From a197bb489d6fd56fc78eefadd59057fb0fed984f Mon Sep 17 00:00:00 2001 From: sreedev Date: Mon, 29 Sep 2025 22:31:04 +0530 Subject: [PATCH 01/10] c5-agent commit --- agent-c5/build.gradle | 146 ++ agent-c5/gradle.properties | 2 + agent-c5/src/docker/Dockerfile | 22 + .../src/docker/jmx_prometheus_exporter.yaml | 83 + agent-c5/src/docker/table1.yaml | 28 + .../com/datastax/oss/cdc/agent/Agent.java | 94 ++ .../datastax/oss/cdc/agent/CdcMetrics.java | 54 + .../cdc/agent/CommitLogReadHandlerImpl.java | 485 ++++++ .../cdc/agent/CommitLogReaderServiceImpl.java | 89 + .../com/datastax/oss/cdc/agent/Mutation.java | 68 + .../datastax/oss/cdc/agent/MutationMaker.java | 39 + .../oss/cdc/agent/PulsarMutationSender.java | 161 ++ .../oss/cdc/agent/PulsarDualNodeC5Tests.java | 37 + .../cdc/agent/PulsarSingleNodeC5Tests.java | 50 + .../test/resources/cassandra/cassandra.yaml | 1430 +++++++++++++++++ .../src/test/resources/cassandra/logback.xml | 103 ++ agent-c5/src/test/resources/logback-test.xml | 15 + gradle.properties | 3 +- settings.gradle | 2 + .../com/datastax/oss/cdc/AgentTestUtil.java | 1 + 20 files changed, 2911 insertions(+), 1 deletion(-) create mode 100644 agent-c5/build.gradle create mode 100644 agent-c5/gradle.properties create mode 100644 agent-c5/src/docker/Dockerfile create mode 100644 agent-c5/src/docker/jmx_prometheus_exporter.yaml create mode 100644 agent-c5/src/docker/table1.yaml create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/Agent.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/CdcMetrics.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReadHandlerImpl.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReaderServiceImpl.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/Mutation.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/MutationMaker.java create mode 100644 agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java create mode 100644 agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarDualNodeC5Tests.java create mode 100644 agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarSingleNodeC5Tests.java create mode 100644 agent-c5/src/test/resources/cassandra/cassandra.yaml create mode 100644 agent-c5/src/test/resources/cassandra/logback.xml create mode 100644 agent-c5/src/test/resources/logback-test.xml diff --git a/agent-c5/build.gradle b/agent-c5/build.gradle new file mode 100644 index 00000000..63accc37 --- /dev/null +++ b/agent-c5/build.gradle @@ -0,0 +1,146 @@ +plugins { + id 'java-library' + id 'java' + id 'application' + id "com.github.johnrengelman.shadow" + id 'com.palantir.docker' + id 'docker-compose' +} + +application { + mainClass = "$mainClassName" +} + +jar { + duplicatesStrategy = DuplicatesStrategy.INCLUDE + manifest { + attributes 'Premain-Class': "$mainClassName" + } + zip64=true +} +tasks.jar.dependsOn project(':commons').jar +tasks.jar.dependsOn project(':agent').jar + +compileTestJava { + options.compilerArgs += '-parameters' +} + +sourceSets { + // Make the compileOnly dependencies available when compiling/running tests + test.compileClasspath += configurations.compileClasspath + test.runtimeClasspath += configurations.compileClasspath +} + +shadowJar { + manifest { + inheritFrom project.tasks.jar.manifest + } +} + +jar.enabled = true +assemble.dependsOn(shadowJar) + +dependencies { + implementation project(':commons') + implementation project(':agent') + + implementation("org.apache.avro:avro:${avroVersion}") + + implementation("${pulsarGroup}:pulsar-client:${pulsarVersion}") + + compileOnly("org.apache.cassandra:cassandra-all:${cassandra5Version}") + testCompileOnly("org.apache.cassandra:cassandra-all:${cassandra5Version}") + testImplementation("org.apache.cassandra:cassandra-all:${cassandra5Version}") { + exclude group: 'io.netty' + } + + testImplementation "com.datastax.oss:java-driver-core:${ossDriverVersion}" + testImplementation "com.datastax.oss:java-driver-query-builder:${ossDriverVersion}" + + testImplementation "org.testcontainers:testcontainers:${testContainersVersion}" + testImplementation project(':testcontainers') + + testRuntimeOnly "org.slf4j:slf4j-api:${slf4jVersion}" + testRuntimeOnly "ch.qos.logback:logback-classic:${logbackVersion}" +} + +test { + // Add dependency on jar task, since it will be main target for testing + dependsOn shadowJar + + // Rearrange test classpath, add compiled JAR instead of main classes + classpath = project.sourceSets.test.output + configurations.testRuntimeClasspath + files(shadowJar.archiveFile) + + useJUnitPlatform() + + // JVM arguments for Cassandra 5.0 Java 17+ compatibility + jvmArgs '--add-exports', 'java.base/jdk.internal.misc=ALL-UNNAMED', + '--add-exports', 'java.management.rmi/com.sun.jmx.remote.internal.rmi=ALL-UNNAMED', + '--add-exports', 'java.rmi/sun.rmi.registry=ALL-UNNAMED', + '--add-exports', 'java.rmi/sun.rmi.server=ALL-UNNAMED', + '--add-exports', 'java.sql/java.sql=ALL-UNNAMED', + '--add-exports', 'java.base/java.lang.ref=ALL-UNNAMED', + '--add-exports', 'jdk.unsupported/sun.misc=ALL-UNNAMED', + '--add-opens', 'java.base/java.lang.module=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.loader=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.ref=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.reflect=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.math=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.module=ALL-UNNAMED', + '--add-opens', 'java.base/jdk.internal.util.jar=ALL-UNNAMED', + '--add-opens', 'jdk.management/com.sun.management.internal=ALL-UNNAMED', + '--add-opens', 'java.base/sun.nio.ch=ALL-UNNAMED', + '--add-opens', 'java.base/java.io=ALL-UNNAMED', + '--add-opens', 'java.base/java.lang=ALL-UNNAMED', + '--add-opens', 'java.base/java.lang.reflect=ALL-UNNAMED', + '--add-opens', 'java.base/java.util=ALL-UNNAMED', + '--add-opens', 'java.base/java.nio=ALL-UNNAMED' + + environment 'PULSAR_IMAGE', testPulsarImage + ':' + testPulsarImageTag + environment 'CASSANDRA_IMAGE', 'cassandra:' + cassandra5Version + + systemProperty "buildDir", buildDir + systemProperty "projectVersion", project.version +} + +dockerPrepare.dependsOn(jar, shadowJar) +dockerPrepare.duplicatesStrategy = DuplicatesStrategy.INCLUDE +docker { + name "${dockerRepo}cassandra:${cassandra5Version}-cdc" + files "$buildDir/libs/", "src/docker/" + buildArgs([BUILD_VERSION: project.version, + CASSANDRA_VERSION: cassandra5Version, + COMMITMOG_SYNC_PERIOD_IN_MS: commitlog_sync_period_in_ms, + CDC_TOTAL_SPACE_IN_MB: cdc_total_space_in_mb]) +} +build.dependsOn(project.tasks['docker']) + +dockerCompose { + projectName = "test1" + useComposeFiles = ['../docker-compose.yaml'] + environment.put 'AGENT_VERSION', 'c5' + environment.put 'PROJECT_VERSION', project.version + environment.put 'CASSANDRA_IMAGE', "${dockerRepo}cassandra:${cassandra5Version}-cdc" + environment.put 'PULSAR_IMAGE', "${dockerRepo}pulsar:${testPulsarImageTag}-csc" + waitForTcpPorts = false + startedServices = ['cassandra','pulsar'] + + stress { + projectName = "test1" + startedServices = ['cassandra-stress'] + scale = ['cassandra-stress': 1] + } + stress2 { + projectName = "test1" + startedServices = ['cassandra-stress'] + scale = ['cassandra-stress': 2] + } + prometheus { + projectName = "test1" + startedServices = ['prometheus','grafana'] + } + elasticsearch { + projectName = "test1" + startedServices = ['elasticsearch'] + } +} diff --git a/agent-c5/gradle.properties b/agent-c5/gradle.properties new file mode 100644 index 00000000..e4ecc1e2 --- /dev/null +++ b/agent-c5/gradle.properties @@ -0,0 +1,2 @@ +artifact=agent-c5 +mainClassName=com.datastax.oss.cdc.agent.Agent diff --git a/agent-c5/src/docker/Dockerfile b/agent-c5/src/docker/Dockerfile new file mode 100644 index 00000000..d5eadfeb --- /dev/null +++ b/agent-c5/src/docker/Dockerfile @@ -0,0 +1,22 @@ +ARG CASSANDRA_VERSION +FROM cassandra:${CASSANDRA_VERSION} +ARG BUILD_VERSION +ARG COMMITMOG_SYNC_PERIOD_IN_MS +ARG CDC_TOTAL_SPACE_IN_MB + +RUN sed -i 's/cdc_enabled: false/cdc_enabled: true/g' /etc/cassandra/cassandra.yaml +RUN sed -i "s/commitlog_sync_period_in_ms: 10000/commitlog_sync_period_in_ms: $COMMITMOG_SYNC_PERIOD_IN_MS/g" /etc/cassandra/cassandra.yaml +RUN echo "cdc_total_space_in_mb: ${CDC_TOTAL_SPACE_IN_MB}" >> /etc/cassandra/cassandra.yaml + +COPY agent-c5-${BUILD_VERSION}-all.jar / + +# Add cassandra-stress config +COPY table1.yaml / + +# Add the prometheus exporter +ADD https://repo1.maven.org/maven2/io/prometheus/jmx/jmx_prometheus_javaagent/0.16.1/jmx_prometheus_javaagent-0.16.1.jar / +RUN chmod a+rx /jmx_prometheus_javaagent-0.16.1.jar +COPY jmx_prometheus_exporter.yaml / + +# Add cassandra tools in the PATH +ENV PATH="${PATH}:/opt/cassandra/tools/bin" diff --git a/agent-c5/src/docker/jmx_prometheus_exporter.yaml b/agent-c5/src/docker/jmx_prometheus_exporter.yaml new file mode 100644 index 00000000..fca93edf --- /dev/null +++ b/agent-c5/src/docker/jmx_prometheus_exporter.yaml @@ -0,0 +1,83 @@ +lowercaseOutputName: true +lowercaseOutputLabelNames: true +whitelistObjectNames: [ + "org.apache.cassandra.metrics:type=ColumnFamily,name=RangeLatency,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=LiveSSTableCount,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=SSTablesPerReadHistogram,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=SpeculativeRetries,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=MemtableOnHeapSize,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=MemtableSwitchCount,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=MemtableLiveDataSize,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=MemtableColumnsCount,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=MemtableOffHeapSize,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=BloomFilterFalsePositives,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=BloomFilterFalseRatio,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=BloomFilterDiskSpaceUsed,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=BloomFilterOffHeapMemoryUsed,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=SnapshotsSize,*", + "org.apache.cassandra.metrics:type=ColumnFamily,name=TotalDiskSpaceUsed,*", + "org.apache.cassandra.metrics:type=CQL,name=RegularStatementsExecuted,*", + "org.apache.cassandra.metrics:type=CQL,name=PreparedStatementsExecuted,*", + "org.apache.cassandra.metrics:type=Compaction,name=PendingTasks,*", + "org.apache.cassandra.metrics:type=Compaction,name=CompletedTasks,*", + "org.apache.cassandra.metrics:type=Compaction,name=BytesCompacted,*", + "org.apache.cassandra.metrics:type=Compaction,name=TotalCompactionsCompleted,*", + "org.apache.cassandra.metrics:type=ClientRequest,name=Latency,*", + "org.apache.cassandra.metrics:type=ClientRequest,name=Unavailables,*", + "org.apache.cassandra.metrics:type=ClientRequest,name=Timeouts,*", + "org.apache.cassandra.metrics:type=ClientRequest,name=Failures,*", + "org.apache.cassandra.metrics:type=ClientRequest,name=Latency,*", + "org.apache.cassandra.metrics:type=Storage,name=Exceptions,*", + "org.apache.cassandra.metrics:type=Storage,name=TotalHints,*", + "org.apache.cassandra.metrics:type=Storage,name=TotalHintsInProgress,*", + "org.apache.cassandra.metrics:type=Storage,name=Load,*", + "org.apache.cassandra.metrics:type=Connection,name=TotalTimeouts,*", + "org.apache.cassandra.metrics:type=ThreadPools,name=CompletedTasks,*", + "org.apache.cassandra.metrics:type=ThreadPools,name=PendingTasks,*", + "org.apache.cassandra.metrics:type=ThreadPools,name=ActiveTasks,*", + "org.apache.cassandra.metrics:type=ThreadPools,name=TotalBlockedTasks,*", + "org.apache.cassandra.metrics:type=ThreadPools,name=CurrentlyBlockedTasks,*", + "org.apache.cassandra.metrics:type=DroppedMessage,name=Dropped,*", + "org.apache.cassandra.metrics:type=Cache,scope=KeyCache,name=HitRate,*", + "org.apache.cassandra.metrics:type=Cache,scope=KeyCache,name=Hits,*", + "org.apache.cassandra.metrics:type=Cache,scope=KeyCache,name=Requests,*", + "org.apache.cassandra.metrics:type=Cache,scope=KeyCache,name=Entries,*", + "org.apache.cassandra.metrics:type=Cache,scope=KeyCache,name=Size,*", + "org.apache.cassandra.metrics:type=Streaming,name=TotalIncomingBytes,*", + "org.apache.cassandra.metrics:type=Streaming,name=TotalOutgoingBytes,*", + "org.apache.cassandra.metrics:type=Client,name=connectedNativeClients,*", + "org.apache.cassandra.metrics:type=Client,name=connectedThriftClients,*", + "org.apache.cassandra.metrics:type=Table,name=WriteLatency,*", + "org.apache.cassandra.metrics:type=Table,name=ReadLatency,*", + "org.apache.cassandra.metrics:type=CdcAgent,*", + "org.apache.cassandra.metrics:type=CommitLog,*", + "org.apache.cassandra.net:type=FailureDetector,*", +] +#blacklistObjectNames: ["org.apache.cassandra.metrics:type=ColumnFamily,*"] +rules: + - pattern: org.apache.cassandra.metrics<>(Count|Value) + name: cassandra_$1_$3 + labels: + address: "$2" + - pattern: org.apache.cassandra.metrics<>(Mean) + name: cassandra_$1_$2_$3 + - pattern: org.apache.cassandra.net<>(DownEndpointCount) + name: cassandra_$1_$2 + - pattern: org.apache.cassandra.metrics<>(Count|Mean|95thPercentile) + name: cassandra_$1_$3_$4 + labels: + "$1": "$2" + - pattern: org.apache.cassandra.metrics<>(Count|Mean|95thPercentile) + name: cassandra_$1_$4_$5 + labels: + "keyspace": "$2" + "table": "$3" + - pattern: org.apache.cassandra.metrics<>(Count|Mean|95thPercentile) + name: cassandra_$1_$3_$4 + labels: + "type": "$2" + - pattern: org.apache.cassandra.metrics<>(Count|Value) + name: cassandra_$1_$5 + labels: + "$1": "$4" + "$2": "$3" diff --git a/agent-c5/src/docker/table1.yaml b/agent-c5/src/docker/table1.yaml new file mode 100644 index 00000000..c79fbea0 --- /dev/null +++ b/agent-c5/src/docker/table1.yaml @@ -0,0 +1,28 @@ +keyspace: ks1 +keyspace_definition: | + CREATE KEYSPACE ks1 WITH replication = {'class': 'SimpleStrategy', 'replication_factor': '1'}; +# +# Table name and create CQL +# +table: table1 +table_definition: | + CREATE TABLE table1 (a text, b text, PRIMARY KEY (a)) WITH cdc=true; + +columnspec: + - name: a + size: uniform(10..30) + - name: b + size: fixed(16) + +# +# Specs for insert queries +# +insert: + partitions: fixed(1) # 1 partition per batch + batchtype: UNLOGGED # use unlogged batches + select: fixed(10)/10 # no chance of skipping a row when generating inserts + +queries: + read1: + cql: select * from table1 where a = ? + fields: samerow # samerow or multirow (select arguments from the same row, or randomly from all rows in the partition) diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Agent.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Agent.java new file mode 100644 index 00000000..b769a074 --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Agent.java @@ -0,0 +1,94 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import lombok.extern.slf4j.Slf4j; +import org.apache.cassandra.config.DatabaseDescriptor; +import org.apache.cassandra.service.StorageService; + +import java.lang.instrument.Instrumentation; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.Executors; + +@Slf4j +public class Agent { + public static void premain(String agentArgs, Instrumentation inst) { + log.info("[Agent] In premain method"); + try { + main(agentArgs, inst); + } catch(Exception e) { + log.error("error:", e); + System.exit(-1); + } + } + + public static void agentmain(String agentArgs, Instrumentation inst) { + log.info("[Agent] In agentmain method"); + try { + main(agentArgs, inst); + } catch(Exception e) { + log.error("error:", e); + System.exit(-1); + } + } + + static void main(String agentArgs, Instrumentation inst) throws Exception { + DatabaseDescriptor.daemonInitialization(); + if (DatabaseDescriptor.isCDCEnabled() == false) { + log.error("cdc_enabled=false in your cassandra configuration, CDC agent not started."); + } else if (DatabaseDescriptor.getCDCLogLocation() == null) { + log.error("cdc_raw_directory=null in your cassandra configuration, CDC agent not started."); + } else { + startCdcAgent(agentArgs); + } + } + + static void startCdcAgent(String agentArgs) throws Exception { + log.info("Starting CDC agent, cdc_raw_directory={}", DatabaseDescriptor.getCDCLogLocation()); + AgentConfig config = AgentConfig.create(AgentConfig.Platform.PULSAR, agentArgs); + + SegmentOffsetFileWriter segmentOffsetFileWriter = new SegmentOffsetFileWriter(config.cdcWorkingDir); + segmentOffsetFileWriter.loadOffsets(); + + PulsarMutationSender pulsarMutationSender = new PulsarMutationSender(config); + CommitLogTransfer commitLogTransfer = new BlackHoleCommitLogTransfer(config); + CommitLogReaderServiceImpl commitLogReaderService = new CommitLogReaderServiceImpl(config, pulsarMutationSender, segmentOffsetFileWriter, commitLogTransfer); + CommitLogProcessor commitLogProcessor = new CommitLogProcessor(DatabaseDescriptor.getCDCLogLocation(), config, commitLogTransfer, segmentOffsetFileWriter, commitLogReaderService, true); + + commitLogReaderService.initialize(); + + // detect commitlogs file and submit new/modified files to the commitLogReader + ExecutorService commitLogExecutor = Executors.newSingleThreadExecutor(); + commitLogExecutor.submit(() -> { + try { + do { + // wait to initialize the hostID before starting + Thread.sleep(1000); + } while(StorageService.instance.getLocalHostUUID() == null); + + commitLogProcessor.initialize(); + commitLogProcessor.start(); + } catch(Exception e) { + log.error("commitLogProcessor error:", e); + } + }); + + ExecutorService commitLogServiceExecutor = Executors.newSingleThreadExecutor(); + commitLogServiceExecutor.submit(commitLogReaderService); + + log.info("CDC agent started"); + } +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CdcMetrics.