[LOG4J2-1730]: Add CassandraAppender and tests
Project: http://git-wip-us.apache.org/repos/asf/logging-log4j2/repo Commit: http://git-wip-us.apache.org/repos/asf/logging-log4j2/commit/33e7ab30 Tree: http://git-wip-us.apache.org/repos/asf/logging-log4j2/tree/33e7ab30 Diff: http://git-wip-us.apache.org/repos/asf/logging-log4j2/diff/33e7ab30 Branch: refs/heads/master Commit: 33e7ab30b95c34e4229157a99e3771dffb99be06 Parents: 9f7fae1 Author: Matt Sicker <[email protected]> Authored: Sat Dec 31 18:48:20 2016 -0600 Committer: Matt Sicker <[email protected]> Committed: Sat Dec 31 18:48:20 2016 -0600 ---------------------------------------------------------------------- .../appender/cassandra/CassandraAppender.java | 182 ++++ .../appender/cassandra/CassandraManager.java | 210 +++++ .../cassandra/ClockTimestampGenerator.java | 34 + .../nosql/appender/cassandra/TypeCodecs.java | 75 ++ .../nosql/appender/cassandra/package-info.java | 22 + .../appender/cassandra/CassandraAppenderIT.java | 87 ++ .../nosql/appender/cassandra/CassandraRule.java | 113 +++ .../test/resources/CassandraAppenderTest.xml | 39 + log4j-nosql/src/test/resources/cassandra.yaml | 901 +++++++++++++++++++ 9 files changed, 1663 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppender.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppender.java b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppender.java new file mode 100644 index 0000000..24e81cd --- /dev/null +++ b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppender.java @@ -0,0 +1,182 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import com.datastax.driver.core.BatchStatement; +import org.apache.logging.log4j.core.Core; +import org.apache.logging.log4j.core.Filter; +import org.apache.logging.log4j.core.appender.AbstractAppender; +import org.apache.logging.log4j.core.appender.db.AbstractDatabaseAppender; +import org.apache.logging.log4j.core.appender.db.ColumnMapping; +import org.apache.logging.log4j.core.config.plugins.Plugin; +import org.apache.logging.log4j.core.config.plugins.PluginBuilderAttribute; +import org.apache.logging.log4j.core.config.plugins.PluginBuilderFactory; +import org.apache.logging.log4j.core.config.plugins.PluginElement; +import org.apache.logging.log4j.core.config.plugins.validation.constraints.Required; +import org.apache.logging.log4j.core.net.SocketAddress; +import org.apache.logging.log4j.core.util.Clock; + +/** + * Appender plugin that uses a Cassandra database. + */ +@Plugin(name = "Cassandra", category = Core.CATEGORY_NAME, elementType = CassandraAppender.ELEMENT_TYPE, printObject = true) +public class CassandraAppender extends AbstractDatabaseAppender<CassandraManager> { + + private CassandraAppender(final String name, final Filter filter, final boolean ignoreExceptions, + final CassandraManager manager) { + super(name, filter, ignoreExceptions, manager); + } + + @PluginBuilderFactory + public static <B extends Builder<B>> B newBuilder() { + return new Builder<B>().asBuilder(); + } + + public static class Builder<B extends Builder<B>> extends AbstractAppender.Builder<B> + implements org.apache.logging.log4j.core.util.Builder<CassandraAppender> { + + /** + * List of Cassandra node contact points. Addresses without a port (or port set to 0) will use the default + * Cassandra port (9042). + */ + @PluginElement("ContactPoints") + @Required(message = "No Cassandra servers provided") + private SocketAddress[] contactPoints = new SocketAddress[]{SocketAddress.getLoopback()}; + + /** + * List of column mappings to convert a LogEvent into a database row. + */ + @PluginElement("Columns") + @Required(message = "No Cassandra columns provided") + private ColumnMapping[] columns; + + @PluginBuilderAttribute + private boolean useTls; + + @PluginBuilderAttribute + @Required(message = "No cluster name provided") + private String clusterName; + + @PluginBuilderAttribute + @Required(message = "No keyspace provided") + private String keyspace; + + @PluginBuilderAttribute + @Required(message = "No table name provided") + private String table; + + @PluginBuilderAttribute + private String username; + + @PluginBuilderAttribute(sensitive = true) + private String password; + + /** + * Override the default TimestampGenerator with one based on the configured {@link Clock}. + */ + @PluginBuilderAttribute + private boolean useClockForTimestampGenerator; + + /** + * Number of LogEvents to buffer before writing. Can be used with or without batch statements. + */ + @PluginBuilderAttribute + private int bufferSize; + + /** + * Whether or not to use batch statements when inserting records. + */ + @PluginBuilderAttribute + private boolean batched; + + /** + * If batch statements are enabled, use this type of batch statement. + */ + @PluginBuilderAttribute + private BatchStatement.Type batchType = BatchStatement.Type.LOGGED; + + public B setContactPoints(final