This is an automated email from the ASF dual-hosted git repository.
smiklosovic pushed a commit to branch trunk
in repository https://gitbox.apache.org/repos/asf/cassandra.git
commit b7e2b3b9dc6246f75962eaf5facbb74cc1216be5
Merge: acec78abf4 74e0794d92
Author: Stefan Miklosovic <smikloso...@apache.org>
AuthorDate: Wed Aug 20 10:54:42 2025 +0200
Merge branch 'cassandra-5.0' into trunk
CHANGES.txt | 1 +
.../cassandra/db/compaction/CompactionTask.java | 74 ++++++++++++++++++++++
src/java/org/apache/cassandra/index/Index.java | 22 +++++++
.../cassandra/index/sai/StorageAttachedIndex.java | 6 ++
.../org/apache/cassandra/index/sasi/SASIIndex.java | 6 ++
.../apache/cassandra/index/CustomIndexTest.java | 60 ++++++++++++++++++
6 files changed, 169 insertions(+)
diff --cc CHANGES.txt
index aeef6ebc6c,86b9274c38..a524728bc4
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@@ -294,12 -74,7 +294,13 @@@ Merged from 4.1
* Optionally skip exception logging on invalid legacy protocol magic
exception (CASSANDRA-19483)
* Fix SimpleClient ability to release acquired capacity (CASSANDRA-20202)
* Fix WaitQueue.Signal.awaitUninterruptibly may block forever if invoking
thread is interrupted (CASSANDRA-20084)
+ * Run audit_logging_options through santiation and validation on startup
(CASSANDRA-20208)
+ * Enforce CQL message size limit on multiframe messages (CASSANDRA-20052)
+ * Fix race condition in DecayingEstimatedHistogramReservoir during rescale
(CASSANDRA-19365)
Merged from 4.0:
++ * Make secondary index implementations notified about rows in fully expired
SSTables in compaction (CASSANDRA-20829)
+ * Ensure prepared_statement INSERT timestamp precedes eviction DELETE
(CASSANDRA-19703)
+ * Gossip doesn't converge due to race condition when updating EndpointStates
multiple fields (CASSANDRA-20659)
* Handle sstable metadata stats file getting a new mtime after compaction
has finished (CASSANDRA-18119)
* Honor MAX_PARALLEL_TRANSFERS correctly (CASSANDRA-20532)
* Updating a column with a new TTL but same expiration time is
non-deterministic and causes repair mismatches. (CASSANDRA-20561)
diff --cc src/java/org/apache/cassandra/db/compaction/CompactionTask.java
index eb331dda8f,cc8cdae157..1f9e8ea403
--- a/src/java/org/apache/cassandra/db/compaction/CompactionTask.java
+++ b/src/java/org/apache/cassandra/db/compaction/CompactionTask.java
@@@ -17,6 -17,8 +17,7 @@@
*/
package org.apache.cassandra.db.compaction;
-import java.time.Instant;
+ import java.util.ArrayList;
import java.util.Collection;
import java.util.HashMap;
import java.util.HashSet;
@@@ -26,14 -28,10 +27,16 @@@ import java.util.Set
import java.util.concurrent.TimeUnit;
import com.google.common.base.Predicate;
+import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import com.google.common.collect.Iterables;
-import com.google.common.collect.Sets;
import com.google.common.util.concurrent.RateLimiter;
+
+import org.apache.cassandra.db.compaction.unified.UnifiedCompactionTask;
++import org.apache.cassandra.db.rows.Unfiltered;
++import org.apache.cassandra.db.rows.UnfilteredRowIterator;
+import org.apache.cassandra.dht.Range;
+import org.apache.cassandra.dht.Token;
import org.apache.commons.lang3.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@@ -42,9 -40,16 +45,14 @@@ import org.apache.cassandra.config.Data
import org.apache.cassandra.db.ColumnFamilyStore;
import org.apache.cassandra.db.Directories;
import org.apache.cassandra.db.SystemKeyspace;
+ import org.apache.cassandra.db.WriteContext;
import org.apache.cassandra.db.compaction.writers.CompactionAwareWriter;