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CdcMetrics.java new file mode 100644 index 00000000..9305ff2f --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CdcMetrics.java @@ -0,0 +1,54 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.codahale.metrics.Counter; +import com.codahale.metrics.Gauge; +import org.apache.cassandra.metrics.DefaultNameFactory; +import org.apache.cassandra.metrics.MetricNameFactory; + +import static org.apache.cassandra.metrics.CassandraMetricsRegistry.Metrics; + +public class CdcMetrics { + public static final String CDC_AGENT_MBEAN_NAME = "CdcAgent"; + private static final MetricNameFactory factory = new DefaultNameFactory(CDC_AGENT_MBEAN_NAME); + + public static final Counter sentMutations = Metrics.counter(factory.createMetricName("SentMutations")); + public static final Counter sentErrors = Metrics.counter(factory.createMetricName("SentErrors")); + + public static final Counter commitLogReadErrors = Metrics.counter(factory.createMetricName("CommitLogReadErrors")); + public static final Counter skippedMutations = Metrics.counter(factory.createMetricName("SkippedMutations")); + + public static final Counter executedTasks = Metrics.counter(factory.createMetricName("ExecutedTasks")); + + public static final Gauge submittedTasksGauge = Metrics.register(factory.createMetricName("SubmittedTasks"), + CommitLogReaderService.submittedTasks::size); + + public static final Gauge maxSubmittedTasks = Metrics.register(factory.createMetricName("MaxSubmittedTasks"), + CommitLogReaderService.maxSubmittedTasks::get); + + public static final Gauge pendingTasksGauge = Metrics.register(factory.createMetricName("PendingTasks"), + CommitLogReaderService.pendingTasks::size); + + public static final Gauge maxPendingTasks = Metrics.register(factory.createMetricName("MaxPendingTasks"), + CommitLogReaderService.maxPendingTasks::get); + + public static final Gauge uncleanedTasksGauge = Metrics.register(factory.createMetricName("UncleanedTasks"), + CommitLogReaderService.pendingTasks::size); + + public static final Gauge maxUncleanedTasks = Metrics.register(factory.createMetricName("MaxUncleanedTasks"), + CommitLogReaderService.maxUncleanedTasks::get); +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReadHandlerImpl.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReadHandlerImpl.java new file mode 100644 index 00000000..360b83db --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReadHandlerImpl.java @@ -0,0 +1,485 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.datastax.oss.cdc.agent.exceptions.CassandraConnectorSchemaException; +import com.datastax.oss.cdc.agent.exceptions.CassandraConnectorTaskException; +import lombok.extern.slf4j.Slf4j; +import org.apache.cassandra.cql3.ColumnSpecification; +import org.apache.cassandra.db.LivenessInfo; +import org.apache.cassandra.db.commitlog.CommitLogDescriptor; +import org.apache.cassandra.db.commitlog.CommitLogReadHandler; +import org.apache.cassandra.db.marshal.AbstractType; +import org.apache.cassandra.db.marshal.ValueAccessor; +import org.apache.cassandra.db.partitions.PartitionUpdate; +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.io.util.DataOutputBuffer; +import org.apache.cassandra.schema.ColumnMetadata; +import org.apache.cassandra.schema.TableMetadata; +import org.apache.cassandra.service.StorageService; +import org.apache.cassandra.utils.ByteBufferUtil; +import org.apache.commons.codec.digest.DigestUtils; + +import java.nio.ByteBuffer; +import java.util.*; +import java.util.stream.Collectors; + +import static com.datastax.oss.cdc.agent.CommitLogReadHandlerImpl.RowType.DELETE; + +/** + * Handler that implements {@link CommitLogReadHandler} interface provided by Cassandra source code. + * + * This handler implementation processes each {@link org.apache.cassandra.db.Mutation} and invokes one of the registered partition handler + * for each {@link PartitionUpdate} in the {@link org.apache.cassandra.db.Mutation} (a mutation could have multiple partitions if it is a batch update), + * which in turn makes one or more record via the {@link AbstractMutationMaker}. + */ +@Slf4j +public class CommitLogReadHandlerImpl implements CommitLogReadHandler { + + private final AbstractMutationMaker mutationMaker; + private final MutationSender mutationSender; + private final CommitLogReaderService.Task task; + private int processedPosition; + + CommitLogReadHandlerImpl(MutationSender mutationSender, + CommitLogReaderService.Task task, + int currentPosition) { + this.mutationSender = mutationSender; + this.mutationMaker = new MutationMaker(); + this.task = task; + this.processedPosition = currentPosition; + } + + public int getProcessedPosition() { + return this.processedPosition; + } + + /** + * A PartitionType represents the type of a PartitionUpdate. + */ + enum PartitionType { + /** + * a partition-level deletion where partition key = primary key (no clustering key) + */ + PARTITION_KEY_ROW_DELETION, + + /** + * a partition-level deletion where partition key + clustering key = primary key + */ + PARTITION_AND_CLUSTERING_KEY_ROW_DELETION, + + /** + * a row-level modification + */ + ROW_LEVEL_MODIFICATION, + + /** + * an update on materialized view + */ + MATERIALIZED_VIEW, + + /** + * an update on secondary index + */ + SECONDARY_INDEX, + + /** + * an update on a table that contains counter data type + */ + COUNTER, + + /** + * a partition-level modification + */ + PARTITION_LEVEL_MODIFICATION; + + static final Set supportedPartitionTypes = new HashSet<>(Arrays.asList( + PARTITION_KEY_ROW_DELETION, + PARTITION_AND_CLUSTERING_KEY_ROW_DELETION, + ROW_LEVEL_MODIFICATION, + PARTITION_LEVEL_MODIFICATION)); + + public static PartitionType getPartitionType(PartitionUpdate pu) { + if (pu.metadata().isCounter()) { + return COUNTER; + } + else if (pu.metadata().isView()) { + return MATERIALIZED_VIEW; + } + else if (pu.metadata().isIndex()) { + return SECONDARY_INDEX; + } + else if (isPartitionDeletion(pu) && hasClusteringKeys(pu)) { + return PARTITION_AND_CLUSTERING_KEY_ROW_DELETION; + } + else if (isPartitionDeletion(pu) && !hasClusteringKeys(pu)) { + return PARTITION_KEY_ROW_DELETION; + } + else if (!pu.unfilteredIterator().hasNext()) { + return PARTITION_LEVEL_MODIFICATION; + } + else { + return ROW_LEVEL_MODIFICATION; + } + } + + public static boolean isValid(PartitionType type) { + return supportedPartitionTypes.contains(type); + } + + public static boolean hasClusteringKeys(PartitionUpdate pu) { + return !pu.metadata().clusteringColumns().isEmpty(); + } + + public static boolean isPartitionDeletion(PartitionUpdate pu) { + return pu.partitionLevelDeletion().markedForDeleteAt() > LivenessInfo.NO_TIMESTAMP; + } + } + + /** + * A RowType represents different types of {@link Row}-level modifications in a Cassandra table. + */ + enum RowType { + /** + * Single-row insert + */ + INSERT, + + /** + * Single-row update + */ + UPDATE, + + /** + * Single-row delete + */ + DELETE, + + /** + * A row-level deletion that deletes a range of keys. + * For example: DELETE * FROM table WHERE partition_key = 1 AND clustering_key > 0; + */ + RANGE_TOMBSTONE, + + /** + * Unknown row-level operation + */ + UNKNOWN; + + static final Set supportedRowTypes = new HashSet<>(Arrays.asList(INSERT, UPDATE, DELETE)); + + public static RowType getRowType(Unfiltered unfiltered) { + if (unfiltered.isRangeTombstoneMarker()) { + return RANGE_TOMBSTONE; + } + else if (unfiltered.isRow()) { + Row row = (Row) unfiltered; + return getRowType(row); + } + return UNKNOWN; + } + + public static RowType getRowType(Row row) { + if (isDelete(row)) { + return DELETE; + } + else if (isInsert(row)) { + return INSERT; + } + else if (isUpdate(row)) { + return UPDATE; + } + return UNKNOWN; + } + + public static boolean isValid(RowType rowType) { + return supportedRowTypes.contains(rowType); + } + + public static boolean isDelete(Row row) { + return row.deletion().time().markedForDeleteAt() > LivenessInfo.NO_TIMESTAMP; + } + + public static boolean isInsert(Row row) { + return row.primaryKeyLivenessInfo().timestamp() > LivenessInfo.NO_TIMESTAMP; + } + + public static boolean isUpdate(Row row) { + return row.primaryKeyLivenessInfo().timestamp() == LivenessInfo.NO_TIMESTAMP; + } + } + + @Override + public void handleMutation(org.apache.cassandra.db.Mutation mutation, int size, int entryLocation, CommitLogDescriptor descriptor) { + if (!mutation.trackedByCDC()) { + return; + } + + for (PartitionUpdate pu : mutation.getPartitionUpdates()) { + try { + DataOutputBuffer dataOutputBuffer = new DataOutputBuffer(); + org.apache.cassandra.db.Mutation.serializer.serialize(mutation, dataOutputBuffer, descriptor.getMessagingVersion()); + String md5Digest = DigestUtils.md5Hex(dataOutputBuffer.getData()); + process(pu, descriptor.id, entryLocation, md5Digest); + } + catch (Exception e) { + throw new RuntimeException(String.format("Failed to process PartitionUpdate %s at %d:%d for table %s.%s.", + pu.toString(), descriptor.id, entryLocation, pu.metadata().keyspace, pu.metadata().name), e); + } + } + } + + @Override + public void handleUnrecoverableError(CommitLogReadException exception) { + log.error("Unrecoverable error when reading commit log", exception); + CdcMetrics.commitLogReadErrors.inc(); + } + + @Override + public boolean shouldSkipSegmentOnError(CommitLogReadException exception) { + if (exception.permissible) { + log.error("Encountered a permissible exception during log replay", exception); + } + else { + log.error("Encountered a non-permissible exception during log replay", exception); + } + return false; + } + + /** + * Method which processes a partition update if it's valid (either a single-row partition-level + * deletion or a row-level modification) or throw an exception if it isn't. The valid partition + * update is then converted into a {@link AbstractMutation}. + */ + private void process(PartitionUpdate pu, long segment, int position, String md5Digest) { + PartitionType partitionType = PartitionType.getPartitionType(pu); + + if (!PartitionType.isValid(partitionType)) { + log.warn("Encountered an unsupported partition type {}, skipping...", partitionType); + return; + } + + switch (partitionType) { + case PARTITION_AND_CLUSTERING_KEY_ROW_DELETION: + case PARTITION_KEY_ROW_DELETION: { + handlePartitionDeletion(pu, segment, position, md5Digest); + } + break; + + case PARTITION_LEVEL_MODIFICATION: { + UnfilteredRowIterator it = pu.unfilteredIterator(); + Row row = it.staticRow(); + RowType rowType = RowType.getRowType(row); + handleRowModifications(row, rowType, pu, segment, position, md5Digest); + } + break; + + case ROW_LEVEL_MODIFICATION: { + UnfilteredRowIterator it = pu.unfilteredIterator(); + while (it.hasNext()) { + Unfiltered rowOrRangeTombstone = it.next(); + RowType rowType = RowType.getRowType(rowOrRangeTombstone); + if (!RowType.isValid(rowType)) { + log.warn("Encountered an unsupported row type {}, skipping...", rowType); + continue; + } + Row row = (Row) rowOrRangeTombstone; + + handleRowModifications(row, rowType, pu, segment, position, md5Digest); + } + } + break; + + default: + throw new CassandraConnectorSchemaException("Unsupported partition type " + partitionType + " should have been skipped"); + } + } + + /** + * Handle a valid deletion event resulted from a partition-level deletion by converting Cassandra representation + * of this event into a {@link AbstractMutation} object and send it to pulsar. A valid deletion + * event means a partition only has a single row, this implies there are no clustering keys. + */ + private void handlePartitionDeletion(PartitionUpdate pu, long segment, int position, String md5Digest) { + try { + Object[] after = new Object[pu.metadata().partitionKeyColumns().size() + pu.metadata().clusteringColumns().size()]; + populatePartitionColumns(after, pu); + mutationMaker.delete(StorageService.instance.getLocalHostUUID(), segment, position, + pu.maxTimestamp(), after, this::sendAsync, md5Digest, pu.metadata(), pu.partitionKey().getToken().getTokenValue()); + } + catch (Exception e) { + log.error("Fail to send delete partition at {}:{}. Reason: {}", segment, position, e); + } + } + + /** + * Handle a valid event resulted from a row-level modification by converting Cassandra representation of + * this event into a {@link AbstractMutation} object and sent it to pulsar. A valid event + * implies this must be an insert, update, or delete. + */ + private void handleRowModifications(Row row, RowType rowType, PartitionUpdate pu, + long segment, int position, String md5Digest) { + Object[] after = new Object[pu.metadata().partitionKeyColumns().size() + pu.metadata().clusteringColumns().size()]; + populatePartitionColumns(after, pu); + populateClusteringColumns(after, row, pu); + + long ts = rowType == DELETE ? row.deletion().time().markedForDeleteAt() : pu.maxTimestamp(); + switch (rowType) { + case INSERT: + mutationMaker.insert(StorageService.instance.getLocalHostUUID(), segment, position, + ts, after, this::sendAsync, md5Digest, pu.metadata(), pu.partitionKey().getToken().getTokenValue()); + break; + + case UPDATE: + mutationMaker.update(StorageService.instance.getLocalHostUUID(), segment, position, + ts, after, this::sendAsync, md5Digest, pu.metadata(), pu.partitionKey().getToken().getTokenValue()); + break; + + case DELETE: + mutationMaker.delete(StorageService.instance.getLocalHostUUID(), segment, position, + ts, after, this::sendAsync, md5Digest, pu.metadata(), pu.partitionKey().getToken().getTokenValue()); + break; + + default: + throw new CassandraConnectorTaskException("Unsupported row type " + rowType + " should have been skipped"); + } + } + + private void populatePartitionColumns(Object[] after, PartitionUpdate pu) { + List partitionKeys = getPartitionKeys(pu); + int i = 0; + for (ColumnMetadata cd : pu.metadata().partitionKeyColumns()) { + try { + after[i++] = partitionKeys.get(cd.position()); + } + catch (Exception e) { + throw new RuntimeException(String.format("Failed to populate Column %s with Type %s of Table %s in KeySpace %s.", + cd.name.toString(), cd.type.toString(), cd.cfName, cd.ksName), e); + } + } + } + + @SuppressWarnings({"unchecked","rawtypes"}) + private void populateClusteringColumns(Object[] after, Row row, PartitionUpdate pu) { + int i = pu.metadata().partitionKeyColumns().size(); + for (ColumnMetadata cd : pu.metadata().clusteringColumns().stream().limit(row.clustering().size()).collect(Collectors.toList())) { + try { + ValueAccessor valueAccessor = row.clustering().accessor(); + after[i++] = cd.type.compose(valueAccessor.toBuffer(row.clustering().get(cd.position()))); + } + catch (Exception e) { + throw new RuntimeException(String.format("Failed to populate Column %s with Type %s of Table %s in KeySpace %s.", + cd.name.toString(), cd.type.toString(), cd.cfName, cd.ksName), e); + } + } + } + + /** + * Given a PartitionUpdate, deserialize the partition key byte buffer + * into a list of partition key values. + */ + @SuppressWarnings("checkstyle:magicnumber") + private static List getPartitionKeys(PartitionUpdate pu) { + List values = new ArrayList<>(pu.metadata().partitionKeyColumns().size()); + List columnDefinitions = pu.metadata().partitionKeyColumns(); + + // simple partition key + if (columnDefinitions.size() == 1) { + ByteBuffer bb = pu.partitionKey().getKey(); + ColumnSpecification cs = columnDefinitions.get(0); + AbstractType type = cs.type; + try { + Object value = type.compose(bb); + values.add(value); + } + catch (Exception e) { + throw new RuntimeException(String.format("Failed to deserialize Column %s with Type %s in Table %s and KeySpace %s.", + cs.name.toString(), cs.type.toString(), cs.cfName, cs.ksName), e); + } + } + else { + ByteBuffer keyBytes = pu.partitionKey().getKey().duplicate(); + + // 0xFFFF is reserved to encode "static column", skip if it exists at the start + if (keyBytes.remaining() >= 2) { + int header = ByteBufferUtil.getShortLength(keyBytes, keyBytes.position()); + if ((header & 0xFFFF) == 0xFFFF) { + ByteBufferUtil.readShortLength(keyBytes); + } + } + + // the encoding of columns in the partition key byte buffer is + // ... + // where is: + // + // is a 2 bytes unsigned short (excluding 0xFFFF used to encode "static columns") + // should always be 0 for columns (1 for query bounds) + // this section reads the bytes for each column and deserialize into objects based on each column type + int i = 0; + while (keyBytes.remaining() > 0 && i < columnDefinitions.size()) { + ColumnSpecification cs = columnDefinitions.get(i); + AbstractType type = cs.type; + ByteBuffer bb = ByteBufferUtil.readBytesWithShortLength(keyBytes); + try { + Object value = type.compose(bb); + values.add(value); + } + catch (Exception e) { + throw new RuntimeException(String.format("Failed to deserialize Column %s with Type %s in Table %s and KeySpace %s", + cs.name.toString(), cs.type.toString(), cs.cfName, cs.ksName), e); + } + byte b = keyBytes.get(); + if (b != 0) { + break; + } + ++i; + } + } + + return values; + } + + public void sendAsync(Mutation mutation) { + log.debug("Sending mutation={}", mutation); + try { + task.inflightMessagesSemaphore.acquireUninterruptibly(); // may block + this.mutationSender.sendMutationAsync(mutation) + .handle((msgId, t)-> { + if (t == null) { + CdcMetrics.sentMutations.inc(); + log.debug("Sent mutation={}", mutation); + } else { + if (t instanceof CassandraConnectorSchemaException) { + log.error("Invalid primary key schema:", t); + CdcMetrics.skippedMutations.inc(); + } else { + CdcMetrics.sentErrors.inc(); + log.debug("Sent failed mutation=" + mutation, t); + task.lastException = t; + } + } + task.inflightMessagesSemaphore.release(); + return msgId; + }); + this.processedPosition = Math.max(this.processedPosition, mutation.getPosition()); + } catch(Exception e) { + log.error("Send failed:", e); + CdcMetrics.sentErrors.inc(); + } + } +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReaderServiceImpl.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReaderServiceImpl.java new file mode 100644 index 00000000..4389b013 --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/CommitLogReaderServiceImpl.java @@ -0,0 +1,89 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import lombok.extern.slf4j.Slf4j; +import org.apache.cassandra.concurrent.ExecutorFactory; +import org.apache.cassandra.concurrent.ExecutorPlus; +import org.apache.cassandra.config.DatabaseDescriptor; +import org.apache.cassandra.db.commitlog.CommitLogPosition; +import org.apache.cassandra.db.commitlog.CommitLogReader; +import org.apache.cassandra.schema.TableMetadata; + +import java.io.File; +import java.util.Optional; +import java.util.concurrent.