SocketAddress... contactPoints) { + this.contactPoints = contactPoints; + return asBuilder(); + } + + public B setColumns(final ColumnMapping... columns) { + this.columns = columns; + return asBuilder(); + } + + public B setUseTls(final boolean useTls) { + this.useTls = useTls; + return asBuilder(); + } + + public B setClusterName(final String clusterName) { + this.clusterName = clusterName; + return asBuilder(); + } + + public B setKeyspace(final String keyspace) { + this.keyspace = keyspace; + return asBuilder(); + } + + public B setTable(final String table) { + this.table = table; + return asBuilder(); + } + + public B setUsername(final String username) { + this.username = username; + return asBuilder(); + } + + public B setPassword(final String password) { + this.password = password; + return asBuilder(); + } + + public B setUseClockForTimestampGenerator(final boolean useClockForTimestampGenerator) { + this.useClockForTimestampGenerator = useClockForTimestampGenerator; + return asBuilder(); + } + + public B setBufferSize(final int bufferSize) { + this.bufferSize = bufferSize; + return asBuilder(); + } + + public B setBatched(final boolean batched) { + this.batched = batched; + return asBuilder(); + } + + public B setBatchType(final BatchStatement.Type batchType) { + this.batchType = batchType; + return asBuilder(); + } + + @Override + public CassandraAppender build() { + final CassandraManager manager = CassandraManager.getManager(getName(), contactPoints, columns, useTls, + clusterName, keyspace, table, username, password, useClockForTimestampGenerator, bufferSize, batched, + batchType); + return new CassandraAppender(getName(), getFilter(), isIgnoreExceptions(), manager); + } + + } + +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraManager.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraManager.java b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraManager.java new file mode 100644 index 0000000..75a90dd --- /dev/null +++ b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraManager.java @@ -0,0 +1,210 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import java.net.InetSocketAddress; +import java.util.Arrays; +import java.util.List; + +import com.datastax.driver.core.BatchStatement; +import com.datastax.driver.core.BoundStatement; +import com.datastax.driver.core.Cluster; +import com.datastax.driver.core.PreparedStatement; +import com.datastax.driver.core.Session; +import org.apache.logging.log4j.core.LogEvent; +import org.apache.logging.log4j.core.appender.ManagerFactory; +import org.apache.logging.log4j.core.appender.db.AbstractDatabaseManager; +import org.apache.logging.log4j.core.appender.db.ColumnMapping; +import org.apache.logging.log4j.core.config.plugins.convert.TypeConverters; +import org.apache.logging.log4j.core.net.SocketAddress; +import org.apache.logging.log4j.spi.ThreadContextMap; +import org.apache.logging.log4j.spi.ThreadContextStack; +import org.apache.logging.log4j.util.Strings; + +/** + * Manager for a Cassandra appender instance. + */ +public class CassandraManager extends AbstractDatabaseManager { + + static { + // pre-register custom type codecs + TypeCodecs.registerCustomCodecs(); + } + + private static final int DEFAULT_PORT = 9042; + + private final Cluster cluster; + private final String keyspace; + private final String insertQueryTemplate; + private final List<ColumnMapping> columnMappings; + private final BatchStatement batchStatement; + // re-usable argument binding array + private final Object[] values; + + private Session session; + private PreparedStatement preparedStatement; + + private CassandraManager(final String name, final int bufferSize, final Cluster cluster, + final String keyspace, final String insertQueryTemplate, + final List<ColumnMapping> columnMappings, final BatchStatement batchStatement) { + super(name, bufferSize); + this.cluster = cluster; + this.keyspace = keyspace; + this.insertQueryTemplate = insertQueryTemplate; + this.columnMappings = columnMappings; + this.batchStatement = batchStatement; + this.values = new Object[columnMappings.size()]; + } + + @Override + protected void startupInternal() throws Exception { + session = cluster.connect(keyspace); + preparedStatement = session.prepare(insertQueryTemplate); + } + + @Override + protected boolean shutdownInternal() throws Exception { + session.close(); + cluster.close(); + return true; + } + + @Override + protected void connectAndStart() { + // a Session automatically manages connections for us + } + + @Override + protected void writeInternal(final LogEvent event) { + for (int i = 0; i < columnMappings.size(); i++) { + final ColumnMapping columnMapping = columnMappings.get(i); + if (ThreadContextMap.class.isAssignableFrom(columnMapping.getType())) { + values[i] = event.getContextData().toMap(); + } else if (ThreadContextStack.class.isAssignableFrom(columnMapping.getType())) { + values[i] = event.getContextStack().asList(); + } else { + values[i] = TypeConverters.convert(columnMapping.getLayout().toSerializable(event), + columnMapping.getType(), null); + } + } + final BoundStatement boundStatement = preparedStatement.bind(values); + if (batchStatement == null) { + session.execute(boundStatement); + } else { + batchStatement.add(boundStatement); + } + } + + @Override + protected boolean commitAndClose() { + if (batchStatement != null) { + session.execute(batchStatement); + } + return true; + } + + public static CassandraManager getManager(final String name, final SocketAddress[] contactPoints, + final ColumnMapping[] columns, final boolean useTls, + final String clusterName, final String keyspace, final String table, + final String username, final String password, + final boolean useClockForTimestampGenerator, final int bufferSize, + final boolean batched, final BatchStatement.Type batchType) { + return getManager(name, + new FactoryData(contactPoints, columns, useTls, clusterName, keyspace, table, username, password, + useClockForTimestampGenerator, bufferSize, batched, batchType), CassandraManagerFactory.INSTANCE); + } + + private static class CassandraManagerFactory implements ManagerFactory<CassandraManager, FactoryData> { + + private static final CassandraManagerFactory INSTANCE = new CassandraManagerFactory(); + + @Override + public CassandraManager createManager(final String name, final FactoryData data) { + final Cluster.Builder builder = Cluster.builder() + .addContactPointsWithPorts(data.contactPoints) + .withClusterName(data.clusterName); + if (data.useTls) { + builder.withSSL(); + } + if (Strings.isNotBlank(data.username)) { + builder.withCredentials(data.username, data.password); + } + if (data.useClockForTimestampGenerator) { + builder.withTimestampGenerator(new ClockTimestampGenerator()); + } + final Cluster cluster = builder.build(); + + final StringBuilder sb = new StringBuilder("INSERT INTO ").append(data.table).append(" ("); + for (final ColumnMapping column : data.columns) { + sb.append(column.getName()).append(','); + } + sb.setCharAt(sb.length() - 1, ')'); + sb.append(" VALUES ("); + for (int i = 0; i < data.columns.length; i++) { + sb.append("?,"); + } + sb.setCharAt(sb.length() - 1, ')'); + final String insertQueryTemplate = sb.toString(); + LOGGER.debug("Using CQL for appender {}: {}", name, insertQueryTemplate); + return new CassandraManager(name, data.getBufferSize(), cluster, data.keyspace, insertQueryTemplate, + Arrays.asList(data.columns), data.batched ? new BatchStatement(data.batchType) : null); + } + } + + private static class FactoryData extends AbstractFactoryData { + private final InetSocketAddress[] contactPoints; + private final ColumnMapping[] columns; + private final boolean useTls; + private final String clusterName; + private final String keyspace; + private final String table; + private final String username; + private final String password; + private final boolean useClockForTimestampGenerator; + private final boolean batched; + private final BatchStatement.Type batchType; + + private FactoryData(final SocketAddress[] contactPoints, final ColumnMapping[] columns, final boolean useTls, + final String clusterName, final String keyspace, final String table, final String username, + final String password, final boolean useClockForTimestampGenerator, final int bufferSize, + final boolean batched, final BatchStatement.Type batchType) { + super(bufferSize); + this.contactPoints = convertAndAddDefaultPorts(contactPoints); + this.columns = columns; + this.useTls = useTls; + this.clusterName = clusterName; + this.keyspace = keyspace; + this.table = table; + this.username = username; + this.password = password; + this.useClockForTimestampGenerator = useClockForTimestampGenerator; + this.batched = batched; + this.batchType = batchType; + } + + private static InetSocketAddress[] convertAndAddDefaultPorts(final SocketAddress... socketAddresses) { + final InetSocketAddress[] inetSocketAddresses = new InetSocketAddress[socketAddresses.length]; + for (int i = 0; i < inetSocketAddresses.length; i++) { + final SocketAddress socketAddress = socketAddresses[i]; + inetSocketAddresses[i] = socketAddress.getPort() == 0 + ? new InetSocketAddress(socketAddress.getAddress(), DEFAULT_PORT) + : socketAddress.getSocketAddress(); + } + return inetSocketAddresses; + } + } +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/ClockTimestampGenerator.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/ClockTimestampGenerator.java b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/ClockTimestampGenerator.java new file mode 100644 index 0000000..06758dd --- /dev/null +++ b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/ClockTimestampGenerator.java @@ -0,0 +1,34 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import com.datastax.driver.core.TimestampGenerator; +import org.apache.logging.log4j.core.util.Clock; +import org.apache.logging.log4j.core.util.ClockFactory; + +/** + * A {@link TimestampGenerator} implementation using the configured {@link Clock}. + */ +public class ClockTimestampGenerator implements TimestampGenerator { + + private final Clock clock = ClockFactory.getClock(); + + @Override + public long next() { + return clock.currentTimeMillis(); + } +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/TypeCodecs.