicating resources to scans and/or using different hardware for scans. Clients can"
           + " configure the ConfigurableScanServerSelector to specify the resource group to use for"
           + " eventual consistency scans.",
       "3.0.0"),
-  @Experimental
   SSERV_CACHED_TABLET_METADATA_EXPIRATION("sserver.cache.metadata.expiration", "5m",
       PropertyType.TIMEDURATION,
       "The time after which cached tablet metadata will be expired if not previously refreshed.",
       "2.1.0"),
-  @Experimental
   SSERV_CACHED_TABLET_METADATA_REFRESH_PERCENT("sserver.cache.metadata.refresh.percent", ".75",
       PropertyType.FRACTION,
       "The time after which cached tablet metadata will be refreshed, expressed as a "
           + "percentage of the expiration time. Cache hits after this time, but before the "
           + "expiration time, will trigger a background refresh for future hits. "
           + "Value must be less than 100%. Set to 0 will disable refresh.",
       "2.1.3"),
-  @Experimental
   SSERV_PORTSEARCH("sserver.port.search", "true", PropertyType.BOOLEAN,
       "if the sserver.port.client ports are in use, search higher ports until one is available.",
       "2.1.0"),
-  @Experimental
   SSERV_CLIENTPORT("sserver.port.client", "9996", PropertyType.PORT,
       "The port used for handling client connections on the tablet servers.", "2.1.0"),
-  @Experimental
   SSERV_MINTHREADS("sserver.server.threads.minimum", "2", PropertyType.COUNT,
       "The minimum number of threads to use to handle incoming requests.", "2.1.0"),
-  @Experimental
   SSERV_MINTHREADS_TIMEOUT("sserver.server.threads.timeout", "0s", PropertyType.TIMEDURATION,
       "The time after which incoming request threads terminate with no work available.  Zero (0) will keep the threads alive indefinitely.",
       "2.1.0"),
-  @Experimental
   SSERV_SCAN_EXECUTORS_PREFIX("sserver.scan.executors.", null, PropertyType.PREFIX,
       "Prefix for defining executors to service scans. See "
           + "[scan executors]({% durl administration/scan-executors %}) for an overview of why and"
@@ -541,7 +528,6 @@ public enum Property {
           + "`sserver.scan.executors.<name>.prioritizer=<class name>`, and "
           + "`sserver.scan.executors.<name>.prioritizer.opts.<key>=<value>`.",
       "2.1.0"),
-  @Experimental
   SSERV_SCAN_EXECUTORS_DEFAULT_THREADS("sserver.scan.executors.default.threads", "16",
       PropertyType.COUNT, "The number of threads for the scan executor that tables use by default.",
       "2.1.0"),
@@ -551,18 +537,14 @@ public enum Property {
           + "results in FIFO priority.  Set to a class that implements "
           + ScanPrioritizer.class.getName() + " to configure one.",
       "2.1.0"),
-  @Experimental
   SSERV_SCAN_EXECUTORS_META_THREADS("sserver.scan.executors.meta.threads", "8", PropertyType.COUNT,
       "The number of threads for the metadata table scan executor.", "2.1.0"),
-  @Experimental
   SSERV_SCAN_REFERENCE_EXPIRATION_TIME("sserver.scan.reference.expiration", "5m",
       PropertyType.TIMEDURATION,
       "The amount of time a scan reference is unused before its deleted from metadata table.",
       "2.1.0"),
-  @Experimental
   SSERV_THREADCHECK("sserver.server.threadcheck.time", "1s", PropertyType.TIMEDURATION,
       "The time between adjustments of the thrift server thread pool.", "2.1.0"),
-  @Experimental
   SSERV_WAL_SORT_MAX_CONCURRENT("sserver.wal.sort.concurrent.max", "2", PropertyType.COUNT,
       "The maximum number of threads to use to sort logs during recovery.", "4.0.0"),
   // properties that are specific to tablet server behavior
@@ -1153,7 +1135,6 @@ public enum Property {
           + "constraint.",
       "2.0.0"),
   // Compactor properties
-  @Experimental
   COMPACTOR_PREFIX("compactor.", null, PropertyType.PREFIX,
       "Properties in this category affect the behavior of the accumulo compactor server.", "2.1.0"),
   COMPACTOR_CANCEL_CHECK_INTERVAL("compactor.cancel.check.interval", "5m",
@@ -1162,11 +1143,9 @@ public enum Property {
           + " should be cancelled. This checks for situations like was the tablet deleted (split "
           + " and merge do this), was the table deleted, was a user compaction canceled, etc.",
       "2.1.4"),
-  @Experimental
   COMPACTOR_PORTSEARCH("compactor.port.search", "true", PropertyType.BOOLEAN,
       "If the compactor.port.client ports are in use, search higher ports until one is available.",
       "2.1.0"),
-  @Experimental
   COMPACTOR_CLIENTPORT("compactor.port.client", "9133", PropertyType.PORT,
       "The port used for handling client connections on the compactor servers.", "2.1.0"),
   COMPACTOR_MIN_JOB_WAIT_TIME("compactor.wait.time.job.min", "1s", PropertyType.TIMEDURATION,
@@ -1177,21 +1156,16 @@ public enum Property {
       "Compactors do exponential backoff when their request for work repeatedly come back empty. "
           + "This is the maximum amount of time to wait between checks for the next compaction job.",
       "2.1.3"),
-  @Experimental
   COMPACTOR_MINTHREADS("compactor.threads.minimum", "1", PropertyType.COUNT,
       "The minimum number of threads to use to handle incoming requests.", "2.1.0"),
-  @Experimental
   COMPACTOR_MINTHREADS_TIMEOUT("compactor.threads.timeout", "0s", PropertyType.TIMEDURATION,
       "The time after which incoming request threads terminate with no work available.  Zero (0) will keep the threads alive indefinitely.",
       "2.1.0"),
-  @Experimental
   COMPACTOR_THREADCHECK("compactor.threadcheck.time", "1s", PropertyType.TIMEDURATION,
       "The time between adjustments of the server thread pool.", "2.1.0"),
-  @Experimental
   COMPACTOR_GROUP_NAME("compactor.group", Constants.DEFAULT_RESOURCE_GROUP_NAME,
       PropertyType.STRING, "Resource group name for this Compactor.", "3.0.0"),
   // CompactionCoordinator properties
-  @Experimental
   COMPACTION_COORDINATOR_PREFIX("compaction.coordinator.", null, PropertyType.PREFIX,
       "Properties in this category affect the behavior of the accumulo compaction coordinator server.",
       "2.1.0"),
@@ -1207,7 +1181,6 @@ public enum Property {
       "64", PropertyType.COUNT,
       "The number of threads used to reserve files for compaction in a tablet for user tables.",
       "4.0.0"),
-  @Experimental
   COMPACTION_COORDINATOR_DEAD_COMPACTOR_CHECK_INTERVAL(
       "compaction.coordinator.compactor.dead.check.interval", "5m", PropertyType.TIMEDURATION,
       "The interval at which to check for dead compactors.", "2.1.0");