*; +import java.util.function.IntBinaryOperator; + +/** + * Consume a queue of commitlog files to read mutations. + */ +@Slf4j +public class CommitLogReaderServiceImpl extends CommitLogReaderService { + + public CommitLogReaderServiceImpl(AgentConfig config, + MutationSender mutationSender, + SegmentOffsetWriter segmentOffsetWriter, + CommitLogTransfer commitLogTransfer) { + super(config, mutationSender, segmentOffsetWriter, commitLogTransfer); + int threads = config.cdcConcurrentProcessors == -1 ? DatabaseDescriptor.getFlushWriters() : config.cdcConcurrentProcessors; + this.tasksExecutor = ExecutorFactory.Global.executorFactory() + .configurePooled("CdcCommitlogProcessor", threads) + .withKeepAlive(1, TimeUnit.MINUTES) + .withQueueLimit(Integer.MAX_VALUE) + .build(); + } + + @SuppressWarnings("unchecked") + public Task createTask(String filename, long segment, int syncPosition, boolean completed) { + return new Task(filename, segment, syncPosition, completed) { + + public void run() { + log.debug("Starting task={} lasSentPosition={}", this, segmentOffsetWriter.position(Optional.empty(), segment)); + File file = getFile(); + try { + int lastSentPosition = -1; + if (!file.exists()) { + log.warn("CL file={} does not exist any more, ignoring", file.getName()); + finish(TaskStatus.SUCCESS, -1); + return; + } + long seg = CommitLogUtil.extractTimestamp(file.getName()); + + int currentPosition = segmentOffsetWriter.position(Optional.empty(), seg); + if (syncPosition >= currentPosition) { + CommitLogPosition minPosition = new CommitLogPosition(seg, currentPosition); + CommitLogReadHandlerImpl commitLogReadHandler = new CommitLogReadHandlerImpl((MutationSender) mutationSender, this, currentPosition); + CommitLogReader commitLogReader = new CommitLogReader(); + commitLogReader.readCommitLogSegment(commitLogReadHandler, new org.apache.cassandra.io.util.File(file), minPosition, org.apache.cassandra.db.commitlog.CommitLogReader.ALL_MUTATIONS, false); + lastSentPosition = commitLogReadHandler.getProcessedPosition(); + } + finish(TaskStatus.SUCCESS, lastSentPosition); + } catch (Exception e) { + log.warn("Task failed {}", this, e); + finish(TaskStatus.ERROR, -1); + } finally { + CdcMetrics.executedTasks.inc(); + } + } + + @Override + public File getFile() { + return new File(DatabaseDescriptor.getCDCLogLocation(), filename); + } + }; + } +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Mutation.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Mutation.java new file mode 100644 index 00000000..41855db4 --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/Mutation.java @@ -0,0 +1,68 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import org.apache.cassandra.schema.ColumnMetadata; +import org.apache.cassandra.schema.TableMetadata; + +import java.util.ArrayList; +import java.util.List; +import java.util.UUID; + +public class Mutation extends AbstractMutation { + + public Mutation(UUID nodeId, Long segment, int position, Object[] pkValues, long tsMicro, String md5Digest, TableMetadata t, Object token) { + super(nodeId, segment, position, pkValues, tsMicro, md5Digest, t, token); + } + + @Override + public String key() { + return metadata.keyspace + "." + metadata.name; + } + + @Override + public String name() { + return metadata.name; + } + + @Override + public String keyspace() { + return metadata.keyspace; + } + + @Override + public List primaryKeyColumns() { + List columnInfos = new ArrayList<>(); + for(ColumnMetadata cm :metadata.primaryKeyColumns()) + columnInfos.add(new ColumnInfo() { + @Override + public String name() { + return cm.name.toString(); + } + + @Override + public String cql3Type() { + return cm.type.asCQL3Type().toString(); + } + + @Override + public boolean isClusteringKey() { + return cm.isClusteringColumn(); + } + }); + return columnInfos; + } +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/MutationMaker.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/MutationMaker.java new file mode 100644 index 00000000..bfb90009 --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/MutationMaker.java @@ -0,0 +1,39 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.datastax.oss.cdc.agent.exceptions.CassandraConnectorTaskException; +import lombok.extern.slf4j.Slf4j; +import org.apache.cassandra.schema.TableMetadata; + +import java.util.UUID; + +@Slf4j +public class MutationMaker extends AbstractMutationMaker { + + public void createRecord(UUID nodeId, long segment, int position, + long tsMicro, Object[] pkValues, BlockingConsumer consumer, + String md5Digest, TableMetadata t, Object token) { + Mutation record = new Mutation(nodeId, segment, position, pkValues, tsMicro, md5Digest, t, token); + try { + consumer.accept(record); + } + catch (InterruptedException e) { + log.error("Interruption while enqueuing Change Event {}", record); + throw new CassandraConnectorTaskException("Enqueuing has been interrupted: ", e); + } + } +} diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java new file mode 100644 index 00000000..6195ab7c --- /dev/null +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java @@ -0,0 +1,161 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.datastax.oss.cdc.CqlLogicalTypes; +import com.google.common.collect.ImmutableMap; +import lombok.extern.slf4j.Slf4j; +import org.apache.cassandra.config.DatabaseDescriptor; +import org.apache.cassandra.cql3.ColumnIdentifier; +import org.apache.cassandra.db.marshal.AbstractType; +import org.apache.cassandra.db.marshal.AsciiType; +import org.apache.cassandra.db.marshal.BooleanType; +import org.apache.cassandra.db.marshal.ByteType; +import org.apache.cassandra.db.marshal.BytesType; +import org.apache.cassandra.db.marshal.DecimalType; +import org.apache.cassandra.db.marshal.DoubleType; +import org.apache.cassandra.db.marshal.DurationType; +import org.apache.cassandra.db.marshal.FloatType; +import org.apache.cassandra.db.marshal.InetAddressType; +import org.apache.cassandra.db.marshal.Int32Type; +import org.apache.cassandra.db.marshal.IntegerType; +import org.apache.cassandra.db.marshal.LongType; +import org.apache.cassandra.db.marshal.ReversedType; +import org.apache.cassandra.db.marshal.ShortType; +import org.apache.cassandra.db.marshal.SimpleDateType; +import org.apache.cassandra.db.marshal.TimeType; +import org.apache.cassandra.db.marshal.TimeUUIDType; +import org.apache.cassandra.db.marshal.TimestampType; +import org.apache.cassandra.db.marshal.UTF8Type; +import org.apache.cassandra.db.marshal.UUIDType; +import org.apache.cassandra.dht.Murmur3Partitioner; +import org.apache.cassandra.schema.ColumnMetadata; +import org.apache.cassandra.schema.TableMetadata; +import org.apache.cassandra.service.StorageService; + +import java.net.InetAddress; +import java.time.Duration; +import java.time.Instant; +import java.time.LocalDate; +import java.time.LocalDateTime; +import java.time.ZoneOffset; +import java.util.Date; +import java.util.UUID; + +@Slf4j +public class PulsarMutationSender extends AbstractPulsarMutationSender { + + private static final ImmutableMap avroSchemaTypes = ImmutableMap.builder() + .put(UTF8Type.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.STRING)) + .put(AsciiType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.STRING)) + .put(BooleanType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.BOOLEAN)) + .put(BytesType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.BYTES)) + .put(ByteType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.INT)) // INT8 not supported by AVRO + .put(ShortType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.INT)) // INT16 not supported by AVRO + .put(Int32Type.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.INT)) + .put(IntegerType.instance.asCQL3Type().toString(), CqlLogicalTypes.varintType) + .put(LongType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.LONG)) + .put(FloatType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.FLOAT)) + .put(DoubleType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.DOUBLE)) + .put(DecimalType.instance.asCQL3Type().toString(), CqlLogicalTypes.decimalType) + .put(InetAddressType.instance.asCQL3Type().toString(), org.apache.avro.Schema.create(org.apache.avro.Schema.Type.STRING)) + .put(TimestampType.instance.asCQL3Type().toString(), CqlLogicalTypes.timestampMillisType) + .put(SimpleDateType.instance.asCQL3Type().toString(), CqlLogicalTypes.dateType) + .put(TimeType.instance.asCQL3Type().toString(), CqlLogicalTypes.timeMicrosType) + .put(DurationType.instance.asCQL3Type().toString(), CqlLogicalTypes.durationType) + .put(UUIDType.instance.asCQL3Type().toString(), CqlLogicalTypes.uuidType) + .put(TimeUUIDType.instance.asCQL3Type().toString(), CqlLogicalTypes.uuidType) + .build(); + + public PulsarMutationSender(AgentConfig config) { + super(config, DatabaseDescriptor.getPartitionerName().equals(Murmur3Partitioner.class.getName())); + } + + public PulsarMutationSender(AgentConfig config, boolean useMurmur3Partitioner) { + super(config, useMurmur3Partitioner); + } + + @Override + public void incSkippedMutations() { + CdcMetrics.skippedMutations.inc(); + } + + @Override + public UUID getHostId() { + return StorageService.instance.getLocalHostUUID(); + } + + @Override + public org.apache.avro.Schema getNativeSchema(String cql3Type) { + return avroSchemaTypes.get(cql3Type); + } + + /** + * Check the primary key has supported columns. + * @param mutation + * @return false if the primary key has unsupported CQL columns + */ + @Override + public boolean isSupported(final AbstractMutation mutation) { + if (!pkSchemas.containsKey(mutation.key())) { + for (ColumnMetadata cm : mutation.metadata.primaryKeyColumns()) { + if (!avroSchemaTypes.containsKey(cm.type.asCQL3Type().toString())) { + log.warn("Unsupported primary key column={}.{}.{} type={}, skipping mutation", cm.ksName, cm.cfName, cm.name, cm.type.asCQL3Type().toString()); + return false; + } + } + } + return true; + } + + @Override + public Object cqlToAvro(TableMetadata tableMetadata, String columnName, Object value) { + ColumnMetadata columnMetadata = tableMetadata.getColumn(ColumnIdentifier.getInterned(columnName, false)); + AbstractType type = columnMetadata.type.isReversed() ? ((ReversedType) columnMetadata.type).baseType : columnMetadata.type; + log.trace("column name={} type={} class={} value={}", + columnMetadata.name, type.getClass().getName(), + value != null ? value.getClass().getName() : null, value); + + if (value == null) + return null; + + if (type instanceof TimestampType) { + if (value instanceof Date) + return ((Date) value).getTime(); + if (value instanceof Instant) + return ((Instant) value).toEpochMilli(); + } + if (type instanceof SimpleDateType && value instanceof Integer) { + long timeInMillis = Duration.ofDays((Integer) value + Integer.MIN_VALUE).toMillis(); + Instant instant = Instant.ofEpochMilli(timeInMillis); + LocalDate localDate = LocalDateTime.ofInstant(instant, ZoneOffset.UTC).toLocalDate(); + return (int) localDate.toEpochDay(); // Avro date is an int that stores the number of days from the unix epoch + } + if (type instanceof TimeType && value instanceof Long) { + return ((Long) value / 1000); // Avro time is in microseconds + } + if (type instanceof InetAddressType) { + return ((InetAddress) value).getHostAddress(); + } + if (type instanceof ByteType) { + return Byte.toUnsignedInt((byte) value); // AVRO does not support INT8 + } + if (type instanceof ShortType) { + return Short.toUnsignedInt((short) value); // AVRO does not support INT16 + } + return value; + } +} diff --git a/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarDualNodeC5Tests.java b/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarDualNodeC5Tests.java new file mode 100644 index 00000000..6a9e5e10 --- /dev/null +++ b/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarDualNodeC5Tests.java @@ -0,0 +1,37 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.datastax.oss.cdc.AgentTestUtil; +import com.datastax.oss.cdc.PulsarDualNodeTests; +import com.datastax.testcontainers.cassandra.CassandraContainer; +import lombok.extern.slf4j.Slf4j; +import org.testcontainers.containers.Network; + +@Slf4j +public class PulsarDualNodeC5Tests extends PulsarDualNodeTests { + + public PulsarDualNodeC5Tests() { + super(AgentTestUtil.Version.C5); + } + + @Override + public CassandraContainer createCassandraContainer(int nodeIndex, String pulsarServiceUrl, Network testNetwork) { + return CassandraContainer.createCassandraContainerWithAgent( + PulsarSingleNodeC5Tests.CASSANDRA_IMAGE, testNetwork, nodeIndex, "c5", pulsarServiceUrl); + } + +} diff --git a/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarSingleNodeC5Tests.java b/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarSingleNodeC5Tests.java new file mode 100644 index 00000000..6d52ffba --- /dev/null +++ b/agent-c5/src/test/java/com/datastax/oss/cdc/agent/PulsarSingleNodeC5Tests.java @@ -0,0 +1,50 @@ +/** + * Copyright DataStax, Inc 2021. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package com.datastax.oss.cdc.agent; + +import com.datastax.oss.cdc.AgentTestUtil; +import com.datastax.oss.cdc.PulsarSingleNodeTests; +import com.datastax.testcontainers.cassandra.CassandraContainer; +import lombok.extern.slf4j.Slf4j; +import org.testcontainers.containers.Network; +import org.testcontainers.utility.DockerImageName; + +import java.util.Optional; + +@Slf4j +public class PulsarSingleNodeC5Tests extends PulsarSingleNodeTests { + + public static final DockerImageName CASSANDRA_IMAGE = DockerImageName.parse( + Optional.ofNullable(System.getenv("CASSANDRA_IMAGE")) + .orElse("cassandra:" + System.getProperty("cassandraVersion")) + ).asCompatibleSubstituteFor("cassandra"); + + public PulsarSingleNodeC5Tests() { + super(AgentTestUtil.Version.C5); + } + + @Override + public CassandraContainer createCassandraContainer(int nodeIndex, String pulsarServiceUrl, Network testNetwork) { + return CassandraContainer.createCassandraContainerWithAgent( + CASSANDRA_IMAGE, testNetwork, nodeIndex, "c5", pulsarServiceUrl); + } + + @Override + public int getSegmentSize() { + return 1024 * 1024; + } + +} diff --git a/agent-c5/src/test/resources/cassandra/cassandra.yaml b/agent-c5/src/test/resources/cassandra/cassandra.yaml new file mode 100644 index 00000000..bba869a5 --- /dev/null +++ b/agent-c5/src/test/resources/cassandra/cassandra.yaml @@ -0,0 +1,1430 @@ +# Cassandra storage config YAML + +# NOTE: +# See https://cassandra.apache.org/doc/latest/configuration/ for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# See https://cassandra.apache.org/doc/latest/getting_started/production.html#tokens for +# best practice information about num_tokens. +# +num_tokens: 16 + +# Triggers automatic allocation of num_tokens tokens for this node. The allocation +# algorithm attempts to choose tokens in a way that optimizes replicated load over +# the nodes in the datacenter for the replica factor. +# +# The load assigned to each node will be close to proportional to its number of +# vnodes. +# +# Only supported with the Murmur3Partitioner. + +# Replica factor is determined via the replication strategy used by the specified +# keyspace. +# allocate_tokens_for_keyspace: KEYSPACE + +# Replica factor is explicitly set, regardless of keyspace or datacenter. +# This is the replica factor within the datacenter, like NTS. +allocate_tokens_for_local_replication_factor: 3 + +# initial_token allows you to specify tokens manually. While you can use it with +# vnodes (num_tokens > 1, above) -- in which case you should provide a +# comma-separated list -- it's primarily used when adding nodes to legacy clusters +# that do not have vnodes enabled. +# initial_token: + +# May either be "true" or "false" to enable globally +hinted_handoff_enabled: true + +# When hinted_handoff_enabled is true, a black list of data centers that will not +# perform hinted handoff +# hinted_handoff_disabled_datacenters: +# - DC1 +# - DC2 + +# this defines the maximum amount of time a dead host will have hints +# generated. After it has been dead this long, new hints for it will not be +# created until it has been seen alive and gone down again. +max_hint_window_in_ms: 10800000 # 3 hours + +# Maximum throttle in KBs per second, per delivery thread. This will be +# reduced proportionally to the number of nodes in the cluster. (If there +# are two nodes in the cluster, each delivery thread will use the maximum +# rate; if there are three, each will throttle to half of the maximum, +# since we expect two nodes to be delivering hints simultaneously.) +hinted_handoff_throttle_in_kb: 1024 + +# Number of threads with which to deliver hints; +# Consider increasing this number when you have multi-dc deployments, since +# cross-dc handoff tends to be slower +max_hints_delivery_threads: 2 + +# Directory where Cassandra should store hints. +# If not set, the default directory is $CASSANDRA_HOME/data/hints. +# hints_directory: /var/lib/cassandra/hints + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: AllowAllAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: AllowAllAuthorizer + +# Part of the Authentication & Authorization backend, implementing IRoleManager; used +# to maintain grants and memberships between roles. +# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager, +# which stores role information in the system_auth keyspace. Most functions of the +# IRoleManager require an authenticated login, so unless the configured IAuthenticator +# actually implements authentication, most of this functionality will be unavailable. +# +# - CassandraRoleManager stores role data in the system_auth keyspace. Please +# increase system_auth keyspace replication factor if you use this role manager. +role_manager: CassandraRoleManager + +# Network authorization backend, implementing INetworkAuthorizer; used to restrict user +# access to certain DCs +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllNetworkAuthorizer, +# CassandraNetworkAuthorizer}. +# +# - AllowAllNetworkAuthorizer allows access to any DC to any user - set it to disable authorization. +# - CassandraNetworkAuthorizer stores permissions in system_auth.network_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +network_authorizer: AllowAllNetworkAuthorizer + +# Validity period for roles cache (fetching granted roles can be an expensive +# operation depending on the role manager, CassandraRoleManager is one example) +# Granted roles are cached for authenticated sessions in AuthenticatedUser and +# after the period specified here, become eligible for (async) reload. +# Defaults to 2000, set to 0 to disable caching entirely. +# Will be disabled automatically for AllowAllAuthenticator. +roles_validity_in_ms: 2000 + +# Refresh interval for roles cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If roles_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as roles_validity_in_ms. +# roles_update_interval_in_ms: 2000 + +# Validity period for permissions cache (fetching permissions can be an +# expensive operation depending on the authorizer, CassandraAuthorizer is +# one example). Defaults to 2000, set to 0 to disable. +# Will be disabled automatically for AllowAllAuthorizer. +permissions_validity_in_ms: 2000 + +# Refresh interval for permissions cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If permissions_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as permissions_validity_in_ms. +# permissions_update_interval_in_ms: 2000 + +# Validity period for credentials cache. This cache is tightly coupled to +# the provided PasswordAuthenticator implementation of IAuthenticator. If +# another IAuthenticator implementation is configured, this cache will not +# be automatically used and so the following settings will have no effect. +# Please note, credentials are cached in their encrypted form, so while +# activating this cache may