Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -285,6 +285,15 @@ public void notifyLeaderChanged(RaftGroupMemberId groupMemberId,
currentLeaderTerm.set(scm.getScmHAManager().getRatisServer().getDivision()
.getInfo().getCurrentTerm());

if (!refreshedAfterLeaderReady.get()) {
// refresh and validate safe mode rules if it can exit safe mode
// if being leader, all previous term transactions have been applied
// if other states, just refresh safe mode rules, and transaction keeps flushing from leader
// and does not depend on pending transactions.
refreshedAfterLeaderReady.set(true);
scm.getScmSafeModeManager().refreshAndValidate();
}

if (!groupMemberId.getPeerId().equals(newLeaderId)) {
LOG.info("leader changed, yet current SCM is still follower.");
return;
Expand Down Expand Up @@ -355,12 +364,9 @@ public void notifyTermIndexUpdated(long term, long index) {
}

if (currentLeaderTerm.get() == term) {
// Means all transactions before this term have been applied.
// This means after a restart, all pending transactions have been applied.
// Perform
// 1. Refresh Safemode rules state.
// 2. Start DN Rpc server.
if (!refreshedAfterLeaderReady.get()) {
// Refresh Safemode rules state if not already done.
refreshedAfterLeaderReady.set(true);
scm.getScmSafeModeManager().refreshAndValidate();
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -54,8 +54,11 @@
import org.apache.hadoop.hdds.scm.container.replication.ContainerReplicaPendingOps;
import org.apache.hadoop.hdds.scm.events.SCMEvents;
import org.apache.hadoop.hdds.scm.ha.SCMContext;
import org.apache.hadoop.hdds.scm.ha.SCMHAManager;
import org.apache.hadoop.hdds.scm.ha.SCMHAManagerStub;
import org.apache.hadoop.hdds.scm.ha.SCMRatisServer;
import org.apache.hadoop.hdds.scm.ha.SCMServiceManager;
import org.apache.hadoop.hdds.scm.ha.SCMStateMachine;
import org.apache.hadoop.hdds.scm.metadata.SCMMetadataStore;
import org.apache.hadoop.hdds.scm.metadata.SCMMetadataStoreImpl;
import org.apache.hadoop.hdds.scm.node.NodeManager;
Expand All @@ -67,6 +70,7 @@
import org.apache.hadoop.hdds.scm.pipeline.PipelineProvider;
import org.apache.hadoop.hdds.scm.server.SCMDatanodeHeartbeatDispatcher;
import org.apache.hadoop.hdds.scm.server.SCMDatanodeProtocolServer;
import org.apache.hadoop.hdds.scm.server.StorageContainerManager;
import org.apache.hadoop.hdds.server.events.EventQueue;
import org.apache.ozone.test.GenericTestUtils;
import org.junit.jupiter.api.AfterEach;
Expand Down Expand Up @@ -177,6 +181,16 @@ public void testSafeModeExitRule() throws Exception {
}
ContainerManager containerManager = mock(ContainerManager.class);
when(containerManager.getContainers(ReplicationType.RATIS)).thenReturn(containers);

StorageContainerManager mockScmManager = mock(StorageContainerManager.class);
SCMHAManager mockScmhaManager = mock(SCMHAManager.class);
when(mockScmManager.getScmHAManager()).thenReturn(mockScmhaManager);
SCMRatisServer mockScmRatisServer = mock(SCMRatisServer.class);
when(mockScmhaManager.getRatisServer()).thenReturn(mockScmRatisServer);
SCMStateMachine mockScmStateMachine = mock(SCMStateMachine.class);
when(mockScmRatisServer.getSCMStateMachine()).thenReturn(mockScmStateMachine);
when((mockScmStateMachine.isRefreshedAfterLeaderReady())).thenReturn(true);
scmContext = new SCMContext.Builder().setSCM(mockScmManager).build();
scmSafeModeManager = new SCMSafeModeManager(config, null, null, containerManager,
serviceManager, queue, scmContext);
scmSafeModeManager.start();
Expand Down Expand Up @@ -207,6 +221,7 @@ public void testSafeModeExitRule() throws Exception {
testContainerThreshold(containers.subList(75, 100), 1.0);
assertEquals(100, scmSafeModeManager.getSafeModeMetrics()
.getCurrentContainersWithOneReplicaReportedCount().value());
scmSafeModeManager.validateSafeModeExitRules(StateMachineReadyRule.class.getSimpleName());

GenericTestUtils.waitFor(() -> !scmSafeModeManager.getInSafeMode(),
100, 1000 * 5);
Expand Down