import org.apache.cassandra.db.compaction.writers.DefaultCompactionWriter;
-import org.apache.cassandra.db.lifecycle.LifecycleTransaction;
+import org.apache.cassandra.db.lifecycle.ILifecycleTransaction;
+ import org.apache.cassandra.db.rows.Row;
-import org.apache.cassandra.db.rows.Unfiltered;
-import org.apache.cassandra.db.rows.UnfilteredRowIterator;
+ import org.apache.cassandra.index.Index;
+ import org.apache.cassandra.index.transactions.IndexTransaction;
+ import org.apache.cassandra.io.sstable.ISSTableScanner;
import org.apache.cassandra.io.sstable.format.SSTableReader;
import org.apache.cassandra.io.sstable.metadata.MetadataCollector;
import org.apache.cassandra.io.util.File;
@@@ -160,34 -134,21 +168,37 @@@ public class CompactionTask extends Abs
if (DatabaseDescriptor.isSnapshotBeforeCompaction())
{
- Instant creationTime = now();
- cfs.snapshotWithoutMemtable(creationTime.toEpochMilli() +
"-compact-" + cfs.name, creationTime);
+ SnapshotOptions options =
SnapshotOptions.systemSnapshot(cfs.name, SnapshotType.COMPACT,
cfs.getKeyspaceTableName()).skipFlush().build();
+ SnapshotManager.instance.takeSnapshot(options);
}
- try (CompactionController controller =
getCompactionController(transaction.originals()))
+ try (CompactionController controller =
getCompactionController(inputSSTables()))
{
+ // Note: the controller set-up above relies on using the
transaction-provided sstable list, from which
+ // fully-expired sstables should not be removed (so that the
overlap tracker does not include them), but
+ // sstables excluded for scope reduction should be removed.
+ Set<SSTableReader> actuallyCompact = new
HashSet<>(inputSSTables());
final Set<SSTableReader> fullyExpiredSSTables =
controller.getFullyExpiredSSTables();
+
++
maybeNotifyIndexersAboutRowsInFullyExpiredSSTables(fullyExpiredSSTables);
++
+ if (!fullyExpiredSSTables.isEmpty())
+ {
+ logger.debug("Compaction {} dropping expired sstables: {}",
transaction.opIdString(), fullyExpiredSSTables);
+ actuallyCompact.removeAll(fullyExpiredSSTables);
+ }
+
TimeUUID taskId = transaction.opId();
// select SSTables to compact based on available disk space.
- if
(!buildCompactionCandidatesForAvailableDiskSpace(fullyExpiredSSTables, taskId))
+ final boolean hasExpirations = !fullyExpiredSSTables.isEmpty();
+ if ((shouldReduceScopeForSpace() &&
!buildCompactionCandidatesForAvailableDiskSpace(actuallyCompact,
hasExpirations, taskId))
+ || hasExpirations)
{
// The set of sstables has changed (one or more were excluded
due to limited available disk space).
- // We need to recompute the overlaps between sstables.
+ // We need to recompute the overlaps between sstables. The
iterators used in the compaction controller
+ // and tracker will reflect the changed set of sstables made
by LifecycleTransaction.cancel(),
+ // so refreshing the overlaps will be based on the updated
set of sstables.
controller.refreshOverlaps();
}
diff --cc test/unit/org/apache/cassandra/index/CustomIndexTest.java
index 3c0d75b5fc,5504a8760b..3cd756b9e3
--- a/test/unit/org/apache/cassandra/index/CustomIndexTest.java
+++ b/test/unit/org/apache/cassandra/index/CustomIndexTest.java
@@@ -43,7 -33,8 +43,9 @@@ import com.google.common.collect.Immuta
import com.google.common.collect.Maps;
import com.google.common.collect.Sets;
import org.junit.Assume;
+import org.junit.BeforeClass;
+ import com.google.common.util.concurrent.Uninterruptibles;
+ import org.junit.Assert;
import org.junit.Test;
import com.datastax.driver.core.exceptions.QueryValidationException;
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