reduce the number of queries made to the +# underlying table, it may not bring a significant reduction in the +# latency of individual authentication attempts. +# Defaults to 2000, set to 0 to disable credentials caching. +credentials_validity_in_ms: 2000 + +# Refresh interval for credentials cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If credentials_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as credentials_validity_in_ms. +# credentials_update_interval_in_ms: 2000 + +# The partitioner is responsible for distributing groups of rows (by +# partition key) across nodes in the cluster. The partitioner can NOT be +# changed without reloading all data. If you are adding nodes or upgrading, +# you should set this to the same partitioner that you are currently using. +# +# The default partitioner is the Murmur3Partitioner. Older partitioners +# such as the RandomPartitioner, ByteOrderedPartitioner, and +# OrderPreservingPartitioner have been included for backward compatibility only. +# For new clusters, you should NOT change this value. +# +partitioner: org.apache.cassandra.dht.Murmur3Partitioner + +# Directories where Cassandra should store data on disk. If multiple +# directories are specified, Cassandra will spread data evenly across +# them by partitioning the token ranges. +# If not set, the default directory is $CASSANDRA_HOME/data/data. +# data_file_directories: +# - /var/lib/cassandra/data + +# commit log. when running on magnetic HDD, this should be a +# separate spindle than the data directories. +# If not set, the default directory is $CASSANDRA_HOME/data/commitlog. +# commitlog_directory: /var/lib/cassandra/commitlog + +# Enable / disable CDC functionality on a per-node basis. This modifies the logic used +# for write path allocation rejection (standard: never reject. cdc: reject Mutation +# containing a CDC-enabled table if at space limit in cdc_raw_directory). +cdc_enabled: true + +# CommitLogSegments are moved to this directory on flush if cdc_enabled: true and the +# segment contains mutations for a CDC-enabled table. This should be placed on a +# separate spindle than the data directories. If not set, the default directory is +# $CASSANDRA_HOME/data/cdc_raw. +cdc_raw_directory: /var/lib/cassandra/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down the node and kill the JVM, so the node can be replaced. +# +# stop +# shut down the node, leaving the node effectively dead, but +# can still be inspected via JMX. +# +# stop_commit +# shutdown the commit log, letting writes collect but +# continuing to service reads, as in pre-2.0.5 Cassandra +# +# ignore +# ignore fatal errors and let the batches fail +commit_failure_policy: stop + +# Maximum size of the native protocol prepared statement cache +# +# Valid values are either "auto" (omitting the value) or a value greater 0. +# +# Note that specifying a too large value will result in long running GCs and possbily +# out-of-memory errors. Keep the value at a small fraction of the heap. +# +# If you constantly see "prepared statements discarded in the last minute because +# cache limit reached" messages, the first step is to investigate the root cause +# of these messages and check whether prepared statements are used correctly - +# i.e. use bind markers for variable parts. +# +# Do only change the default value, if you really have more prepared statements than +# fit in the cache. In most cases it is not neccessary to change this value. +# Constantly re-preparing statements is a performance penalty. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +prepared_statements_cache_size_mb: + +# Maximum size of the key cache in memory. +# +# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the +# minimum, sometimes more. The key cache is fairly tiny for the amount of +# time it saves, so it's worthwhile to use it at large numbers. +# The row cache saves even more time, but must contain the entire row, +# so it is extremely space-intensive. It's best to only use the +# row cache if you have hot rows or static rows. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache. +key_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the key cache. Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 14400 or 4 hours. +key_cache_save_period: 14400 + +# Number of keys from the key cache to save +# Disabled by default, meaning all keys are going to be saved +# key_cache_keys_to_save: 100 + +# Row cache implementation class name. Available implementations: +# +# org.apache.cassandra.cache.OHCProvider +# Fully off-heap row cache implementation (default). +# +# org.apache.cassandra.cache.SerializingCacheProvider +# This is the row cache implementation availabile +# in previous releases of Cassandra. +# row_cache_class_name: org.apache.cassandra.cache.OHCProvider + +# Maximum size of the row cache in memory. +# Please note that OHC cache implementation requires some additional off-heap memory to manage +# the map structures and some in-flight memory during operations before/after cache entries can be +# accounted against the cache capacity. This overhead is usually small compared to the whole capacity. +# Do not specify more memory that the system can afford in the worst usual situation and leave some +# headroom for OS block level cache. Do never allow your system to swap. +# +# Default value is 0, to disable row caching. +row_cache_size_in_mb: 0 + +# Duration in seconds after which Cassandra should save the row cache. +# Caches are saved to saved_caches_directory as specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 0 to disable saving the row cache. +row_cache_save_period: 0 + +# Number of keys from the row cache to save. +# Specify 0 (which is the default), meaning all keys are going to be saved +# row_cache_keys_to_save: 100 + +# Maximum size of the counter cache in memory. +# +# Counter cache helps to reduce counter locks' contention for hot counter cells. +# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before +# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration +# of the lock hold, helping with hot counter cell updates, but will not allow skipping +# the read entirely. Only the local (clock, count) tuple of a counter cell is kept +# in memory, not the whole counter, so it's relatively cheap. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache. +# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache. +counter_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the counter cache (keys only). Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Default is 7200 or 2 hours. +counter_cache_save_period: 7200 + +# Number of keys from the counter cache to save +# Disabled by default, meaning all keys are going to be saved +# counter_cache_keys_to_save: 100 + +# saved caches +# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches. +# saved_caches_directory: /var/lib/cassandra/saved_caches + +# commitlog_sync may be either "periodic", "group", or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been flushed to disk. Each incoming write will trigger the flush task. +# commitlog_sync_batch_window_in_ms is a deprecated value. Previously it had +# almost no value, and is being removed. +# +# commitlog_sync_batch_window_in_ms: 2 +# +# group mode is similar to batch mode, where Cassandra will not ack writes +# until the commit log has been flushed to disk. The difference is group +# mode will wait up to commitlog_sync_group_window_in_ms between flushes. +# +# commitlog_sync_group_window_in_ms: 1000 +# +# the default option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# When in periodic commitlog mode, the number of milliseconds to block writes +# while waiting for a slow disk flush to complete. +# periodic_commitlog_sync_lag_block_in_ms: + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 1 + +# Compression to apply to the commit log. If omitted, the commit log +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +# commitlog_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Compression to apply to SSTables as they flush for compressed tables. +# Note that tables without compression enabled do not respect this flag. +# +# As high ratio compressors like LZ4HC, Zstd, and Deflate can potentially +# block flushes for too long, the default is to flush with a known fast +# compressor in those cases. Options are: +# +# none : Flush without compressing blocks but while still doing checksums. +# fast : Flush with a fast compressor. If the table is already using a +# fast compressor that compressor is used. +# table: Always flush with the same compressor that the table uses. This +# was the pre 4.0 behavior. +# +# flush_compression: fast + +# any class that implements the SeedProvider interface and has a +# constructor that takes a Map of parameters will do. +seed_provider: + # Addresses of hosts that are deemed contact points. + # Cassandra nodes use this list of hosts to find each other and learn + # the topology of the ring. You must change this if you are running + # multiple nodes! + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + # seeds is actually a comma-delimited list of addresses. + # Ex: ",," + - seeds: "127.0.0.1:7000" + +# For workloads with more data than can fit in memory, Cassandra's +# bottleneck will be reads that need to fetch data from +# disk. "concurrent_reads" should be set to (16 * number_of_drives) in +# order to allow the operations to enqueue low enough in the stack +# that the OS and drives can reorder them. Same applies to +# "concurrent_counter_writes", since counter writes read the current +# values before incrementing and writing them back. +# +# On the other hand, since writes are almost never IO bound, the ideal +# number of "concurrent_writes" is dependent on the number of cores in +# your system; (8 * number_of_cores) is a good rule of thumb. +concurrent_reads: 32 +concurrent_writes: 32 +concurrent_counter_writes: 32 + +# For materialized view writes, as there is a read involved, so this should +# be limited by the less of concurrent reads or concurrent writes. +concurrent_materialized_view_writes: 32 + +# Maximum memory to use for inter-node and client-server networking buffers. +# +# Defaults to the smaller of 1/16 of heap or 128MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# networking_cache_size_in_mb: 128 + +# Enable the sstable chunk cache. The chunk cache will store recently accessed +# sections of the sstable in-memory as uncompressed buffers. +# file_cache_enabled: false + +# Maximum memory to use for sstable chunk cache and buffer pooling. +# 32MB of this are reserved for pooling buffers, the rest is used for chunk cache +# that holds uncompressed sstable chunks. +# Defaults to the smaller of 1/4 of heap or 512MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# file_cache_size_in_mb: 512 + +# Flag indicating whether to allocate on or off heap when the sstable buffer +# pool is exhausted, that is when it has exceeded the maximum memory +# file_cache_size_in_mb, beyond which it will not cache buffers but allocate on request. + +# buffer_pool_use_heap_if_exhausted: true + +# The strategy for optimizing disk read +# Possible values are: +# ssd (for solid state disks, the default) +# spinning (for spinning disks) +# disk_optimization_strategy: ssd + +# Total permitted memory to use for memtables. Cassandra will stop +# accepting writes when the limit is exceeded until a flush completes, +# and will trigger a flush based on memtable_cleanup_threshold +# If omitted, Cassandra will set both to 1/4 the size of the heap. +# memtable_heap_space_in_mb: 2048 +# memtable_offheap_space_in_mb: 2048 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Limit memory usage for Merkle tree calculations during repairs. The default +# is 1/16th of the available heap. The main tradeoff is that smaller trees +# have less resolution, which can lead to over-streaming data. If you see heap +# pressure during repairs, consider lowering this, but you cannot go below +# one megabyte. If you see lots of over-streaming, consider raising +# this or using subrange repair. +# +# For more details see https://issues.apache.org/jira/browse/CASSANDRA-14096. +# +# repair_session_space_in_mb: + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: false +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for legacy encrypted communication. This property is unused unless enabled in +# server_encryption_options (see below). As of cassandra 4.0, this property is deprecated +# as a single port can be used for either/both secure and insecure connections. +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +ssl_storage_port: 7001 + +# Address or interface to bind to and tell other Cassandra nodes to connect to. +# You _must_ change this if you want multiple nodes to be able to communicate! +# +# Set listen_address OR listen_interface, not both. +# +# Leaving it blank leaves it up to InetAddress.getLocalHost(). This +# will always do the Right Thing _if_ the node is properly configured +# (hostname, name resolution, etc), and the Right Thing is to use the +# address associated with the hostname (it might not be). If unresolvable +# it will fall back to InetAddress.getLoopbackAddress(), which is wrong for production systems. +# +# Setting listen_address to 0.0.0.0 is always wrong. +# +listen_address: localhost + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# The address on which the native transport is bound is defined by rpc_address. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests (note that idle threads are stopped +# after 30 seconds so there is not corresponding minimum setting). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Controls whether Cassandra honors older, yet currently supported, protocol versions. +# The default is true, which means all supported protocols will be honored. +native_transport_allow_older_protocols: true + +# Controls when idle client connections are closed. Idle connections are ones that had neither reads +# nor writes for a time period. +# +# Clients may implement heartbeats by sending OPTIONS native protocol message after a timeout, which +# will reset idle timeout timer on the server side. To close idle client connections, corresponding +# values for heartbeat intervals have to be set on the client side. +# +# Idle connection timeouts are disabled by default. +# native_transport_idle_timeout_in_ms: 60000 + +# The address or interface to bind the native transport server to. +# +# Set rpc_address OR rpc_interface, not both. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: localhost + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# RPC address to broadcast to drivers and other Cassandra nodes. This cannot +# be set to 0.0.0.0. If left blank, this will be set to the value of +# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must +# be set. +# broadcast_rpc_address: 1.2.3.4 + +# enable or disable keepalive on rpc/native connections +rpc_keepalive: true + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# See also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# Set to true to have Cassandra create a hard link to each sstable +# flushed or streamed locally in a backups/ subdirectory of the +# keyspace data. Removing these links is the operator's +# responsibility. +incremental_backups: false + +# Whether or not to take a snapshot before each compaction. Be +# careful using this option, since Cassandra won't clean up the +# snapshots for you. Mostly useful if you're paranoid when there +# is a data format change. +snapshot_before_compaction: false + +# Whether or not a snapshot is taken of the data before keyspace truncation +# or dropping of column families. The STRONGLY advised default of true +# should be used to provide data safety. If you set this flag to false, you will +# lose data on truncation or drop. +auto_snapshot: true + +# The act of creating or clearing a snapshot involves creating or removing +# potentially tens of thousands of links, which can cause significant performance +# impact, especially on consumer grade SSDs. A non-zero value here can +# be used to throttle these links to avoid negative performance impact of +# taking and clearing snapshots +snapshot_links_per_second: 0 + +# Granularity of the collation index of rows within a partition. +# Increase if your rows are large, or if you have a very large +# number of rows per partition. The competing goals are these: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# Number of simultaneous repair validations to allow. If not set or set to +# a value less than 1, it defaults to the value of concurrent_compactors. +# To set a value greeater than concurrent_compactors at startup, the system +# property cassandra.allow_unlimited_concurrent_validations must be set to +# true. To dynamically resize to a value > concurrent_compactors on a running +# node, first call the bypassConcurrentValidatorsLimit method on the +# org.apache.cassandra.db:type=StorageService mbean +# concurrent_validations: 0 + +# Number of simultaneous materialized view builder tasks to allow. +concurrent_materialized_view_builders: 1 + +# Throttles compaction to the given total throughput across the entire +# system. The faster you insert data, the faster you need to compact in +# order to keep the sstable count down, but in general, setting this to +# 16 to 32 times the rate you are inserting data is more than sufficient. +# Setting this to 0 disables throttling. Note that this accounts for all types +# of compaction, including validation compaction (building Merkle trees +# for repairs). +compaction_throughput_mb_per_sec: 64 + +# When compacting, the replacement sstable(s) can be opened before they +# are completely written, and used in place of the prior sstables for +# any range that has been written. This helps to smoothly transfer reads +# between the sstables, reducing page cache churn and keeping hot rows hot +sstable_preemptive_open_interval_in_mb: 50 + +# When enabled, permits Cassandra to zero-copy stream entire eligible +# SSTables between nodes, including every component. +# This speeds up the network transfer significantly subject to +# throttling specified by stream_throughput_outbound_megabits_per_sec. +# Enabling this will reduce the GC pressure on sending and receiving node. +# When unset, the default is enabled. While this feature tries to keep the +# disks balanced, it cannot guarantee it. This feature will be automatically +# disabled if internode encryption is enabled. Currently this can be used with +# Leveled Compaction. Once CASSANDRA-14586 is fixed other compaction strategies +# will benefit as well when used in combination with CASSANDRA-6696. +# stream_entire_sstables: true + +# Throttles all outbound streaming file transfers on this node to the +# given total throughput in Mbps. This is necessary because Cassandra does +# mostly sequential IO when streaming data during bootstrap or repair, which +# can lead to saturating the network connection and degrading rpc performance. +# When unset, the default is 200 Mbps or 25 MB/s. +# stream_throughput_outbound_megabits_per_sec: 200 + +# Throttles all streaming file transfer between the datacenters, +# this setting allows users to throttle inter dc stream throughput in addition +# to throttling all network stream traffic as configured with +# stream_throughput_outbound_megabits_per_sec +# When unset, the default is 200 Mbps or 25 MB/s +# inter_dc_stream_throughput_outbound_megabits_per_sec: 200 + +# How long the coordinator should wait for read operations to complete. +# Lowest acceptable value is 10 ms. +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete. +# Lowest acceptable value is 10 ms. +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete. +# Lowest acceptable value is 10 ms. +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete. +# Lowest acceptable value is 10 ms. +counter_write_request_timeout_in_ms: 5000 +# How long a coordinator should continue to retry a CAS operation +# that contends with other proposals for the same row. +# Lowest acceptable value is 10 ms. +cas_contention_timeout_in_ms: 1000 +# How long the coordinator should wait for truncates to complete +# (This can be much longer, because unless auto_snapshot is disabled +# we need to flush first so we can snapshot before removing the data.) +# Lowest acceptable value is 10 ms. +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations. +# Lowest acceptable value is 10 ms. +request_timeout_in_ms: 10000 + +# Defensive settings for protecting Cassandra from true network partitions. +# See (CASSANDRA-14358) for details. +# +# The amount of time to wait for internode tcp connections to establish. +# internode_tcp_connect_timeout_in_ms = 2000 +# +# The amount of time unacknowledged data is allowed on a connection before we throw out the connection +# Note this is only supported on Linux + epoll, and it appears to behave oddly above a setting of 30000 +# (it takes much longer than 30s) as of Linux 4.12. If you want something that high set this to 0 +# which picks up the OS default and configure the net.ipv4.tcp_retries2 sysctl to be ~8. +# internode_tcp_user_timeout_in_ms = 30000 + +# The amount of time unacknowledged data is allowed on a streaming connection. +# The default is 5 minutes. Increase it or set it to 0 in order to increase the timeout. +# internode_streaming_tcp_user_timeout_in_ms = 300000 + +# The maximum continuous period a connection may be unwritable in application space +# internode_application_timeout_in_ms = 30000 + +# Global, per-endpoint and per-connection limits imposed on messages queued for delivery to other nodes +# and waiting to be processed on arrival from other nodes in the cluster. These limits are applied to the on-wire +# size of the message being sent or received. +# +# The basic per-link limit is consumed in isolation before any endpoint or global limit is imposed. +# Each node-pair has three links: urgent, small and large. So any given node may have a maximum of +# N*3*(internode_application_send_queue_capacity_in_bytes+internode_application_receive_queue_capacity_in_bytes) +# messages queued without any coordination between them although in practice, with token-aware routing, only RF*tokens +# nodes should need to communicate with significant bandwidth. +# +# The per-endpoint limit is imposed on all messages exceeding the per-link limit, simultaneously with the global limit, +# on all links to or from a single node in the cluster. +# The global limit is imposed on all messages exceeding the per-link limit, simultaneously with the per-endpoint limit, +# on all links to or from any node in the cluster. +# +# internode_application_send_queue_capacity_in_bytes: 4194304 #4MiB +# internode_application_send_queue_reserve_endpoint_capacity_in_bytes: 134217728 #128MiB +# internode_application_send_queue_reserve_global_capacity_in_bytes: 536870912 #512MiB +# internode_application_receive_queue_capacity_in_bytes: 4194304 #4MiB +# internode_application_receive_queue_reserve_endpoint_capacity_in_bytes: 134217728 #128MiB +# internode_application_receive_queue_reserve_global_capacity_in_bytes: 536870912 #512MiB + + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: It is generally assumed that users have setup NTP on their clusters, and that clocks are modestly in sync, +# since this is a requirement for general correctness of last write wins. +#cross_node_timeout: true + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# Limit number of connections per host for streaming +# Increase this when you notice that joins are CPU-bound rather that network +# bound (for example a few nodes with big files). +# streaming_connections_per_host: 1 + + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 1.0 + +# Configure server-to-server internode encryption +# +# JVM and netty defaults for supported SSL socket protocols and cipher suites can +# be replaced using custom encryption options. This is not recommended +# unless you have policies in place that dictate certain settings, or +# need to disable vulnerable ciphers or protocols in case the JVM cannot +# be updated. +# +# FIPS compliant settings can be configured at JVM level and should not +# involve changing encryption settings here: +# https://docs.oracle.com/javase/8/docs/technotes/guides/security/jsse/FIPS.html +# +# **NOTE** this default configuration is an insecure configuration. If you need to +# enable server-to-server encryption generate server keystores (and truststores for mutual +# authentication) per: +# http://download.oracle.com/javase/8/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# Then perform the following configuration changes: +# +# Step 1: Set internode_encryption= and explicitly set optional=true. Restart all nodes +# +# Step 2: Set optional=false (or remove it) and if you generated truststores and want to use mutual +# auth set require_client_auth=true. Restart all nodes +server_encryption_options: + # On outbound connections, determine which type of peers to securely connect to. + # The available options are : + # none : Do not encrypt outgoing connections + # dc : Encrypt connections to peers in other datacenters but not within datacenters + # rack : Encrypt connections to peers in other racks but not within racks + # all : Always use encrypted connections + internode_encryption: none + # When set to true, encrypted and unencrypted connections are allowed on the storage_port + # This should _only be true_ while in unencrypted or transitional operation + # optional defaults to true if internode_encryption is none + # optional: true + # If enabled, will open up an encrypted listening socket on ssl_storage_port. Should only be used + # during upgrade to 4.0; otherwise, set to false. + enable_legacy_ssl_storage_port: false + # Set to a valid keystore if internode_encryption is dc, rack or all + keystore: conf/.keystore + keystore_password: cassandra + # Verify peer server certificates + require_client_auth: false + # Set to a valid trustore if require_client_auth is true + truststore: conf/.truststore + truststore_password: cassandra + # Verify that the host name in the certificate matches the connected host + require_endpoint_verification: false + # More advanced defaults: + # protocol: TLS + # store_type: JKS + # cipher_suites: [ + # TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, + # TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA, + # TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA, TLS_RSA_WITH_AES_128_GCM_SHA256, TLS_RSA_WITH_AES_128_CBC_SHA, + # TLS_RSA_WITH_AES_256_CBC_SHA + # ] + +# Configure client-to-server encryption. +# +# **NOTE** this default configuration is an insecure configuration. If you need to +# enable client-to-server encryption generate server keystores (and truststores for mutual +# authentication) per: +# http://download.oracle.com/javase/8/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# Then perform the following configuration changes: +# +# Step 1: Set enabled=true and explicitly set optional=true. Restart all nodes +# +# Step 2: Set optional=false (or remove it) and if you generated truststores and want to use mutual +# auth set require_client_auth=true. Restart all nodes +client_encryption_options: + # Enable client-to-server encryption + enabled: false + # When set to true, encrypted and unencrypted connections are allowed on the native_transport_port + # This should _only be true_ while in unencrypted or transitional operation + # optional defaults to true when enabled is false, and false when enabled is true. + # optional: true + # Set keystore and keystore_password to valid keystores if enabled is true + keystore: conf/.keystore + keystore_password: cassandra + # Verify client certificates + require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults: + # protocol: TLS + # store_type: JKS + # cipher_suites: [ + # TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, + # TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA, + # TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA, TLS_RSA_WITH_AES_128_GCM_SHA256, TLS_RSA_WITH_AES_128_CBC_SHA, + # TLS_RSA_WITH_AES_256_CBC_SHA + # ] + +# internode_compression controls whether traffic between nodes is +# compressed. +# Can be: +# +# all +# all traffic is compressed +# +# dc +# traffic between different datacenters is compressed +# +# none +# nothing is compressed. +internode_compression: dc + +# Enable or disable tcp_nodelay for inter-dc communication. +# Disabling it will result in larger (but fewer) network packets being sent, +# reducing overhead from the TCP protocol itself, at the cost of increasing +# latency if you block for cross-datacenter responses. +inter_dc_tcp_nodelay: false + +# TTL for different trace types used during logging of the repair process. +tracetype_query_ttl: 86400 +tracetype_repair_ttl: 604800 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: false + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation. +# Lowering this value on Windows can provide much tighter latency and better throughput, however +# some virtualized environments may see a negative performance impact from changing this setting +# below their system default. The sysinternals 'clockres' tool can confirm your system's default +# setting. +windows_timer_interval: 1 + + +# Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from +# a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by +# the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys +# can still (and should!) be in the keystore and will be used on decrypt operations +# (to handle the case of key rotation). +# +# It is strongly recommended to download and install Java Cryptography Extension (JCE) +# Unlimited Strength Jurisdiction Policy Files for your version of the JDK. +# (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html) +# +# Currently, only the following file types are supported for transparent data encryption, although +# more are coming in future cassandra releases: commitlog, hints +transparent_data_encryption_options: + enabled: false + chunk_length_kb: 64 + cipher: AES/CBC/PKCS5Padding + key_alias: testing:1 + # CBC IV length for AES needs to be 16 bytes (which is also the default size) + # iv_length: 16 + key_provider: + - class_name: org.apache.cassandra.security.JKSKeyProvider + parameters: + - keystore: conf/.keystore + keystore_password: cassandra + store_type: JCEKS + key_password: cassandra + + +##################### +# SAFETY THRESHOLDS # +##################### + +# When executing a scan, within or across a partition, we need to keep the +# tombstones seen in memory so we can return them to the coordinator, which +# will use them to make sure other replicas also know about the deleted rows. +# With workloads that generate a lot of tombstones, this can cause performance +# problems and even exaust the server heap. +# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) +# Adjust the thresholds here if you understand the dangers and want to +# scan more tombstones anyway. These thresholds may also be adjusted at runtime +# using the StorageService mbean. +tombstone_warn_threshold: 1000 +tombstone_failure_threshold: 100000 + +# Filtering and secondary index queries at read consistency levels above ONE/LOCAL_ONE use a +# mechanism called replica filtering protection to ensure that results from stale replicas do +# not violate consistency. (See CASSANDRA-8272 and CASSANDRA-15907 for more details.) This +# mechanism materializes replica results by partition on-heap at the coordinator. The more possibly +# stale results returned by the replicas, the more rows materialized during the query. +replica_filtering_protection: + # These thresholds exist to limit the damage severely out-of-date replicas can cause during these + # queries. They limit the number of rows from all replicas individual index and filtering queries + # can materialize on-heap to return correct results at the desired read consistency level. + # + # "cached_replica_rows_warn_threshold" is the per-query threshold at which a warning will be logged. + # "cached_replica_rows_fail_threshold" is the per-query threshold at which the query will fail. + # + # These thresholds may also be adjusted at runtime using the StorageService mbean. + # + # If the failure threshold is breached, it is likely that either the current page/fetch size + # is too large or one or more replicas is severely out-of-sync and in need of repair. + cached_rows_warn_threshold: 2000 + cached_rows_fail_threshold: 32000 + +# Log WARN on any multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than 200 ms will be logged at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level +# Adjust the threshold based on your application throughput requirement. Setting to 0 +# will deactivate the feature. +# gc_warn_threshold_in_ms: 1000 + +# Maximum size of any value in SSTables. Safety measure to detect SSTable corruption +# early. Any value size larger than this threshold will result into marking an SSTable +# as corrupted. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 + +# Track a metric per keyspace indicating whether replication achieved the ideal consistency +# level for writes without timing out. This is different from the consistency level requested by +# each write which may be lower in order to facilitate availability. +# ideal_consistency_level: EACH_QUORUM + +# Automatically upgrade sstables after upgrade - if there is no ordinary compaction to do, the +# oldest non-upgraded sstable will get upgraded to the latest version +# automatic_sstable_upgrade: false +# Limit the number of concurrent sstable upgrades +# max_concurrent_automatic_sstable_upgrades: 1 + +# Audit logging - Logs every incoming CQL command request, authentication to a node. See the docs +# on audit_logging for full details about the various configuration options. +audit_logging_options: + enabled: false + logger: + - class_name: BinAuditLogger + # audit_logs_dir: + # included_keyspaces: + # excluded_keyspaces: system, system_schema, system_virtual_schema + # included_categories: + # excluded_categories: + # included_users: + # excluded_users: + # roll_cycle: HOURLY + # block: true + # max_queue_weight: 268435456 # 256 MiB + # max_log_size: 17179869184 # 16 GiB + ## archive command is "/path/to/script.sh %path" where %path is replaced with the file being rolled: + # archive_command: + # max_archive_retries: 10 + + +# default options for full query logging - these can be overridden from command line when executing +# nodetool enablefullquerylog +#full_query_logging_options: + # log_dir: + # roll_cycle: HOURLY + # block: true + # max_queue_weight: 268435456 # 256 MiB + # max_log_size: 17179869184 # 16 GiB + ## archive command is "/path/to/script.sh %path" where %path is replaced with the file being rolled: + # archive_command: + # max_archive_retries: 10 + +# validate tombstones on reads and compaction +# can be either "disabled", "warn" or "exception" +# corrupted_tombstone_strategy: disabled + +# Diagnostic Events # +# If enabled, diagnostic events can be helpful for troubleshooting operational issues. Emitted events contain details +# on internal state and temporal relationships across events, accessible by clients via JMX. +diagnostic_events_enabled: false + +# Use native transport TCP message coalescing. If on upgrade to 4.0 you found your throughput decreasing, and in +# particular you run an old kernel or have very fewer client connections, this option might be worth evaluating. +#native_transport_flush_in_batches_legacy: false + +# Enable tracking of repaired state of data during reads and comparison between replicas +# Mismatches between the repaired sets of replicas can be characterized as either confirmed +# or unconfirmed. In this context, unconfirmed indicates that the presence of pending repair +# sessions, unrepaired partition tombstones, or some other condition means that the disparity +# cannot be considered conclusive. Confirmed mismatches should be a trigger for investigation +# as they may be indicative of corruption or data loss. +# There are separate flags for range vs partition reads as single partition reads are only tracked +# when CL > 1 and a digest mismatch occurs. Currently, range queries don't use digests so if +# enabled for range reads, all range reads will include repaired data tracking. As this adds +# some overhead, operators may wish to disable it whilst still enabling it for partition reads +repaired_data_tracking_for_range_reads_enabled: false +repaired_data_tracking_for_partition_reads_enabled: false +# If false, only confirmed mismatches will be reported. If true, a separate metric for unconfirmed +# mismatches will also be recorded. This is to avoid potential signal:noise issues are unconfirmed +# mismatches are less actionable than confirmed ones. +report_unconfirmed_repaired_data_mismatches: false + +# Having many tables and/or keyspaces negatively affects performance of many operations in the +# cluster. When the number of tables/keyspaces in the cluster exceeds the following thresholds +# a client warning will be sent back to the user when creating a table or keyspace. +# table_count_warn_threshold: 150 +# keyspace_count_warn_threshold: 40 + +######################### +# EXPERIMENTAL FEATURES # +######################### + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: false + +# Enables SASI index creation on this node. +# SASI indexes are considered experimental and are not recommended for production use. +enable_sasi_indexes: false + +# Enables creation of transiently replicated keyspaces on this node. +# Transient replication is experimental and is not recommended for production use. +enable_transient_replication: false diff --git a/agent-c5/src/test/resources/cassandra/logback.xml b/agent-c5/src/test/resources/cassandra/logback.xml new file mode 100644 index 00000000..d4261fbe --- /dev/null +++ b/agent-c5/src/test/resources/cassandra/logback.xml @@ -0,0 +1,103 @@ + + + + + + + + + + + + + + TRACE + + ${cassandra.logdir}/system.log + + + ${cassandra.logdir}/system.log.