core/src/main/java/org/apache/accumulo/core/fate/zookeeper/DistributedReadWriteLock.java

@@ -142,7 +142,8 @@ public void lock() {
             return;
           }
         } catch (InterruptedException ex) {
-          // ignored
+          Thread.currentThread().interrupt();
+          log.warn("Interrupted while waiting to acquire lock", ex);
         }
       }
     }

core/src/main/java/org/apache/accumulo/core/util/compaction/RunningCompactionInfo.java

@@ -75,7 +75,7 @@ public RunningCompactionInfo(TExternalCompaction ec) {
     if (lastEntry != null) {
       last = lastEntry.getValue();
       updateMillis = lastEntry.getKey();
-      duration = last.getCompactionAgeNanos();
+      duration = NANOSECONDS.toMillis(last.getCompactionAgeNanos());
     } else {
       log.debug("No updates found for {}", ecid);
       lastUpdate = 1;
@@ -84,7 +84,7 @@ public RunningCompactionInfo(TExternalCompaction ec) {
       duration = 0;
       return;
     }
-    long durationMinutes = NANOSECONDS.toMinutes(duration);
+    long durationMinutes = MILLISECONDS.toMinutes(duration);
     if (durationMinutes > 15) {
       log.warn("Compaction {} has been running for {} minutes", ecid, durationMinutes);
     }

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

@@ -20,6 +20,7 @@
 
 import static java.util.concurrent.TimeUnit.MILLISECONDS;
 
+import java.util.List;
 import java.util.OptionalInt;
 import java.util.concurrent.ScheduledFuture;
 import java.util.concurrent.atomic.AtomicReference;
@@ -31,6 +32,7 @@
 import org.apache.accumulo.core.conf.AccumuloConfiguration;
 import org.apache.accumulo.core.conf.Property;
 import org.apache.accumulo.core.conf.SiteConfiguration;
+import org.apache.accumulo.core.conf.cluster.ClusterConfigParser;
 import org.apache.accumulo.core.lock.ServiceLock;
 import org.apache.accumulo.core.metrics.MetricsProducer;
 import org.apache.accumulo.core.metrics.thrift.MetricSource;
@@ -70,6 +72,7 @@ protected AbstractServer(String appName, ConfigOpts opts,
     var siteConfig = opts.getSiteConfiguration();
     this.hostname = siteConfig.get(Property.GENERAL_PROCESS_BIND_ADDRESS);
     this.resourceGroup = getResourceGroupPropertyValue(siteConfig);
+    ClusterConfigParser.validateGroupNames(List.of(resourceGroup));
     SecurityUtil.serverLogin(siteConfig);
     context = serverContextFactory.apply(siteConfig);
     log = LoggerFactory.getLogger(getClass());

