Skip to content

HDDS-13068. Validate Container Balancer move timeout and replication timeout configs #8490

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

Merged
siddhantsangwan merged 5 commits into from
Jun 3, 2025
+40 −2
Merged

HDDS-13068. Validate Container Balancer move timeout and replication timeout configs #8490

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a735d7e
HDDS-13068. Validate Container Balancer move timeout and replication …
Tejaskriya May 20, 2025
28dff3c
update values in TestContainerBalancerOperations
Tejaskriya May 20, 2025
ff8c2e7
add unit test, fix error message
Tejaskriya May 29, 2025
120275a
change mins to ms, add assertion in test
Tejaskriya Jun 2, 2025
04190de
findbugs fix
Tejaskriya Jun 2, 2025
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
17 changes: 17 additions & 0 deletions ...er-scm/src/main/java/org/apache/hadoop/hdds/scm/container/balancer/ContainerBalancer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,9 @@

import com.google.common.annotations.VisibleForTesting;
import java.io.IOException;
import java.time.Duration;
import java.time.OffsetDateTime;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.concurrent.locks.ReentrantLock;
import org.apache.hadoop.hdds.conf.OzoneConfiguration;
Expand Down Expand Up @@ -459,6 +461,21 @@ private void validateConfiguration(ContainerBalancerConfiguration conf)
"hdds.container.balancer.move.replication.timeout should " +
"be less than hdds.container.balancer.move.timeout.");
}

// (move.timeout - move.replication.timeout - event.timeout.datanode.offset) should be greater than 9 minutes
Comment thread
Tejaskriya marked this conversation as resolved.
Outdated
long datanodeOffset = ozoneConfiguration.getTimeDuration("hdds.scm.replication.event.timeout.datanode.offset",
Duration.ofMinutes(6).toMillis(), TimeUnit.MILLISECONDS);
if ((conf.getMoveTimeout().toMillis() - conf.getMoveReplicationTimeout().toMillis() - datanodeOffset)
< Duration.ofMinutes(9).toMillis()) {
String msg = String.format("(hdds.container.balancer.move.timeout (%sm) - " +
"hdds.container.balancer.move.replication.timeout (%sm) - " +
"hdds.scm.replication.event.timeout.datanode.offset (%sm)) should be greater than 9 minutes.",
Comment thread
Tejaskriya marked this conversation as resolved.
Outdated
conf.getMoveReplicationTimeout().toMinutes(),
conf.getMoveTimeout().toMinutes(),
Duration.ofMillis(datanodeOffset).toMinutes());
LOG.warn(msg);
throw new InvalidContainerBalancerConfigurationException(msg);
}
}

public ContainerBalancerMetrics getMetrics() {
Expand Down
4 changes: 2 additions & 2 deletions ...tegration-test/src/test/java/org/apache/hadoop/ozone/TestContainerBalancerOperations.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ public void testContainerBalancerCLIOperations() throws Exception {
Optional<Long> maxSizeLeavingSourceInGB = Optional.of(6L);
Optional<Integer> balancingInterval = Optional.of(70);
Optional<Integer> moveTimeout = Optional.of(65);
Optional<Integer> moveReplicationTimeout = Optional.of(55);
Optional<Integer> moveReplicationTimeout = Optional.of(50);
Optional<Boolean> networkTopologyEnable = Optional.of(false);
Optional<String> includeNodes = Optional.of("");
Optional<String> excludeNodes = Optional.of("");
Expand Down Expand Up @@ -147,7 +147,7 @@ public void testIfCBCLIOverridesConfigs() throws Exception {
Optional<Long> maxSizeEnteringTargetInGB = Optional.of(6L);
Optional<Long> maxSizeLeavingSourceInGB = Optional.of(6L);
Optional<Integer> moveTimeout = Optional.of(65);
Optional<Integer> moveReplicationTimeout = Optional.of(55);
Optional<Integer> moveReplicationTimeout = Optional.of(50);
Optional<Boolean> networkTopologyEnable = Optional.of(true);
Optional<String> includeNodes = Optional.of("");
Optional<String> excludeNodes = Optional.of("");
Expand Down