%d{yyyy-MM-dd}.%i.zip + + 50MB + 7 + 5GB + + + %-5level [%thread] %date{ISO8601} %F:%L - %msg%n + + + + + + + ${cassandra.logdir}/debug.log + + + ${cassandra.logdir}/debug.log.%d{yyyy-MM-dd}.%i.zip + + 50MB + 7 + 5GB + + + %-5level [%thread] %date{ISO8601} %F:%L %m %msg%n + + + + + + + 1024 + 0 + true + + + + + + + + TRACE + + + %-5level [%thread] %date{ISO8601} %F:%L - %msg%n + + + + + + + + + + + + + + + + diff --git a/agent-c5/src/test/resources/logback-test.xml b/agent-c5/src/test/resources/logback-test.xml new file mode 100644 index 00000000..6a95771c --- /dev/null +++ b/agent-c5/src/test/resources/logback-test.xml @@ -0,0 +1,15 @@ + + + + %d{HH:mm:ss.SSS} [%thread] %-5level %logger - %msg%n + + + + + + + + + + + diff --git a/gradle.properties b/gradle.properties index 8762d9d6..4c5c4748 100644 --- a/gradle.properties +++ b/gradle.properties @@ -12,6 +12,7 @@ lombokVersion=1.18.20 ossDriverVersion=4.16.0 cassandra3Version=3.11.10 cassandra4Version=4.0.4 +cassandra5Version=5.0.4 dse4Version=6.8.23 pulsarGroup=org.apache.pulsar @@ -42,7 +43,7 @@ commitlog_sync_period_in_ms=2000 cdc_total_space_in_mb=70 # default docker repo + slash -dockerRepo=myrepo/ +dockerRepo=cassandra-cdc/ # CDC backfilling Client dsbulkVersion=1.10.0 diff --git a/settings.gradle b/settings.gradle index e23f93e5..5bd913ec 100644 --- a/settings.gradle +++ b/settings.gradle @@ -22,6 +22,8 @@ include 'agent-c3' include 'agent-c4' +include 'agent-c5' + if (startParameter.projectProperties.containsKey("dse4")) { include 'agent-dse4' } diff --git a/testcontainers/src/main/java/com/datastax/oss/cdc/AgentTestUtil.java b/testcontainers/src/main/java/com/datastax/oss/cdc/AgentTestUtil.java index 1091dd6a..94fb29ed 100644 --- a/testcontainers/src/main/java/com/datastax/oss/cdc/AgentTestUtil.java +++ b/testcontainers/src/main/java/com/datastax/oss/cdc/AgentTestUtil.java @@ -91,6 +91,7 @@ public static ByteBuffer randomizeBuffer(int size) { public enum Version { C3, // Cassandra 3.11.x C4, // Cassandra 4.x + C5, // Cassandra 5.x DSE4 // Datastax Enterprise Server } } From 2d2f8c5a6a52f502c612bf499ba4c9d805fe24d5 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 00:36:11 +0530 Subject: [PATCH 02/10] add c5 to ci workflow --- .github/workflows/ci.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index af4fa504..d2d2936c 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -1,6 +1,7 @@ name: CI on: + workflow_dispatch: pull_request: branches: - master @@ -37,7 +38,7 @@ jobs: strategy: fail-fast: false matrix: - module: ['agent', 'agent-c3', 'agent-c4', 'agent-dse4', 'connector'] + module: ['agent', 'agent-c3', 'agent-c4', 'agent-c5','agent-dse4', 'connector'] jdk: ['11', '17'] pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] steps: From 7c419517ba722c78cd5604eb6ca747474a8d1ee8 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 00:43:53 +0530 Subject: [PATCH 03/10] declare java build version for c5 --- agent-c5/build.gradle | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/agent-c5/build.gradle b/agent-c5/build.gradle index 63accc37..798d4f44 100644 --- a/agent-c5/build.gradle +++ b/agent-c5/build.gradle @@ -7,6 +7,21 @@ plugins { id 'docker-compose' } +// Cassandra 5.0 requires Java 17+ due to dependencies like Caffeine 3.1.8 +java { + toolchain { + languageVersion = JavaLanguageVersion.of(17) + } +} + +sourceCompatibility = 17 +targetCompatibility = 17 + +compileJava { + sourceCompatibility = 17 + targetCompatibility = 17 +} + application { mainClass = "$mainClassName" } From c20b6077d303a497be3057450a174d531c093374 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 00:47:07 +0530 Subject: [PATCH 04/10] revert commits that are not needed --- .github/workflows/ci.yaml | 1 - gradle.properties | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index d2d2936c..c47c4753 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -1,7 +1,6 @@ name: CI on: - workflow_dispatch: pull_request: branches: - master diff --git a/gradle.properties b/gradle.properties index 4c5c4748..9c4eda93 100644 --- a/gradle.properties +++ b/gradle.properties @@ -43,7 +43,7 @@ commitlog_sync_period_in_ms=2000 cdc_total_space_in_mb=70 # default docker repo + slash -dockerRepo=cassandra-cdc/ +dockerRepo=myrepo/ # CDC backfilling Client dsbulkVersion=1.10.0 From e76693be22f735f2bd7660acdc83586bb214295c Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 00:49:03 +0530 Subject: [PATCH 05/10] workflow updates --- .github/workflows/backfill-ci.yaml | 2 +- .github/workflows/ci.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/backfill-ci.yaml b/.github/workflows/backfill-ci.yaml index 0fc77f7e..c05ffba0 100644 --- a/.github/workflows/backfill-ci.yaml +++ b/.github/workflows/backfill-ci.yaml @@ -39,7 +39,7 @@ jobs: matrix: jdk: ['11'] # TODO: Enable java 17 tests https://issues.apache.org/jira/browse/CASSANDRA-16895 pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] - cassandraFamily: ['c3', 'c4', 'dse4'] + cassandraFamily: ['c3', 'c4', 'c5'] steps: - uses: actions/checkout@v3 - name: Set up JDK ${{ matrix.jdk }} diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index c47c4753..0cc7fdfa 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -37,7 +37,7 @@ jobs: strategy: fail-fast: false matrix: - module: ['agent', 'agent-c3', 'agent-c4', 'agent-c5','agent-dse4', 'connector'] + module: ['agent', 'agent-c3', 'agent-c4', 'agent-c5', 'connector'] jdk: ['11', '17'] pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] steps: From 67566f3779fcd5b92a93f0c1d39a854a7bc0aa56 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 01:37:42 +0530 Subject: [PATCH 06/10] only c5 with datastax lunastreaming --- .github/workflows/backfill-ci.yaml | 4 ++-- .github/workflows/ci.yaml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/workflows/backfill-ci.yaml b/.github/workflows/backfill-ci.yaml index c05ffba0..450625fd 100644 --- a/.github/workflows/backfill-ci.yaml +++ b/.github/workflows/backfill-ci.yaml @@ -38,8 +38,8 @@ jobs: fail-fast: false matrix: jdk: ['11'] # TODO: Enable java 17 tests https://issues.apache.org/jira/browse/CASSANDRA-16895 - pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] - cassandraFamily: ['c3', 'c4', 'c5'] + pulsarImage: ['datastax/lunastreaming:4.0_3.6'] + cassandraFamily: ['c5'] steps: - uses: actions/checkout@v3 - name: Set up JDK ${{ matrix.jdk }} diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index 0cc7fdfa..7c2493db 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -37,9 +37,9 @@ jobs: strategy: fail-fast: false matrix: - module: ['agent', 'agent-c3', 'agent-c4', 'agent-c5', 'connector'] + module: ['agent-c5', 'connector'] jdk: ['11', '17'] - pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] + pulsarImage: ['datastax/lunastreaming:4.0_3.6'] steps: - uses: actions/checkout@v3 - name: Set up JDK ${{ matrix.jdk }} From dc50743d046334b10de72e80350a2fdad6415e37 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 01:41:26 +0530 Subject: [PATCH 07/10] add c5 to backfill gradle --- backfill-cli/build.gradle | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/backfill-cli/build.gradle b/backfill-cli/build.gradle index 313f4864..d78ba851 100644 --- a/backfill-cli/build.gradle +++ b/backfill-cli/build.gradle @@ -155,13 +155,19 @@ task e2eTest(type: Test) { systemProperty "cassandraFamily", "c4" systemProperty "agentBuildDir", project(':agent-c4').buildDir environment 'CASSANDRA_IMAGE', 'cassandra:' + cassandra4Version + } else if (cassandraFamily == "c5") { + dependsOn project(':agent-c5').shadowJar + systemProperty "cassandraFamily", "c5" + systemProperty "agentBuildDir", project(':agent-c5').buildDir + environment 'CASSANDRA_IMAGE', 'cassandra:' + cassandra5Version } else if (cassandraFamily == "dse4") { dependsOn project(':agent-dse4').shadowJar systemProperty "cassandraFamily", "dse4" systemProperty "agentBuildDir", project(':agent-dse4').buildDir environment 'CASSANDRA_IMAGE', 'datastax/dse-server:' + dse4Version + } else { - throw new GradleException("Unknown Cassandra family. Use -PcassandraFamily=[c3|c4|dse4]") + throw new GradleException("Unknown Cassandra family. Use -PcassandraFamily=[c3|c4|c5|dse4]") } systemProperty "connectorBuildDir", project(':connector').buildDir From f1227c62637ea0ad154dd9abbc94642941c6b640 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 02:23:03 +0530 Subject: [PATCH 08/10] backfill-cli c5 agent --- .../src/test/resources/c5/cassandra.yaml | 1430 +++++++++++++++++ .../src/test/resources/c5/logback.xml | 103 ++ 2 files changed, 1533 insertions(+) create mode 100644 backfill-cli/src/test/resources/c5/cassandra.yaml create mode 100644 backfill-cli/src/test/resources/c5/logback.xml diff --git a/backfill-cli/src/test/resources/c5/cassandra.yaml b/backfill-cli/src/test/resources/c5/cassandra.yaml new file mode 100644 index 00000000..bba869a5 --- /dev/null +++ b/backfill-cli/src/test/resources/c5/cassandra.yaml @@ -0,0 +1,1430 @@ +# Cassandra storage config YAML + +# NOTE: +# See https://cassandra.apache.org/doc/latest/configuration/ for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# See https://cassandra.apache.org/doc/latest/getting_started/production.html#tokens for +# best practice information about num_tokens. +# +num_tokens: 16 + +# Triggers automatic allocation of num_tokens tokens for this node. The allocation +# algorithm attempts to choose tokens in a way that optimizes replicated load over +# the nodes in the datacenter for the replica factor. +# +# The load assigned to each node will be close to proportional to its number of +# vnodes. +# +# Only supported with the Murmur3Partitioner. + +# Replica factor is determined via the replication strategy used by the specified +# keyspace. +# allocate_tokens_for_keyspace: KEYSPACE + +# Replica factor is explicitly set, regardless of keyspace or datacenter. +# This is the replica factor within the datacenter, like NTS. +allocate_tokens_for_local_replication_factor: 3 + +# initial_token allows you to specify tokens manually. While you can use it with +# vnodes (num_tokens > 1, above) -- in which case you should provide a +# comma-separated list -- it's primarily used when adding nodes to legacy clusters +# that do not have vnodes enabled. +# initial_token: + +# May either be "true" or "false" to enable globally +hinted_handoff_enabled: true + +# When hinted_handoff_enabled is true, a black list of data centers that will not +# perform hinted handoff +# hinted_handoff_disabled_datacenters: +# - DC1 +# - DC2 + +# this defines the maximum amount of time a dead host will have hints +# generated. After it has been dead this long, new hints for it will not be +# created until it has been seen alive and gone down again. +max_hint_window_in_ms: 10800000 # 3 hours + +# Maximum throttle in KBs per second, per delivery thread. This will be +# reduced proportionally to the number of nodes in the cluster. (If there +# are two nodes in the cluster, each delivery thread will use the maximum +# rate; if there are three, each will throttle to half of the maximum, +# since we expect two nodes to be delivering hints simultaneously.) +hinted_handoff_throttle_in_kb: 1024 + +# Number of threads with which to deliver hints; +# Consider increasing this number when you have multi-dc deployments, since +# cross-dc handoff tends to be slower +max_hints_delivery_threads: 2 + +# Directory where Cassandra should store hints. +# If not set, the default directory is $CASSANDRA_HOME/data/hints. +# hints_directory: /var/lib/cassandra/hints + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: AllowAllAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: AllowAllAuthorizer + +# Part of the Authentication & Authorization backend, implementing IRoleManager; used +# to maintain grants and memberships between roles. +# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager, +# which stores role information in the system_auth keyspace. Most functions of the +# IRoleManager require an authenticated login, so unless the configured IAuthenticator +# actually implements authentication, most of this functionality will be unavailable. +# +# - CassandraRoleManager stores role data in the system_auth keyspace. Please +# increase system_auth keyspace replication factor if you use this role manager. +role_manager: CassandraRoleManager + +# Network authorization backend, implementing INetworkAuthorizer; used to restrict user +# access to certain DCs +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllNetworkAuthorizer, +# CassandraNetworkAuthorizer}. +# +# - AllowAllNetworkAuthorizer allows access to any DC to any user - set it to disable authorization. +# - CassandraNetworkAuthorizer stores permissions in system_auth.network_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +network_authorizer: AllowAllNetworkAuthorizer + +# Validity period for roles cache (fetching granted roles can be an expensive +# operation depending on the role manager, CassandraRoleManager is one example) +# Granted roles are cached for authenticated sessions in AuthenticatedUser and +# after the period specified here, become eligible for (async) reload. +# Defaults to 2000, set to 0 to disable caching entirely. +# Will be disabled automatically for AllowAllAuthenticator. +roles_validity_in_ms: 2000 + +# Refresh interval for roles cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If roles_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as roles_validity_in_ms. +# roles_update_interval_in_ms: 2000 + +# Validity period for permissions cache (fetching permissions can be an +# expensive operation depending on the authorizer, CassandraAuthorizer is +# one example). Defaults to 2000, set to 0 to disable. +# Will be disabled automatically for AllowAllAuthorizer. +permissions_validity_in_ms: 2000 + +# Refresh interval for permissions cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If permissions_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as permissions_validity_in_ms. +# permissions_update_interval_in_ms: 2000 + +# Validity period for credentials cache. This cache is tightly coupled to +# the provided PasswordAuthenticator implementation of IAuthenticator. If +# another IAuthenticator implementation is configured, this cache will not +# be automatically used and so the following settings will have no effect. +# Please note, credentials are cached in their encrypted form, so while +# activating this cache may reduce the number of queries made to the +# underlying table, it may not bring a significant reduction in the +# latency of individual authentication attempts. +# Defaults to 2000, set to 0 to disable credentials caching. +credentials_validity_in_ms: 2000 + +# Refresh interval for credentials cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If credentials_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as credentials_validity_in_ms. +# credentials_update_interval_in_ms: 2000 + +# The partitioner is responsible for distributing groups of rows (by +# partition key) across nodes in the cluster. The partitioner can NOT be +# changed without reloading all data. If you are adding nodes or upgrading, +# you should set this to the same partitioner that you are currently using. +# +# The default partitioner is the Murmur3Partitioner. Older partitioners +# such as the RandomPartitioner, ByteOrderedPartitioner, and +# OrderPreservingPartitioner have been included for backward compatibility only. +# For new clusters, you should NOT change this value. +# +partitioner: org.apache.cassandra.dht.Murmur3Partitioner + +# Directories where Cassandra should store data on disk. If multiple +# directories are specified, Cassandra will spread data evenly across +# them by partitioning the token ranges. +# If not set, the default directory is $CASSANDRA_HOME/data/data. +# data_file_directories: +# - /var/lib/cassandra/data + +# commit log. when running on magnetic HDD, this should be a +# separate spindle than the data directories. +# If not set, the default directory is $CASSANDRA_HOME/data/commitlog. +# commitlog_directory: /var/lib/cassandra/commitlog + +# Enable / disable CDC functionality on a per-node basis. This modifies the logic used +# for write path allocation rejection (standard: never reject. cdc: reject Mutation +# containing a CDC-enabled table if at space limit in cdc_raw_directory). +cdc_enabled: true + +# CommitLogSegments are moved to this directory on flush if cdc_enabled: true and the +# segment contains mutations for a CDC-enabled table. This should be placed on a +# separate spindle than the data directories. If not set, the default directory is +# $CASSANDRA_HOME/data/cdc_raw. +cdc_raw_directory: /var/lib/cassandra/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down the node and kill the JVM, so the node can be replaced. +# +# stop +# shut down the node, leaving the node effectively dead, but +# can still be inspected via JMX. +# +# stop_commit +# shutdown the commit log, letting writes collect but +# continuing to service reads, as in pre-2.0.5 Cassandra +# +# ignore +# ignore fatal errors and let the batches fail +commit_failure_policy: stop + +# Maximum size of the native protocol prepared statement cache +# +# Valid values are either "auto" (omitting the value) or a value greater 0. +# +# Note that specifying a too large value will result in long running GCs and possbily +# out-of-memory errors. Keep the value at a small fraction of the heap. +# +# If you constantly see "prepared statements discarded in the last minute because +# cache limit reached" messages, the first step is to investigate the root cause +# of these messages and check whether prepared statements are used correctly - +# i.e. use bind markers for variable parts. +# +# Do only change the default value, if you really have more prepared statements than +# fit in the cache. In most cases it is not neccessary to change this value. +# Constantly re-preparing statements is a performance penalty. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +prepared_statements_cache_size_mb: + +# Maximum size of the key cache in memory. +# +# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the +# minimum, sometimes more. The key cache is fairly tiny for the amount of +# time it saves, so it's worthwhile to use it at large numbers. +# The row cache saves even more time, but must contain the entire row, +# so it is extremely space-intensive. It's best to only use the +# row cache if you have hot rows or static rows. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache. +key_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the key cache. Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 14400 or 4 hours. +key_cache_save_period: 14400 + +# Number of keys from the key cache to save +# Disabled by default, meaning all keys are going to be saved +# key_cache_keys_to_save: 100 + +# Row cache implementation class name. Available implementations: +# +# org.apache.cassandra.cache.OHCProvider +# Fully off-heap row cache implementation (default). +# +# org.apache.cassandra.cache.SerializingCacheProvider +# This is the row cache implementation availabile +# in previous releases of Cassandra. +# row_cache_class_name: org.apache.cassandra.cache.OHCProvider + +# Maximum size of the row cache in memory. +# Please note that OHC cache implementation requires some additional off-heap memory to manage +# the map structures and some in-flight memory during operations before/after cache entries can be +# accounted against the cache capacity. This overhead is usually small compared to the whole capacity. +# Do not specify more memory that the system can afford in the worst usual situation and leave some +# headroom for OS block level cache. Do never allow your system to swap. +# +# Default value is 0, to disable row caching. +row_cache_size_in_mb: 0 + +# Duration in seconds after which Cassandra should save the row cache. +# Caches are saved to saved_caches_directory as specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 0 to disable saving the row cache. +row_cache_save_period: 0 + +# Number of keys from the row cache to save. +# Specify 0 (which is the default), meaning all keys are going to be saved +# row_cache_keys_to_save: 100 + +# Maximum size of the counter cache in memory. +# +# Counter cache helps to reduce counter locks' contention for hot counter cells. +# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before +# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration +# of the lock hold, helping with hot counter cell updates, but will not allow skipping +# the read entirely. Only the local (clock, count) tuple of a counter cell is kept +# in memory, not the whole counter, so it's relatively cheap. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache. +# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache. +counter_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the counter cache (keys only). Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Default is 7200 or 2 hours. +counter_cache_save_period: 7200 + +# Number of keys from the counter cache to save +# Disabled by default, meaning all keys are going to be saved +# counter_cache_keys_to_save: 100 + +# saved caches +# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches. +# saved_caches_directory: /var/lib/cassandra/saved_caches + +# commitlog_sync may be either "periodic", "group", or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been flushed to disk. Each incoming write will trigger the flush task. +# commitlog_sync_batch_window_in_ms is a deprecated value. Previously it had +# almost no value, and is being removed. +# +# commitlog_sync_batch_window_in_ms: 2 +# +# group mode is similar to batch mode, where Cassandra will not ack writes +# until the commit log has been flushed to disk. The difference is group +# mode will wait up to commitlog_sync_group_window_in_ms between flushes. +# +# commitlog_sync_group_window_in_ms: 1000 +# +# the default option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# When in periodic commitlog mode, the number of milliseconds to block writes +# while waiting for a slow disk flush to complete. +# periodic_commitlog_sync_lag_block_in_ms: + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 1 + +# Compression to apply to the commit log. If omitted, the commit log +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +# commitlog_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Compression to apply to SSTables as they flush for compressed tables. +# Note that tables without compression enabled do not respect this flag. +# +# As high ratio compressors like LZ4HC, Zstd, and Deflate can potentially +# block flushes for too long, the default is to flush with a known fast +# compressor in those cases. Options are: +# +# none : Flush without compressing blocks but while still doing checksums. +# fast : Flush with a fast compressor. If the table is already using a +# fast compressor that compressor is used. +# table: Always flush with the same compressor that the table uses. This +# was the pre 4.0 behavior. +# +# flush_compression: fast + +# any class that implements the SeedProvider interface and has a +# constructor that takes a Map of parameters will do. +seed_provider: + # Addresses of hosts that are deemed contact points. + # Cassandra nodes use this list of hosts to find each other and learn + # the topology of the ring. You must change this if you are running + # multiple nodes! + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + # seeds is actually a comma-delimited list of addresses. + # Ex: ",," + - seeds: "127.0.0.1:7000" + +# For workloads with more data than can fit in memory, Cassandra's +# bottleneck will be reads that need to fetch data from +# disk. "concurrent_reads" should be set to (16 * number_of_drives) in +# order to allow the operations to enqueue low enough in the stack +# that the OS and drives can reorder them. Same applies to +# "concurrent_counter_writes", since counter writes read the current +# values before incrementing and writing them back. +# +# On the other hand, since writes are almost never IO bound, the ideal +# number of "concurrent_writes" is dependent on the number of cores in +# your system; (8 * number_of_cores) is a good rule of thumb. +concurrent_reads: 32 +concurrent_writes: 32 +concurrent_counter_writes: 32 + +# For materialized view writes, as there is a read involved, so this should +# be limited by the less of concurrent reads or concurrent writes. +concurrent_materialized_view_writes: 32 + +# Maximum memory to use for inter-node and client-server networking buffers. +# +# Defaults to the smaller of 1/16 of heap or 128MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# networking_cache_size_in_mb: 128 + +# Enable the sstable chunk cache. The chunk cache will store recently accessed +# sections of the sstable in-memory as uncompressed buffers. +# file_cache_enabled: false + +# Maximum memory to use for sstable chunk cache and buffer pooling. +# 32MB of this are reserved for pooling buffers, the rest is used for chunk cache +# that holds uncompressed sstable chunks. +# Defaults to the smaller of 1/4 of heap or 512MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# file_cache_size_in_mb: 512 + +# Flag indicating whether to allocate on or off heap when the sstable buffer +# pool is exhausted, that is when it has exceeded the maximum memory +# file_cache_size_in_mb, beyond which it will not cache buffers but allocate on request. + +# buffer_pool_use_heap_if_exhausted: true + +# The strategy for optimizing disk read +# Possible values are: +# ssd (for solid state disks, the default) +# spinning (for spinning disks) +# disk_optimization_strategy: ssd + +# Total permitted memory to use for memtables. Cassandra will stop +# accepting writes when the limit is exceeded until a flush completes, +# and will trigger a flush based on memtable_cleanup_threshold +# If omitted, Cassandra will set both to 1/4 the size of the heap. +# memtable_heap_space_in_mb: 2048 +# memtable_offheap_space_in_mb: 2048 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Limit memory usage for Merkle tree calculations during repairs. The default +# is 1/16th of the available heap. The main tradeoff is that smaller trees +# have less resolution, which can lead to over-streaming data. If you see heap +# pressure during repairs, consider lowering this, but you cannot go below +# one megabyte. If you see lots of over-streaming, consider raising +# this or using subrange repair. +# +# For more details see https://issues.apache.org/jira/browse/CASSANDRA-14096. +# +# repair_session_space_in_mb: + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: false +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for legacy encrypted communication. This property is unused unless enabled in +# server_encryption_options (see below). As of cassandra 4.0, this property is deprecated +# as a single port can be used for either/both secure and insecure connections. +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +ssl_storage_port: 7001 + +# Address or interface to bind to and tell other Cassandra nodes to connect to. +# You _must_ change this if you want multiple nodes to be able to communicate! +# +# Set listen_address OR listen_interface, not both. +# +# Leaving it blank leaves it up to InetAddress.getLocalHost(). This +# will always do the Right Thing _if_ the node is properly configured +# (hostname, name resolution, etc), and the Right Thing is to use the +# address associated with the hostname (it might not be). If unresolvable +# it will fall back to InetAddress.getLoopbackAddress(), which is wrong for production systems. +# +# Setting listen_address to 0.0.0.0 is always wrong. +# +listen_address: localhost + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# The address on which the native transport is bound is defined by rpc_address. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests (note that idle threads are stopped +# after 30 seconds so there is not corresponding minimum setting). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Controls whether Cassandra honors older, yet currently supported, protocol versions. +# The default is true, which means all supported protocols will be honored. +native_transport_allow_older_protocols: true + +# Controls when idle client connections are closed. Idle connections are ones that had neither reads +# nor writes for a time period. +# +# Clients may implement heartbeats by sending OPTIONS native protocol message after a timeout, which +# will reset idle timeout timer on the server side. To close idle client connections, corresponding +# values for heartbeat intervals have to be set on the client side. +# +# Idle connection timeouts are disabled by default. +# native_transport_idle_timeout_in_ms: 60000 + +# The address or interface to bind the native transport server to. +# +# Set rpc_address OR rpc_interface, not both. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: localhost + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# RPC address to broadcast to drivers and other Cassandra nodes. This cannot +# be set to 0.0.0.0. If left blank, this will be set to the value of +# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must +# be set. +# broadcast_rpc_address: 1.2.3.4 + +# enable or disable keepalive on rpc/native connections +rpc_keepalive: true + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# See also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# Set to true to have Cassandra create a hard link to each sstable +# flushed or streamed locally in a backups/ subdirectory of the +# keyspace data. Removing these links is the operator's +# responsibility. +incremental_backups: false + +# Whether or not to take a snapshot before each compaction. Be +# careful using this option, since Cassandra won't clean up the +# snapshots for you. Mostly useful if you're paranoid when there +# is a data format change. +snapshot_before_compaction: false + +# Whether or not a snapshot is taken of the data before keyspace truncation +# or dropping of column families. The STRONGLY advised default of true +# should be used to provide data safety. If you set this flag to false, you will +# lose data on truncation or drop. +auto_snapshot: true + +# The act of creating or clearing a snapshot involves creating or removing +# potentially tens of thousands of links, which can cause significant performance +# impact, especially on consumer grade SSDs. A non-zero value here can +# be used to throttle these links to avoid negative performance impact of +# taking and clearing snapshots +snapshot_links_per_second: 0 + +# Granularity of the collation index of rows within a partition. +# Increase if your rows are large, or if you have a very large +# number of rows per partition. The competing goals are these: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# Number of simultaneous repair validations to allow. If not set or set to +# a value less than 1, it defaults to the value of concurrent_compactors. +# To set a value greeater than concurrent_compactors at startup, the system +# property cassandra.allow_unlimited_concurrent_validations must be set to +# true. To dynamically resize to a value > concurrent_compactors on a running +# node, first call the bypassConcurrentValidatorsLimit method on the +# org.apache.cassandra.db:type=StorageService mbean +# concurrent_validations: 0 + +# Number of simultaneous materialized view builder tasks to allow. +concurrent_materialized_view_builders: 1 + +# Throttles compaction to the given total throughput across the entire +# system. The faster you insert data, the faster you need to compact in +# order to keep the sstable count down, but in general, setting this to +# 16 to 32 times the rate you are inserting data is more than sufficient. +# Setting this to 0 disables throttling. Note that this accounts for all types +# of compaction, including validation compaction (building Merkle trees +# for repairs). +compaction_throughput_mb_per_sec: 64 + +# When compacting, the replacement sstable(s) can be opened before they +# are completely written, and used in place of the prior sstables for +# any range that has been written. This helps to smoothly transfer reads +# between the sstables, reducing page cache churn and keeping hot rows hot +sstable_preemptive_open_interval_in_mb: 50 + +# When enabled, permits Cassandra to zero-copy stream entire eligible +# SSTables between nodes, including every component. +# This speeds up the network transfer significantly subject to +# throttling specified by stream_throughput_outbound_megabits_per_sec. +# Enabling this will reduce the GC pressure on sending and receiving node. +# When unset, the default is enabled. While this feature tries to keep the +# disks balanced, it cannot guarantee it. This feature will be automatically +# disabled if internode encryption is enabled. Currently this can be used with +# Leveled Compaction. Once CASSANDRA-14586 is fixed other compaction strategies +# will benefit as well when used in combination with CASSANDRA-6696. +# stream_entire_sstables: true + +# Throttles all outbound streaming file transfers on this node to the +# given total throughput in Mbps. This is necessary because Cassandra does +# mostly sequential IO when streaming data during bootstrap or repair, which +# can lead to saturating the network connection and degrading rpc performance. +# When unset, the default is 200 Mbps or 25 MB/s. +# stream_throughput_outbound_megabits_per_sec: 200 + +# Throttles all streaming file transfer between the datacenters, +# this setting allows users to throttle inter dc stream throughput in addition +# to throttling all network stream traffic as configured with +# stream_throughput_outbound_megabits_per_sec +# When unset, the default is 200 Mbps or 25 MB/s +# inter_dc_stream_throughput_outbound_megabits_per_sec: 200 + +# How long the coordinator should wait for read operations to complete. +# Lowest acceptable value is 10 ms. +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete. +# Lowest acceptable value is 10 ms. +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete. +# Lowest acceptable value is 10 ms. +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete. +# Lowest acceptable value is 10 ms. +counter_write_request_timeout_in_ms: 5000 +# How long a coordinator should continue to retry a CAS operation +# that contends with other proposals for the same row. +# Lowest acceptable value is 10 ms. +cas_contention_timeout_in_ms: 1000 +# How long the coordinator should wait for truncates to complete +# (This can be much longer, because unless auto_snapshot is disabled +# we need to flush first so we can snapshot before removing the data.) +# Lowest acceptable value is 10 ms. +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations. +# Lowest acceptable value is 10 ms. +request_timeout_in_ms: 10000 + +# Defensive settings for protecting Cassandra from true network partitions. +# See (CASSANDRA-14358) for details. +# +# The amount of time to wait for internode tcp connections to establish. +# internode_tcp_connect_timeout_in_ms = 2000 +# +# The amount of time unacknowledged data is allowed on a connection before we throw out the connection +# Note this is only supported on Linux + epoll, and it appears to behave oddly above a setting of 30000 +# (it takes much longer than 30s) as of Linux 4.12. If you want something that high set this to 0 +# which picks up the OS default and configure the net.ipv4.tcp_retries2 sysctl to be ~8. +# internode_tcp_user_timeout_in_ms = 30000 + +# The amount of time unacknowledged data is allowed on a streaming connection. +# The default is 5 minutes. Increase it or set it to 0 in order to increase the timeout. +# internode_streaming_tcp_user_timeout_in_ms = 300000 + +# The maximum continuous period a connection may be unwritable in application space +# internode_application_timeout_in_ms = 30000 + +# Global, per-endpoint and per-connection limits imposed on messages queued for delivery to other nodes +# and waiting to be processed on arrival from other nodes in the cluster. These limits are applied to the on-wire +# size of the message being sent or received. +# +# The basic per-link limit is consumed in isolation before any endpoint or global limit is imposed. +# Each node-pair has three links: urgent, small and large. So any given node may have a maximum of +# N*3*(internode_application_send_queue_capacity_in_bytes+internode_application_receive_queue_capacity_in_bytes) +# messages queued without any coordination between them although in practice, with token-aware routing, only RF*tokens +# nodes should need to communicate