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/TypeCodecs.java b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/TypeCodecs.java new file mode 100644 index 0000000..ef83852 --- /dev/null +++ b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/TypeCodecs.java @@ -0,0 +1,75 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import java.nio.ByteBuffer; + +import com.datastax.driver.core.CodecRegistry; +import com.datastax.driver.core.DataType; +import com.datastax.driver.core.ProtocolVersion; +import com.datastax.driver.core.TypeCodec; +import com.datastax.driver.core.exceptions.InvalidTypeException; +import org.apache.logging.log4j.util.Strings; + +/** + * Custom TypeCodecs for use with the Datastax Cassandra driver. + */ +public final class TypeCodecs { + + public static void registerCustomCodecs() { + CodecRegistry.DEFAULT_INSTANCE.register(new LongTimestampCodec()); + } + + /** + * TypeCodec that allows a long value to be used as a timestamp. + */ + public static class LongTimestampCodec extends TypeCodec.PrimitiveLongCodec { + + private LongTimestampCodec() { + super(DataType.timestamp()); + } + + @Override + public ByteBuffer serializeNoBoxing(final long v, final ProtocolVersion protocolVersion) { + final ByteBuffer bb = ByteBuffer.allocate(8); + bb.putLong(v); + return bb; + } + + @Override + public long deserializeNoBoxing(final ByteBuffer v, final ProtocolVersion protocolVersion) { + if (v == null || v.remaining() == 0) { + return 0; + } + if (v.remaining() != 8) { + throw new InvalidTypeException("Expected an 8 byte value, but got " + v.remaining() + " bytes"); + } + return v.getLong(v.position()); + } + + @Override + public Long parse(final String value) throws InvalidTypeException { + return Strings.isEmpty(value) || "NULL".equalsIgnoreCase(value) ? null : Long.parseLong(value); + } + + @Override + public String format(final Long value) throws InvalidTypeException { + return value == null ? "NULL" : value.toString(); + } + } + +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/package-info.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/package-info.java b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/package-info.java new file mode 100644 index 0000000..d960f78 --- /dev/null +++ b/log4j-nosql/src/main/java/org/apache/logging/log4j/nosql/appender/cassandra/package-info.java @@ -0,0 +1,22 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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. + */ +/** + * Log4j appender plugin and supporting classes for Apache Cassandra. + * + * @since 2.8 + */ +package org.apache.logging.log4j.nosql.appender.cassandra; \ No newline at end of file http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppenderIT.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppenderIT.java b/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppenderIT.java new file mode 100644 index 0000000..9c7b98c --- /dev/null +++ b/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraAppenderIT.java @@ -0,0 +1,87 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import java.util.List; +import java.util.Map; +import java.util.concurrent.TimeUnit; + +import com.datastax.driver.core.Row; +import com.datastax.driver.core.Session; +import org.apache.logging.log4j.Logger; +import org.apache.logging.log4j.MarkerManager; +import org.apache.logging.log4j.ThreadContext; +import org.apache.logging.log4j.junit.LoggerContextRule; +import org.junit.ClassRule; +import org.junit.Test; +import org.junit.rules.RuleChain; + +import static org.junit.Assert.assertEquals; + +/** + * Integration test for CassandraAppender. + */ +public class CassandraAppenderIT { + + private static final String DDL = "CREATE TABLE logs (" + + "id timeuuid PRIMARY KEY," + + "message text," + + "level text," + + "marker text," + + "logger text," + + "timestamp timestamp," + + "mdc map<text,text>," + + "ndc list<text>" + + ")"; + + private static final LoggerContextRule CTX = new LoggerContextRule("CassandraAppenderTest.xml"); + private static final CassandraRule CASSANDRA = new CassandraRule("test", DDL); + + @ClassRule + public static RuleChain rules = RuleChain.outerRule(CASSANDRA).around(CTX); + + @Test + public void appendManyEvents() throws Exception { + final Logger logger = CTX.getLogger(); + ThreadContext.put("test", "mdc"); + ThreadContext.push("ndc"); + for (int i = 0; i < 20; i++) { + logger.info(MarkerManager.getMarker("MARKER"), "Test