You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@beam.apache.org by da...@apache.org on 2017/04/06 14:33:21 UTC
[2/7] beam git commit: HadoopInputFormatIO with junits
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOCassandraIT.java
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOCassandraIT.java b/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOCassandraIT.java
new file mode 100644
index 0000000..bf9a5fd
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOCassandraIT.java
@@ -0,0 +1,173 @@
+/*
+ * 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.beam.sdk.io.hadoop.inputformat.integration.tests;
+
+import com.datastax.driver.core.Row;
+
+import java.io.Serializable;
+
+import org.apache.beam.sdk.io.hadoop.inputformat.HadoopInputFormatIO;
+import org.apache.beam.sdk.io.hadoop.inputformat.custom.options.HIFTestOptions;
+import org.apache.beam.sdk.io.hadoop.inputformat.hashing.HashingFn;
+import org.apache.beam.sdk.options.PipelineOptionsFactory;
+import org.apache.beam.sdk.testing.PAssert;
+import org.apache.beam.sdk.testing.TestPipeline;
+import org.apache.beam.sdk.transforms.Combine;
+import org.apache.beam.sdk.transforms.Count;
+import org.apache.beam.sdk.transforms.SimpleFunction;
+import org.apache.beam.sdk.transforms.Values;
+import org.apache.beam.sdk.values.KV;
+import org.apache.beam.sdk.values.PCollection;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.mapreduce.InputFormat;
+import org.junit.BeforeClass;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.JUnit4;
+
+/**
+ * A test of {@link org.apache.beam.sdk.io.hadoop.inputformat.HadoopInputFormatIO} on an
+ * independent Cassandra instance.
+ *
+ * <p>This test requires a running instance of Cassandra, and the test dataset must exist in
+ * the database.
+ *
+ * <p>You can run this test by doing the following:
+ * <pre>
+ * mvn -e -Pio-it verify -pl sdks/java/io/hadoop/jdk1.8-tests/HIFIOCassandraIT
+ * -DintegrationTestPipelineOptions='[
+ * "--cassandraServerIp=1.2.3.4",
+ * "--cassandraServerPort=port",
+ * "--cassandraUserName=user",
+ * "--cassandraPassword=mypass" ]'
+ * </pre>
+ *
+ * <p>If you want to run this with a runner besides directrunner, there are profiles for dataflow
+ * and spark in the jdk1.8-tests pom. You'll want to activate those in addition to the normal test
+ * runner invocation pipeline options.
+ */
+
+@RunWith(JUnit4.class)
+public class HIFIOCassandraIT implements Serializable {
+
+ private static final String CASSANDRA_KEYSPACE = "ycsb";
+ private static final String CASSANDRA_TABLE = "usertable";
+ private static final String CASSANDRA_THRIFT_PORT_PROPERTY = "cassandra.input.thrift.port";
+ private static final String CASSANDRA_THRIFT_ADDRESS_PROPERTY = "cassandra.input.thrift.address";
+ private static final String CASSANDRA_PARTITIONER_CLASS_PROPERTY =
+ "cassandra.input.partitioner.class";
+ private static final String CASSANDRA_KEYSPACE_PROPERTY = "cassandra.input.keyspace";
+ private static final String CASSANDRA_COLUMNFAMILY_PROPERTY = "cassandra.input.columnfamily";
+ private static final String CASSANDRA_PARTITIONER_CLASS_VALUE = "Murmur3Partitioner";
+ private static final String USERNAME = "cassandra.username";
+ private static final String PASSWORD = "cassandra.password";
+ private static final String INPUT_KEYSPACE_USERNAME_CONFIG = "cassandra.input.keyspace.username";
+ private static final String INPUT_KEYSPACE_PASSWD_CONFIG = "cassandra.input.keyspace.passwd";
+ private static HIFTestOptions options;
+ @Rule
+ public final transient TestPipeline pipeline = TestPipeline.create();
+
+ @BeforeClass
+ public static void setUp() {
+ PipelineOptionsFactory.register(HIFTestOptions.class);
+ options = TestPipeline.testingPipelineOptions().as(HIFTestOptions.class);
+ }
+
+ /**
+ * This test reads data from the Cassandra instance and verifies if data is read successfully.
+ */
+ @Test
+ public void testHIFReadForCassandra() {
+ // Expected hashcode is evaluated during insertion time one time and hardcoded here.
+ String expectedHashCode = "5ea121d90d95c84076f7556605080f4b2c3081a7";
+ Long expectedRecordsCount = 1000L;
+ Configuration conf = getConfiguration(options);
+ PCollection<KV<Long, String>> cassandraData = pipeline.apply(HadoopInputFormatIO
+ .<Long, String>read().withConfiguration(conf).withValueTranslation(myValueTranslate));
+ PAssert.thatSingleton(cassandraData.apply("Count", Count.<KV<Long, String>>globally()))
+ .isEqualTo(expectedRecordsCount);
+ PCollection<String> textValues = cassandraData.apply(Values.<String>create());
+ // Verify the output values using checksum comparison.
+ PCollection<String> consolidatedHashcode =
+ textValues.apply(Combine.globally(new HashingFn()).withoutDefaults());
+ PAssert.that(consolidatedHashcode).containsInAnyOrder(expectedHashCode);
+ pipeline.run().waitUntilFinish();
+ }
+
+ SimpleFunction<Row, String> myValueTranslate = new SimpleFunction<Row, String>() {
+ @Override
+ public String apply(Row input) {
+ return input.getString("y_id") + "|" + input.getString("field0") + "|"
+ + input.getString("field1") + "|" + input.getString("field2") + "|"
+ + input.getString("field3") + "|" + input.getString("field4") + "|"
+ + input.getString("field5") + "|" + input.getString("field6") + "|"
+ + input.getString("field7") + "|" + input.getString("field8") + "|"
+ + input.getString("field9");
+ }
+ };
+ /**
+ * This test reads data from the Cassandra instance based on query and verifies if data is read
+ * successfully.
