This is an automated email from the ASF dual-hosted git repository.
kturner pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/accumulo.git
commit ea5afb9d85e342834554504cdf541a43dcc79a84
Merge: 9ffc450b0a bdec3a7c3a
Author: Keith Turner <ktur...@apache.org>
AuthorDate: Thu Feb 22 19:00:28 2024 -0500
Merge branch '2.1'
.../server/manager/state/MetaDataStateStore.java | 3 +-
.../manager/state/TabletStateChangeIterator.java | 3 +
.../accumulo/test/manager/SuspendedTabletsIT.java | 249 +++++++++++++--------
3 files changed, 157 insertions(+), 98 deletions(-)
diff --cc
test/src/main/java/org/apache/accumulo/test/manager/SuspendedTabletsIT.java
index ec99094346,764bc1dfc9..8ebb75378b
---
a/test/src/main/java/org/apache/accumulo/test/manager/SuspendedTabletsIT.java
+++
b/test/src/main/java/org/apache/accumulo/test/manager/SuspendedTabletsIT.java
@@@ -333,6 -300,95 +303,93 @@@ public class SuspendedTabletsIT extend
throws Exception;
}
+ private class ShutdownTserverKiller implements TServerKiller {
+
+ @Override
+ public void eliminateTabletServers(ClientContext ctx, TabletLocations
locs, int count)
+ throws Exception {
-
+ Set<TServerInstance> tserverSet = new HashSet<>();
+ Set<TServerInstance> metadataServerSet = new HashSet<>();
+
- TabletLocator tl = TabletLocator.getLocator(ctx, MetadataTable.ID);
++ TabletLocator tl = TabletLocator.getLocator(ctx,
AccumuloTable.METADATA.tableId());
+ for (TabletLocationState tls : locs.locationStates.values()) {
+ if (tls.current != null) {
+ // add to set of all servers
+ tserverSet.add(tls.current.getServerInstance());
+
+ // get server that the current tablets metadata is on
+ TabletLocator.TabletLocation tab =
+ tl.locateTablet(ctx, tls.extent.toMetaRow(), false, false);
+ // add it to the set of servers with metadata
- metadataServerSet
- .add(new TServerInstance(tab.tablet_location,
Long.valueOf(tab.tablet_session, 16)));
++ metadataServerSet.add(new TServerInstance(tab.getTserverLocation(),
++ Long.valueOf(tab.getTserverSession(), 16)));
+ }
+ }
+
+ // remove servers with metadata on them from the list of servers to be
shutdown
+ assertEquals(1, metadataServerSet.size(), "Expecting a single tServer
in metadataServerSet");
+ tserverSet.removeAll(metadataServerSet);
+
+ assertEquals(TSERVERS - 1, tserverSet.size(),
+ "Expecting " + (TSERVERS - 1) + " tServers in shutdown-list");
+
+ List<TServerInstance> tserversList = new ArrayList<>(tserverSet);
- Collections.shuffle(tserversList, random);
++ Collections.shuffle(tserversList, RANDOM.get());
+
+ for (int i1 = 0; i1 < count; ++i1) {
+ final String tserverName = tserversList.get(i1).getHostPortSession();
+ ThriftClientTypes.MANAGER.executeVoid(ctx, client -> {
+ log.info("Sending shutdown command to {} via ManagerClientService",
tserverName);
+ client.shutdownTabletServer(null, ctx.rpcCreds(), tserverName,
false);
+ });
+ }
+
+ log.info("Waiting for tserver process{} to die", count == 1 ? "" :
"es");
+ for (int i2 = 0; i2 < 10; ++i2) {
+ List<ProcessReference> deadProcs = new ArrayList<>();
+ for (ProcessReference pr1 :
getCluster().getProcesses().get(ServerType.TABLET_SERVER)) {
+ Process p = pr1.getProcess();
+ if (!p.isAlive()) {
+ deadProcs.add(pr1);
+ }
+ }
+ for (ProcessReference pr2 : deadProcs) {
+ log.info("Process {} is dead, informing cluster control about
this", pr2.getProcess());
+
getCluster().getClusterControl().killProcess(ServerType.TABLET_SERVER, pr2);
+ --count;
+ }
+ if (count == 0) {
+ return;
+ } else {
+ Thread.sleep(SECONDS.toMillis(2));
+ }
+ }
+ throw new IllegalStateException("Tablet servers didn't die!");
-
+ }
+ }
+
+ private class CrashTserverKiller implements TServerKiller {
+
+ @Override
+ public void eliminateTabletServers(ClientContext ctx, TabletLocations
locs, int count)
+ throws Exception {
+ // Exclude the tablet server hosting the metadata table from the list
and only
+ // kill tablet servers that are not hosting the metadata table.
+ List<ProcessReference> procs =
getCluster().getProcesses().get(ServerType.TABLET_SERVER)
+ .stream().filter(p ->
!metadataTserverProcess.equals(p)).collect(Collectors.toList());
- Collections.shuffle(procs, random);
++ Collections.shuffle(procs, RANDOM.get());
+ assertEquals(TSERVERS - 1, procs.size(), "Not enough tservers exist");
+ assertTrue(procs.size() >= count, "Attempting to kill more tservers ("
+ count
+ + ") than exist in the cluster (" + procs.size() + ")");
+
+ for (int i = 0; i < count; ++i) {
+ ProcessReference pr = procs.get(i);
+ log.info("Crashing {}", pr.getProcess());
+ getCluster().killProcess(ServerType.TABLET_SERVER, pr);
+ }
+ }
+ }
+
private static final AtomicInteger threadCounter = new AtomicInteger(0);
@BeforeAll