log message"); + } + ThreadContext.clearAll(); + + TimeUnit.SECONDS.sleep(3); + + int i = 0; + try (final Session session = CASSANDRA.connect()) { + for (final Row row : session.execute("SELECT * FROM logs")) { + assertEquals("Test log message", row.getString("message")); + assertEquals("MARKER", row.getString("marker")); + assertEquals("INFO", row.getString("level")); + assertEquals(getClass().getName(), row.getString("logger")); + final Map<String, String> mdc = row.getMap("mdc", String.class, String.class); + assertEquals(1, mdc.size()); + assertEquals("mdc", mdc.get("test")); + final List<String> ndc = row.getList("ndc", String.class); + assertEquals(1, ndc.size()); + assertEquals("ndc", ndc.get(0)); + ++i; + } + } + assertEquals(20, i); + } +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraRule.java ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraRule.java b/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraRule.java new file mode 100644 index 0000000..bec97ea --- /dev/null +++ b/log4j-nosql/src/test/java/org/apache/logging/log4j/nosql/appender/cassandra/CassandraRule.java @@ -0,0 +1,113 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.logging.log4j.nosql.appender.cassandra; + +import java.io.IOException; +import java.net.InetAddress; +import java.nio.file.Files; +import java.nio.file.Path; +import java.util.concurrent.CountDownLatch; +import java.util.concurrent.ThreadFactory; + +import com.datastax.driver.core.Cluster; +import com.datastax.driver.core.Session; +import org.apache.cassandra.service.CassandraDaemon; +import org.apache.logging.log4j.LoggingException; +import org.apache.logging.log4j.core.util.Cancellable; +import org.apache.logging.log4j.core.util.Closer; +import org.apache.logging.log4j.core.util.Log4jThreadFactory; +import org.junit.rules.ExternalResource; + +/** + * JUnit rule to set up and tear down a Cassandra database instance. + */ +public class CassandraRule extends ExternalResource { + + private static final ThreadFactory THREAD_FACTORY = Log4jThreadFactory.createThreadFactory("Cassandra"); + + private final CountDownLatch latch = new CountDownLatch(1); + private final Cancellable embeddedCassandra = new EmbeddedCassandra(latch); + private final String keyspace; + private final String tableDdl; + private Cluster cluster; + + public CassandraRule(final String keyspace, final String tableDdl) { + this.keyspace = keyspace; + this.tableDdl = tableDdl; + } + + public Cluster getCluster() { + return cluster; + } + + public Session connect() { + return cluster.connect(keyspace); + } + + @Override + protected void before() throws Throwable { + final Path root = Files.createTempDirectory("cassandra"); + Files.createDirectories(root.resolve("data")); + final Path config = root.resolve("cassandra.yml"); + Files.copy(getClass().getResourceAsStream("/cassandra.yaml"), config); + System.setProperty("cassandra.config", "file:" + config.toString()); + System.setProperty("cassandra.storagedir", root.toString()); + System.setProperty("cassandra-foreground", "true"); // prevents Cassandra from closing stdout/stderr + THREAD_FACTORY.newThread(embeddedCassandra).start(); + latch.await(); + cluster = Cluster.builder().addContactPoints(InetAddress.getLoopbackAddress()).build(); + try (final Session session = cluster.connect()) { + session.execute("CREATE KEYSPACE " + keyspace + " WITH REPLICATION = " + + "{ 'class': 'SimpleStrategy', 'replication_factor': 2 };"); + } + try (final Session session = connect()) { + session.execute(tableDdl); + } + } + + @Override + protected void after() { + Closer.closeSilently(cluster); + embeddedCassandra.cancel(); + } + + private static class EmbeddedCassandra implements Cancellable { + + private final CassandraDaemon daemon = new CassandraDaemon(); + private final CountDownLatch latch; + + private EmbeddedCassandra(final CountDownLatch latch) { + this.latch = latch; + } + + @Override + public void cancel() { + daemon.stop(); + } + + @Override + public void run() { + try { + daemon.init(null); + } catch (final IOException e) { + throw new LoggingException("Cannot initialize embedded Cassandra instance", e); + } + daemon.start(); + latch.countDown(); + } + } +} http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/test/resources/CassandraAppenderTest.xml ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/test/resources/CassandraAppenderTest.xml b/log4j-nosql/src/test/resources/CassandraAppenderTest.xml new file mode 100644 index 0000000..4879750 --- /dev/null +++ b/log4j-nosql/src/test/resources/CassandraAppenderTest.xml @@ -0,0 +1,39 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You 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. + +--> +<Configuration name="CassandraAppenderTest"> + <Appenders> + <Cassandra name="Cassandra" clusterName="Test Cluster" keyspace="test" table="logs" bufferSize="10" batched="true"> + <SocketAddress