with significant bandwidth. +# +# The per-endpoint limit is imposed on all messages exceeding the per-link limit, simultaneously with the global limit, +# on all links to or from a single node in the cluster. +# The global limit is imposed on all messages exceeding the per-link limit, simultaneously with the per-endpoint limit, +# on all links to or from any node in the cluster. +# +# internode_application_send_queue_capacity_in_bytes: 4194304 #4MiB +# internode_application_send_queue_reserve_endpoint_capacity_in_bytes: 134217728 #128MiB +# internode_application_send_queue_reserve_global_capacity_in_bytes: 536870912 #512MiB +# internode_application_receive_queue_capacity_in_bytes: 4194304 #4MiB +# internode_application_receive_queue_reserve_endpoint_capacity_in_bytes: 134217728 #128MiB +# internode_application_receive_queue_reserve_global_capacity_in_bytes: 536870912 #512MiB + + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: It is generally assumed that users have setup NTP on their clusters, and that clocks are modestly in sync, +# since this is a requirement for general correctness of last write wins. +#cross_node_timeout: true + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# Limit number of connections per host for streaming +# Increase this when you notice that joins are CPU-bound rather that network +# bound (for example a few nodes with big files). +# streaming_connections_per_host: 1 + + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 1.0 + +# Configure server-to-server internode encryption +# +# JVM and netty defaults for supported SSL socket protocols and cipher suites can +# be replaced using custom encryption options. This is not recommended +# unless you have policies in place that dictate certain settings, or +# need to disable vulnerable ciphers or protocols in case the JVM cannot +# be updated. +# +# FIPS compliant settings can be configured at JVM level and should not +# involve changing encryption settings here: +# https://docs.oracle.com/javase/8/docs/technotes/guides/security/jsse/FIPS.html +# +# **NOTE** this default configuration is an insecure configuration. If you need to +# enable server-to-server encryption generate server keystores (and truststores for mutual +# authentication) per: +# http://download.oracle.com/javase/8/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# Then perform the following configuration changes: +# +# Step 1: Set internode_encryption= and explicitly set optional=true. Restart all nodes +# +# Step 2: Set optional=false (or remove it) and if you generated truststores and want to use mutual +# auth set require_client_auth=true. Restart all nodes +server_encryption_options: + # On outbound connections, determine which type of peers to securely connect to. + # The available options are : + # none : Do not encrypt outgoing connections + # dc : Encrypt connections to peers in other datacenters but not within datacenters + # rack : Encrypt connections to peers in other racks but not within racks + # all : Always use encrypted connections + internode_encryption: none + # When set to true, encrypted and unencrypted connections are allowed on the storage_port + # This should _only be true_ while in unencrypted or transitional operation + # optional defaults to true if internode_encryption is none + # optional: true + # If enabled, will open up an encrypted listening socket on ssl_storage_port. Should only be used + # during upgrade to 4.0; otherwise, set to false. + enable_legacy_ssl_storage_port: false + # Set to a valid keystore if internode_encryption is dc, rack or all + keystore: conf/.keystore + keystore_password: cassandra + # Verify peer server certificates + require_client_auth: false + # Set to a valid trustore if require_client_auth is true + truststore: conf/.truststore + truststore_password: cassandra + # Verify that the host name in the certificate matches the connected host + require_endpoint_verification: false + # More advanced defaults: + # protocol: TLS + # store_type: JKS + # cipher_suites: [ + # TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, + # TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA, + # TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA, TLS_RSA_WITH_AES_128_GCM_SHA256, TLS_RSA_WITH_AES_128_CBC_SHA, + # TLS_RSA_WITH_AES_256_CBC_SHA + # ] + +# Configure client-to-server encryption. +# +# **NOTE** this default configuration is an insecure configuration. If you need to +# enable client-to-server encryption generate server keystores (and truststores for mutual +# authentication) per: +# http://download.oracle.com/javase/8/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# Then perform the following configuration changes: +# +# Step 1: Set enabled=true and explicitly set optional=true. Restart all nodes +# +# Step 2: Set optional=false (or remove it) and if you generated truststores and want to use mutual +# auth set require_client_auth=true. Restart all nodes +client_encryption_options: + # Enable client-to-server encryption + enabled: false + # When set to true, encrypted and unencrypted connections are allowed on the native_transport_port + # This should _only be true_ while in unencrypted or transitional operation + # optional defaults to true when enabled is false, and false when enabled is true. + # optional: true + # Set keystore and keystore_password to valid keystores if enabled is true + keystore: conf/.keystore + keystore_password: cassandra + # Verify client certificates + require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults: + # protocol: TLS + # store_type: JKS + # cipher_suites: [ + # TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, + # TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA, + # TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA, TLS_RSA_WITH_AES_128_GCM_SHA256, TLS_RSA_WITH_AES_128_CBC_SHA, + # TLS_RSA_WITH_AES_256_CBC_SHA + # ] + +# internode_compression controls whether traffic between nodes is +# compressed. +# Can be: +# +# all +# all traffic is compressed +# +# dc +# traffic between different datacenters is compressed +# +# none +# nothing is compressed. +internode_compression: dc + +# Enable or disable tcp_nodelay for inter-dc communication. +# Disabling it will result in larger (but fewer) network packets being sent, +# reducing overhead from the TCP protocol itself, at the cost of increasing +# latency if you block for cross-datacenter responses. +inter_dc_tcp_nodelay: false + +# TTL for different trace types used during logging of the repair process. +tracetype_query_ttl: 86400 +tracetype_repair_ttl: 604800 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: false + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation. +# Lowering this value on Windows can provide much tighter latency and better throughput, however +# some virtualized environments may see a negative performance impact from changing this setting +# below their system default. The sysinternals 'clockres' tool can confirm your system's default +# setting. +windows_timer_interval: 1 + + +# Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from +# a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by +# the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys +# can still (and should!) be in the keystore and will be used on decrypt operations +# (to handle the case of key rotation). +# +# It is strongly recommended to download and install Java Cryptography Extension (JCE) +# Unlimited Strength Jurisdiction Policy Files for your version of the JDK. +# (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html) +# +# Currently, only the following file types are supported for transparent data encryption, although +# more are coming in future cassandra releases: commitlog, hints +transparent_data_encryption_options: + enabled: false + chunk_length_kb: 64 + cipher: AES/CBC/PKCS5Padding + key_alias: testing:1 + # CBC IV length for AES needs to be 16 bytes (which is also the default size) + # iv_length: 16 + key_provider: + - class_name: org.apache.cassandra.security.JKSKeyProvider + parameters: + - keystore: conf/.keystore + keystore_password: cassandra + store_type: JCEKS + key_password: cassandra + + +##################### +# SAFETY THRESHOLDS # +##################### + +# When executing a scan, within or across a partition, we need to keep the +# tombstones seen in memory so we can return them to the coordinator, which +# will use them to make sure other replicas also know about the deleted rows. +# With workloads that generate a lot of tombstones, this can cause performance +# problems and even exaust the server heap. +# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) +# Adjust the thresholds here if you understand the dangers and want to +# scan more tombstones anyway. These thresholds may also be adjusted at runtime +# using the StorageService mbean. +tombstone_warn_threshold: 1000 +tombstone_failure_threshold: 100000 + +# Filtering and secondary index queries at read consistency levels above ONE/LOCAL_ONE use a +# mechanism called replica filtering protection to ensure that results from stale replicas do +# not violate consistency. (See CASSANDRA-8272 and CASSANDRA-15907 for more details.) This +# mechanism materializes replica results by partition on-heap at the coordinator. The more possibly +# stale results returned by the replicas, the more rows materialized during the query. +replica_filtering_protection: + # These thresholds exist to limit the damage severely out-of-date replicas can cause during these + # queries. They limit the number of rows from all replicas individual index and filtering queries + # can materialize on-heap to return correct results at the desired read consistency level. + # + # "cached_replica_rows_warn_threshold" is the per-query threshold at which a warning will be logged. + # "cached_replica_rows_fail_threshold" is the per-query threshold at which the query will fail. + # + # These thresholds may also be adjusted at runtime using the StorageService mbean. + # + # If the failure threshold is breached, it is likely that either the current page/fetch size + # is too large or one or more replicas is severely out-of-sync and in need of repair. + cached_rows_warn_threshold: 2000 + cached_rows_fail_threshold: 32000 + +# Log WARN on any multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than 200 ms will be logged at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level +# Adjust the threshold based on your application throughput requirement. Setting to 0 +# will deactivate the feature. +# gc_warn_threshold_in_ms: 1000 + +# Maximum size of any value in SSTables. Safety measure to detect SSTable corruption +# early. Any value size larger than this threshold will result into marking an SSTable +# as corrupted. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 + +# Track a metric per keyspace indicating whether replication achieved the ideal consistency +# level for writes without timing out. This is different from the consistency level requested by +# each write which may be lower in order to facilitate availability. +# ideal_consistency_level: EACH_QUORUM + +# Automatically upgrade sstables after upgrade - if there is no ordinary compaction to do, the +# oldest non-upgraded sstable will get upgraded to the latest version +# automatic_sstable_upgrade: false +# Limit the number of concurrent sstable upgrades +# max_concurrent_automatic_sstable_upgrades: 1 + +# Audit logging - Logs every incoming CQL command request, authentication to a node. See the docs +# on audit_logging for full details about the various configuration options. +audit_logging_options: + enabled: false + logger: + - class_name: BinAuditLogger + # audit_logs_dir: + # included_keyspaces: + # excluded_keyspaces: system, system_schema, system_virtual_schema + # included_categories: + # excluded_categories: + # included_users: + # excluded_users: + # roll_cycle: HOURLY + # block: true + # max_queue_weight: 268435456 # 256 MiB + # max_log_size: 17179869184 # 16 GiB + ## archive command is "/path/to/script.sh %path" where %path is replaced with the file being rolled: + # archive_command: + # max_archive_retries: 10 + + +# default options for full query logging - these can be overridden from command line when executing +# nodetool enablefullquerylog +#full_query_logging_options: + # log_dir: + # roll_cycle: HOURLY + # block: true + # max_queue_weight: 268435456 # 256 MiB + # max_log_size: 17179869184 # 16 GiB + ## archive command is "/path/to/script.sh %path" where %path is replaced with the file being rolled: + # archive_command: + # max_archive_retries: 10 + +# validate tombstones on reads and compaction +# can be either "disabled", "warn" or "exception" +# corrupted_tombstone_strategy: disabled + +# Diagnostic Events # +# If enabled, diagnostic events can be helpful for troubleshooting operational issues. Emitted events contain details +# on internal state and temporal relationships across events, accessible by clients via JMX. +diagnostic_events_enabled: false + +# Use native transport TCP message coalescing. If on upgrade to 4.0 you found your throughput decreasing, and in +# particular you run an old kernel or have very fewer client connections, this option might be worth evaluating. +#native_transport_flush_in_batches_legacy: false + +# Enable tracking of repaired state of data during reads and comparison between replicas +# Mismatches between the repaired sets of replicas can be characterized as either confirmed +# or unconfirmed. In this context, unconfirmed indicates that the presence of pending repair +# sessions, unrepaired partition tombstones, or some other condition means that the disparity +# cannot be considered conclusive. Confirmed mismatches should be a trigger for investigation +# as they may be indicative of corruption or data loss. +# There are separate flags for range vs partition reads as single partition reads are only tracked +# when CL > 1 and a digest mismatch occurs. Currently, range queries don't use digests so if +# enabled for range reads, all range reads will include repaired data tracking. As this adds +# some overhead, operators may wish to disable it whilst still enabling it for partition reads +repaired_data_tracking_for_range_reads_enabled: false +repaired_data_tracking_for_partition_reads_enabled: false +# If false, only confirmed mismatches will be reported. If true, a separate metric for unconfirmed +# mismatches will also be recorded. This is to avoid potential signal:noise issues are unconfirmed +# mismatches are less actionable than confirmed ones. +report_unconfirmed_repaired_data_mismatches: false + +# Having many tables and/or keyspaces negatively affects performance of many operations in the +# cluster. When the number of tables/keyspaces in the cluster exceeds the following thresholds +# a client warning will be sent back to the user when creating a table or keyspace. +# table_count_warn_threshold: 150 +# keyspace_count_warn_threshold: 40 + +######################### +# EXPERIMENTAL FEATURES # +######################### + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: false + +# Enables SASI index creation on this node. +# SASI indexes are considered experimental and are not recommended for production use. +enable_sasi_indexes: false + +# Enables creation of transiently replicated keyspaces on this node. +# Transient replication is experimental and is not recommended for production use. +enable_transient_replication: false diff --git a/backfill-cli/src/test/resources/c5/logback.xml b/backfill-cli/src/test/resources/c5/logback.xml new file mode 100644 index 00000000..d4261fbe --- /dev/null +++ b/backfill-cli/src/test/resources/c5/logback.xml @@ -0,0 +1,103 @@ + + + + + + + + + + + + + + TRACE + + ${cassandra.logdir}/system.log + + + ${cassandra.logdir}/system.log.%d{yyyy-MM-dd}.%i.zip + + 50MB + 7 + 5GB + + + %-5level [%thread] %date{ISO8601} %F:%L - %msg%n + + + + + + + ${cassandra.logdir}/debug.log + + + ${cassandra.logdir}/debug.log.%d{yyyy-MM-dd}.%i.zip + + 50MB + 7 + 5GB + + + %-5level [%thread] %date{ISO8601} %F:%L %m %msg%n + + + + + + + 1024 + 0 + true + + + + + + + + TRACE + + + %-5level [%thread] %date{ISO8601} %F:%L - %msg%n + + + + + + + + + + + + + + + + From dfb2ed1c712e8ffdd0b53b55c4087143b478e21b Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 02:52:15 +0530 Subject: [PATCH 09/10] handle cassandra timeuuid class --- .../java/com/datastax/oss/cdc/agent/PulsarMutationSender.java | 3 +++ 1 file changed, 3 insertions(+) diff --git a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java index 6195ab7c..b4e73aeb 100644 --- a/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java +++ b/agent-c5/src/main/java/com/datastax/oss/cdc/agent/PulsarMutationSender.java @@ -156,6 +156,9 @@ public Object cqlToAvro(TableMetadata tableMetadata, String columnName, Object v if (type instanceof ShortType) { return Short.toUnsignedInt((short) value); // AVRO does not support INT16 } + if ((type instanceof TimeUUIDType || type instanceof UUIDType) && value instanceof org.apache.cassandra.utils.TimeUUID) { + return ((org.apache.cassandra.utils.TimeUUID) value).asUUID(); // Handle Cassandra 5 TimeUUID type - convert to UUID string for Avro serialization + } return value; } } From 59970afeb6ac31bddfd20930c58126a81004eb04 Mon Sep 17 00:00:00 2001 From: SreedevT Date: Tue, 30 Sep 2025 15:30:27 +0530 Subject: [PATCH 10/10] revert removal of other modules from ci --- .github/workflows/backfill-ci.yaml | 4 ++-- .github/workflows/ci.yaml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/workflows/backfill-ci.yaml b/.github/workflows/backfill-ci.yaml index 450625fd..7cf16b65 100644 --- a/.github/workflows/backfill-ci.yaml +++ b/.github/workflows/backfill-ci.yaml @@ -38,8 +38,8 @@ jobs: fail-fast: false matrix: jdk: ['11'] # TODO: Enable java 17 tests https://issues.apache.org/jira/browse/CASSANDRA-16895 - pulsarImage: ['datastax/lunastreaming:4.0_3.6'] - cassandraFamily: ['c5'] + pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] + cassandraFamily: ['c3', 'c4', 'c5', 'dse4'] steps: - uses: actions/checkout@v3 - name: Set up JDK ${{ matrix.jdk }} diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index 7c2493db..8889ad97 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -37,9 +37,9 @@ jobs: strategy: fail-fast: false matrix: - module: ['agent-c5', 'connector'] + module: ['agent', 'agent-c3', 'agent-c4', 'agent-c5', 'agent-dse4', 'connector'] jdk: ['11', '17'] - pulsarImage: ['datastax/lunastreaming:4.0_3.6'] + pulsarImage: ['datastax/lunastreaming:2.10_3.4', 'apachepulsar/pulsar:2.10.3', 'apachepulsar/pulsar:2.11.0'] steps: - uses: actions/checkout@v3 - name: Set up JDK ${{ matrix.jdk }}