Skip to content

[fix](routineload) Preserve cloud progress for Kafka property alters #67515

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
0AyanamiRei wants to merge 1 commit into
base: master
Choose a base branch
from
+60 −1
Open

[fix](routineload) Preserve cloud progress for Kafka property alters #67515

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion fe/fe-core/src/main/java/org/apache/doris/load/routineload/kafka/KafkaRoutineLoadJob.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -839,7 +839,10 @@ private void modifyPropertiesInternal(Map<String, String> jobProperties,
((KafkaProgress) progress).checkPartitions(kafkaPartitionOffsets);
}

if (Config.isCloudMode()) {
// Kafka client properties do not change the consumed offsets, so keep the cloud progress for replay.
if (Config.isCloudMode()
&& (!Strings.isNullOrEmpty(dataSourceProperties.getTopic())
|| !kafkaPartitionOffsets.isEmpty())) {
Cloud.ResetRLProgressRequest.Builder builder = Cloud.ResetRLProgressRequest.newBuilder()
.setRequestIp(FrontendOptions.getLocalHostAddressCached());
builder.setCloudUniqueId(Config.cloud_unique_id);
Expand Down
56 changes: 56 additions & 0 deletions fe/fe-core/src/test/java/org/apache/doris/load/routineload/KafkaRoutineLoadJobTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,8 @@
import org.apache.doris.catalog.Partition;
import org.apache.doris.catalog.Table;
import org.apache.doris.catalog.info.PartitionNamesInfo;
import org.apache.doris.cloud.proto.Cloud;
import org.apache.doris.cloud.rpc.MetaServiceProxy;
import org.apache.doris.common.Config;
import org.apache.doris.common.MetaNotFoundException;
import org.apache.doris.common.Pair;
Expand All @@ -44,6 +46,7 @@
import org.apache.doris.nereids.trees.plans.commands.info.LabelNameInfo;
import org.apache.doris.nereids.trees.plans.commands.load.LoadProperty;
import org.apache.doris.nereids.trees.plans.commands.load.LoadSeparator;
import org.apache.doris.persist.AlterRoutineLoadJobOperationLog;
import org.apache.doris.qe.ConnectContext;
import org.apache.doris.thrift.TResourceInfo;
import org.apache.doris.thrift.TRoutineLoadTask;
Expand Down Expand Up @@ -248,6 +251,59 @@ public void testUpdateLagRebuildsConvertedPropertiesAfterReplay() throws UserExc
}
}

@Test
public void testReplayKafkaClientPropertiesKeepsCloudProgress() throws Exception {
String originalCloudUniqueId = Config.cloud_unique_id;
String originalMetaServiceEndpoint = Config.meta_service_endpoint;
try {
Config.cloud_unique_id = "test-cloud";
Config.meta_service_endpoint = "127.0.0.1:20121";

KafkaRoutineLoadJob routineLoadJob = new KafkaRoutineLoadJob(1L, "kafka_routine_load_job", 1L,
1L, "127.0.0.1:9020", "topic1", UserIdentity.ADMIN);
Map<Integer, Long> partitionOffsets = Maps.newHashMap();
partitionOffsets.put(1, 10L);
Deencapsulation.setField(routineLoadJob, "progress", new KafkaProgress(partitionOffsets));

Map<String, String> alteredProperties = Maps.newHashMap();
alteredProperties.put("property.group.id", "replayed-group");
alteredProperties.put("property.client.id", "replayed-client");
KafkaDataSourceProperties dataSourceProperties = new KafkaDataSourceProperties(alteredProperties);
dataSourceProperties.setAlter(true);
dataSourceProperties.setTimezone("Asia/Shanghai");
dataSourceProperties.analyze();

Env env = Mockito.mock(Env.class);
MetaServiceProxy metaServiceProxy = Mockito.mock(MetaServiceProxy.class);
Cloud.ResetRLProgressResponse response = Cloud.ResetRLProgressResponse.newBuilder()
.setStatus(Cloud.MetaServiceResponseStatus.newBuilder()
.setCode(Cloud.MetaServiceCode.OK))
.build();
Mockito.when(metaServiceProxy.resetRLProgress(Mockito.any())).thenReturn(response);
try (MockedStatic<Env> envStatic = Mockito.mockStatic(Env.class);
MockedStatic<MetaServiceProxy> metaServiceProxyStatic =
Mockito.mockStatic(MetaServiceProxy.class)) {
envStatic.when(Env::getCurrentEnv).thenReturn(env);
metaServiceProxyStatic.when(MetaServiceProxy::getInstance).thenReturn(metaServiceProxy);

routineLoadJob.replayModifyProperties(new AlterRoutineLoadJobOperationLog(
routineLoadJob.getId(), Maps.newHashMap(), dataSourceProperties));

Mockito.verify(metaServiceProxy, Mockito.never()).resetRLProgress(Mockito.any());
}

Assert.assertEquals("replayed-group",
routineLoadJob.getConvertedCustomProperties().get("group.id"));
Assert.assertEquals("replayed-client",
routineLoadJob.getConvertedCustomProperties().get("client.id"));
Assert.assertEquals(partitionOffsets,
((KafkaProgress) routineLoadJob.getProgress()).getOffsetByPartition());
} finally {
Config.cloud_unique_id = originalCloudUniqueId;
Config.meta_service_endpoint = originalMetaServiceEndpoint;
}
}

@Test
public void testUpdateProgressWarnsWhenReadCommittedTaskHasZeroRowsAndLag() throws UserException {
KafkaRoutineLoadJob routineLoadJob = new KafkaRoutineLoadJob(1L, "kafka_routine_load_job", 1L,
Expand Down