host="localhost" port="9042"/> + <ColumnMapping name="id" pattern="%uuid{TIME}" type="java.util.UUID"/> + <ColumnMapping name="message" pattern="%message"/> + <ColumnMapping name="level" pattern="%level"/> + <ColumnMapping name="marker" pattern="%marker"/> + <ColumnMapping name="logger" pattern="%logger"/> + <ColumnMapping name="timestamp" pattern="%date{UNIX_MILLIS}" type="java.lang.Long"/> + <ColumnMapping name="mdc" type="org.apache.logging.log4j.spi.ThreadContextMap"/> + <ColumnMapping name="ndc" type="org.apache.logging.log4j.spi.ThreadContextStack"/> + </Cassandra> + </Appenders> + <Loggers> + <Logger name="org.apache.logging.log4j.nosql.appender.cassandra" level="DEBUG"> + <AppenderRef ref="Cassandra"/> + </Logger> + <Root level="ERROR"/> + </Loggers> +</Configuration> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/logging-log4j2/blob/33e7ab30/log4j-nosql/src/test/resources/cassandra.yaml ---------------------------------------------------------------------- diff --git a/log4j-nosql/src/test/resources/cassandra.yaml b/log4j-nosql/src/test/resources/cassandra.yaml new file mode 100644 index 0000000..356e43d --- /dev/null +++ b/log4j-nosql/src/test/resources/cassandra.yaml @@ -0,0 +1,901 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You 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. + +# Cassandra storage config YAML + +# NOTE: +# See http://wiki.apache.org/cassandra/StorageConfiguration 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. +# +# If you already have a cluster with 1 token per node, and wish to migrate to +# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations +num_tokens: 256 + +# 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: + +# See http://wiki.apache.org/cassandra/HintedHandoff +# May either be "true" or "false" to enable globally, or contain a list +# of data centers to enable per-datacenter. +# hinted_handoff_enabled: DC1,DC2 +hinted_handoff_enabled: true +# 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 + +# 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.credentials 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.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 + +# Validity period for roles cache (fetching permissions can be an +# expensive operation depending on the authorizer). 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. +# 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: 1000 + +# 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: 1000 + +# The partitioner is responsible for distributing groups of rows (by +# partition key) across nodes in the cluster. You should leave this +# alone for new clusters. The partitioner can NOT be changed without +# reloading all data, so when upgrading you should set this to the +# same partitioner you were already using. +# +# Besides Murmur3Partitioner, partitioners included for backwards +# compatibility include RandomPartitioner, ByteOrderedPartitioner, and +# OrderPreservingPartitioner. +# +partitioner: org.apache.cassandra.dht.Murmur3Partitioner + +# Directories where Cassandra should store data on disk. Cassandra +# will spread data evenly across them, subject to the granularity of +# the configured compaction strategy. +# 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 + +# 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 gossip and Thrift and kill the JVM, so the node can be replaced. +# stop: shut down gossip and Thrift, 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 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" or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait +# commitlog_sync_batch_window_in_ms milliseconds between fsyncs. +# This window should be kept short because the writer threads will +# be unable to do extra work while waiting. (You may need to increase +# concurrent_writes for the same reason.) +# +# commitlog_sync: batch +# commitlog_sync_batch_window_in_ms: 2 +# +# the other 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 + +# 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. +commitlog_segment_size_in_mb: 32 + +# 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: +# - + +# any class that implements the SeedProvider interface and has a +# constructor that takes a Map<String, String> 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: "<ip1>,<ip2>,<ip3>" + - seeds: "127.0.0.1" + +# 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 + +# Total memory to use for sstable-reading buffers. Defaults to +# the smaller of 1/4 of heap or 512MB. +# file_cache_size_in_mb: 512 + +# 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 + +# 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: native memory, eliminating nio buffer heap overhead +memtable_allocation_type: heap_buffers + +# 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 amount of memtable flush writer threads. These will +# be blocked by disk io, and each one will hold a memtable in memory +# while blocked. +# +# memtable_flush_writers 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. +#memtable_flush_writers: 8 + +# 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 encrypted communication. Unused unless enabled in +# encryption_options +# 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. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# +# 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). +# +# Setting listen_address to 0.0.0.0 is always wrong. +# +# 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_address: localhost +# listen_interface: eth0 +# 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. +# Please note that the address on which the native transport is bound is the +# same as the rpc_address. The port however is different and specified below. +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 +# The maximum threads for handling requests when the native transport is used. +# This is similar to rpc_max_threads though the default differs slightly (and +# there is no native_transport_min_threads, idle threads will always be stopped +# after 30 seconds). +# 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. +# 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 + +# Whether to start the thrift rpc server. +start_rpc: false + +# The address or interface to bind the Thrift RPC service and native transport +# server to. +# +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# +# 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. +# +# 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_address: localhost +# rpc_interface: eth1 +# rpc_interface_prefer_ipv6: false + +# port for Thrift to listen for clients on +rpc_port: 9160 + +# 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 + +# Cassandra provides two out-of-the-box options for the RPC Server: +# +# sync -> One thread per thrift connection. For a very large number of clients, memory +# will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size +# per thread, and that will correspond to your use of virtual memory (but physical memory +# may be limited depending on use of stack space). +# +# hsha -> Stands for "half synchronous, half asynchronous." All thrift clients are handled +# asynchronously using a small number of threads that does not vary with the amount +# of thrift clients (and thus scales well to many clients). The rpc requests are still +# synchronous (one thread per active request). If hsha is selected then it is essential +# that rpc_max_threads is changed from the default value of unlimited. +# +# The default is sync because on Windows hsha is about 30% slower. On Linux, +# sync/hsha performance is about the same, with hsha of course using less memory. +# +# Alternatively, can provide your own RPC server by providing the fully-qualified class name +# of an o.a.c.t.TServerFactory that can create an instance of it. +rpc_server_type: sync + +# Uncomment rpc_min|max_thread to set request pool size limits. +# +# Regardless of your choice of RPC server (see above), the number of maximum requests in the +# RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync +# RPC server, it also dictates the number of clients that can be connected at all). +# +# The default is unlimited and thus provides no protection against clients overwhelming the server. You are +# encouraged to set a maximum that makes sense for you in production, but do keep in mind that +# rpc_max_threads represents the maximum number of client requests this server may execute concurrently. +# +# rpc_min_threads: 16 +# rpc_max_threads: 2048 + +# uncomment to set socket buffer sizes on rpc connections +# rpc_send_buff_size_in_bytes: +# rpc_recv_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 +# See: +# /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: +# internode_recv_buff_size_in_bytes: + +# Frame size for thrift (maximum message length). +thrift_framed_transport_size_in_mb: 15 + +# 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 + +# 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 + +# 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: +# 1) a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# 2) 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 + + +# Log WARN on any 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 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 + +# 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 + +# 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 account for all types +# of compaction, including validation compaction. +compaction_throughput_mb_per_sec: 16 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# 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 + +# 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 +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete +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 +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.) +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations +request_timeout_in_ms: 10000 + +# 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: before enabling this property make sure to ntp is installed +# and the times are synchronized between the nodes. +cross_node_timeout: false + +# Set socket timeout for streaming operation. +# The stream session is failed if no data/ack is received by any of the participants +# within that period, which means this should also be sufficient to stream a large +# sstable or rebuild table indexes. +# Default value is 86400000ms, which means stale streams timeout after 24 hours. +# A value of zero means stream sockets should never time out. +# streaming_socket_timeout_in_ms: 86400000 + +# 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 and read_repair_chance is < 1.0, 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: 0.1 + +# request_scheduler -- Set this to a class that implements +# RequestScheduler, which will schedule incoming client requests +# according to the specific policy. This is useful for multi-tenancy +# with a single Cassandra cluster. +# NOTE: This is specifically for requests from the client and does +# not affect inter node communication. +# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place +# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of +# client requests to a node with a separate queue for each +# request_scheduler_id. The scheduler is further customized by +# request_scheduler_options as described below. +request_scheduler: org.apache.cassandra.scheduler.NoScheduler + +# Scheduler Options vary based on the type of scheduler +# NoScheduler - Has no options +# RoundRobin +# - throttle_limit -- The throttle_limit is the number of in-flight +# requests per client. Requests beyond +# that limit are queued up until +# running requests can complete. +# The value of 80 here is twice the number of +# concurrent_reads + concurrent_writes. +# - default_weight -- default_weight is optional and allows for +# overriding the default which is 1. +# - weights -- Weights are optional and will default to 1 or the +# overridden default_weight. The weight translates into how +# many requests are handled during each turn of the +# RoundRobin, based on the scheduler id. +# +# request_scheduler_options: +# throttle_limit: 80 +# default_weight: 5 +# weights: +# Keyspace1: 1 +# Keyspace2: 5 + +# request_scheduler_id -- An identifier based on which to perform +# the request scheduling. Currently the only valid option is keyspace. +# request_scheduler_id: keyspace + +# Enable or disable inter-node encryption +# Default settings are TLS v1, RSA 1024-bit keys (it is imperative that +# users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher +# suite for authentication, key exchange and encryption of the actual data transfers. +# Use the DHE/ECDHE ciphers if running in FIPS 140 compliant mode. +# NOTE: No custom encryption options are enabled at the moment +# The available internode options are : all, none, dc, rack +# +# If set to dc cassandra will encrypt the traffic between the DCs +# If set to rack cassandra will encrypt the traffic between the racks +# +# The passwords used in these options must match the passwords used when generating +# the keystore and truststore. For instructions on generating these files, see: +# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# +server_encryption_options: + internode_encryption: none + keystore: conf/.keystore + keystore_password: cassandra + truststore: conf/.truststore + truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] + # require_client_auth: false + +# enable or disable client/server encryption. +client_encryption_options: + enabled: false + # If enabled and optional is set to true encrypted and unencrypted connections are handled. + optional: false + keystore: conf/.keystore + keystore_password: cassandra + # require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_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: all + +# 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 + +# By default, Cassandra logs GC Pauses greater than 200 ms 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 +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# Adjust the threshold based on your application throughput requirement +# gc_warn_threshold_in_ms: 1000 + +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 2.2, there is no security manager or anything else in place that +# prevents execution of evil code. CASSANDRA-9402 will fix this issue for Cassandra 3.0. +# This will inherently be backwards-incompatible with any 2.2 UDF that perform insecure +# operations such as opening a socket or writing to the filesystem. +enable_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