server/base/src/main/java/org/apache/accumulo/server/util/Admin.java

@@ -572,22 +572,32 @@ private static void flushAll(final ClientContext context) {
     try {
       flusher.join(3000);
     } catch (InterruptedException e) {
-      // ignore
+      Thread.currentThread().interrupt();
+      log.warn("Interrupted while waiting to join Flush thread", e);
     }
 
     while (flusher.isAlive() && System.currentTimeMillis() - start < 15000) {
       int flushCount = flushesStarted.get();
       try {
         flusher.join(1000);
       } catch (InterruptedException e) {
-        // ignore
+        Thread.currentThread().interrupt();
+        log.warn("Interrupted while waiting to join Flush thread", e);
       }
 
       if (flushCount == flushesStarted.get()) {
         // no progress was made while waiting for join... maybe its stuck, stop waiting on it
         break;
       }
     }
+
+    flusher.interrupt();
+    try {
+      flusher.join();
+    } catch (InterruptedException e) {
+      Thread.currentThread().interrupt();
+      log.warn("Interrupted while waiting to join Flush thread", e);
+    }
   }
 
   private static void stopServer(final ClientContext context, final boolean tabletServersToo)

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/bulkImport.js

@@ -37,7 +37,7 @@ function refresh() {
 /**
  * Initializes the bulk import DataTables
  */
-$(document).ready(function () {
+$(function () {
 
   const url = '/rest/bulkImports';
   console.debug('REST url used to fetch data for the DataTables in bulkImport.js: ' + url);

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/compactions.js

@@ -22,7 +22,7 @@ var compactionsList;
 /**
  * Creates active compactions table
  */
-$(document).ready(function () {
+$(function () {
   // Create a table for compactions list
   compactionsList = $('#compactionsList').DataTable({
     "ajax": {

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/ec.js

@@ -27,7 +27,7 @@ var runningTableData;
 /**
  * Creates active compactions table
  */
-$(document).ready(function () {
+$(function () {
   if (sessionStorage.ecDetailsJSON === undefined) {
     sessionStorage.ecDetailsJSON = JSON.stringify([]);
   }
@@ -85,7 +85,6 @@ $(document).ready(function () {
     "columnDefs": [{
         "targets": "duration",
         "render": function (data, type, row) {
-          data = data / 1_000_000; // convert from nanos to millis
           if (type === 'display') data = timeDuration(data);
           return data;
         }

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/gc.js

@@ -22,7 +22,7 @@ var gcTable;
 /**
  * Creates active compactions table
  */
-$(document).ready(function () {
+$(function () {
   // Create a table for compactions list
   gcTable = $('#gcActivity').DataTable({
     "ajax": {

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/manager.js

@@ -90,7 +90,7 @@ function refreshManagerTables() {
 /**
  * Creates initial tables
  */
-$(document).ready(function () {
+$(function () {
 
   // Generates the manager table
   managerStatusTable = $('#managerStatus').DataTable({

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/navbar.js

@@ -122,7 +122,7 @@ function updateServerNotifications(statusData) {
 /**
  * Creates the initial sidebar
  */
-$(document).ready(function () {
+$(function () {
   refreshSidebar();
 });
 

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/overview.js

@@ -21,7 +21,7 @@
 /**
  * Creates overview initial table
  */
-$(document).ready(function () {
+$(function () {
   refreshOverview();
 });
 

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/scans.js

@@ -23,7 +23,7 @@ var scansList;
 /**
  * Creates scans initial table
  */
-$(document).ready(function () {
+$(function () {
   // Create a table for scans list
   scansList = $('#scansList').DataTable({
     "ajax": {

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/systemAlert.js

@@ -154,7 +154,7 @@ function updateSystemAlerts() {
   updateManagerAlerts();
 }
 
-$(document).ready(function () {
+$(function () {
 
   // dismiss the alert when clicked
   $('#systemAlertCloseButton').click(function () {

server/monitor/src/main/resources/org/apache/accumulo/monitor/resources/js/tservers.js

@@ -129,7 +129,7 @@ function clearDeadTServers(server) {
 /**
  * Creates initial tables
  */
-$(document).ready(function () {
+$(function () {
 
   refreshRecoveryList();
 

server/monitor/src/main/resources/org/apache/accumulo/monitor/templates/default.ftl

@@ -49,7 +49,7 @@
       /**
        * Sets up autorefresh on initial load
        */
-      $(document).ready(function() {
+      $(function() {
         setupAutoRefresh();
       });
     </script>

server/monitor/src/main/resources/org/apache/accumulo/monitor/templates/server.ftl

@@ -19,7 +19,7 @@
 
 -->
       <script>
-        $(document).ready(function () {
+        $(function () {
           // initialize DataTables
           initServerTables('${server}');
         });

server/monitor/src/main/resources/org/apache/accumulo/monitor/templates/table.ftl

@@ -22,7 +22,7 @@
         /**
          * Creates participating Tservers initial table, passes the tableID from the template
          */
-        $(document).ready(function () {
+        $(function () {
           initTableServerTable('${tableID}');
         });
       </script>