+ */
+ @Test
+ public void testHIFReadForCassandraQuery() {
+ String expectedHashCode = "a19593e4c72a67e26cb470130864daabf5a99d62";
+ Long expectedNumRows = 1L;
+ Configuration conf = getConfiguration(options);
+ conf.set("cassandra.input.cql", "select * from " + CASSANDRA_KEYSPACE + "." + CASSANDRA_TABLE
+ + " where token(y_id) > ? and token(y_id) <= ? "
+ + "and field0 = 'user48:field0:431531' allow filtering");
+ PCollection<KV<Long, String>> cassandraData =
+ pipeline.apply(HadoopInputFormatIO.<Long, String>read().withConfiguration(conf)
+ .withValueTranslation(myValueTranslate));
+ PAssert.thatSingleton(cassandraData.apply("Count", Count.<KV<Long, String>>globally()))
+ .isEqualTo(expectedNumRows);
+ PCollection<String> textValues = cassandraData.apply(Values.<String>create());
+ // Verify the output values using checksum comparison.
+ PCollection<String> consolidatedHashcode =
+ textValues.apply(Combine.globally(new HashingFn()).withoutDefaults());
+ PAssert.that(consolidatedHashcode).containsInAnyOrder(expectedHashCode);
+ pipeline.run().waitUntilFinish();
+ }
+
+ /**
+ * Returns Hadoop configuration for reading data from Cassandra. To read data from Cassandra using
+ * HadoopInputFormatIO, following properties must be set: InputFormat class, InputFormat key
+ * class, InputFormat value class, Thrift address, Thrift port, partitioner class, keyspace and
+ * columnfamily name.
+ */
+ private static Configuration getConfiguration(HIFTestOptions options) {
+ Configuration conf = new Configuration();
+ conf.set(CASSANDRA_THRIFT_PORT_PROPERTY, options.getCassandraServerPort().toString());
+ conf.set(CASSANDRA_THRIFT_ADDRESS_PROPERTY, options.getCassandraServerIp());
+ conf.set(CASSANDRA_PARTITIONER_CLASS_PROPERTY, CASSANDRA_PARTITIONER_CLASS_VALUE);
+ conf.set(CASSANDRA_KEYSPACE_PROPERTY, CASSANDRA_KEYSPACE);
+ conf.set(CASSANDRA_COLUMNFAMILY_PROPERTY, CASSANDRA_TABLE);
+ // Set user name and password if Cassandra instance has security configured.
+ conf.set(USERNAME, options.getCassandraUserName());
+ conf.set(PASSWORD, options.getCassandraPassword());
+ conf.set(INPUT_KEYSPACE_USERNAME_CONFIG, options.getCassandraUserName());
+ conf.set(INPUT_KEYSPACE_PASSWD_CONFIG, options.getCassandraPassword());
+ conf.setClass("mapreduce.job.inputformat.class",
+ org.apache.cassandra.hadoop.cql3.CqlInputFormat.class, InputFormat.class);
+ conf.setClass("key.class", java.lang.Long.class, Object.class);
+ conf.setClass("value.class", com.datastax.driver.core.Row.class, Object.class);
+ return conf;
+ }
+}
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOElasticIT.java
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOElasticIT.java b/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOElasticIT.java
new file mode 100644
index 0000000..13c0cbc
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/java/org/apache/beam/sdk/io/hadoop/inputformat/integration/tests/HIFIOElasticIT.java
@@ -0,0 +1,215 @@
+/*
+ * 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.beam.sdk.io.hadoop.inputformat.integration.tests;
+
+import java.io.IOException;
+import java.io.Serializable;
+
+import org.apache.beam.sdk.io.hadoop.inputformat.HadoopInputFormatIO;
+import org.apache.beam.sdk.io.hadoop.inputformat.custom.options.HIFTestOptions;
+import org.apache.beam.sdk.io.hadoop.inputformat.hashing.HashingFn;
+import org.apache.beam.sdk.options.PipelineOptionsFactory;
+import org.apache.beam.sdk.testing.PAssert;
+import org.apache.beam.sdk.testing.TestPipeline;
+import org.apache.beam.sdk.transforms.Combine;
+import org.apache.beam.sdk.transforms.Count;
+import org.apache.beam.sdk.transforms.MapElements;
+import org.apache.beam.sdk.transforms.SimpleFunction;
+import org.apache.beam.sdk.transforms.Values;
+import org.apache.beam.sdk.values.KV;
+import org.apache.beam.sdk.values.PCollection;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.io.MapWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputFormat;
+import org.elasticsearch.hadoop.cfg.ConfigurationOptions;
+import org.elasticsearch.hadoop.mr.LinkedMapWritable;
+import org.junit.BeforeClass;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.JUnit4;
+
+/**
+ * A test of {@link org.apache.beam.sdk.io.hadoop.inputformat.HadoopInputFormatIO} on an
+ * independent Elasticsearch instance.
+ *
+ * <p>This test requires a running instance of Elasticsearch, and the test dataset must exist in
+ * the database.
+ *
+ * <p>You can run this test by doing the following:
+ * <pre>
+ * mvn -e -Pio-it verify -pl sdks/java/io/hadoop/jdk1.8-tests/HIFIOElasticIT
+ * -DintegrationTestPipelineOptions='[
+ * "--elasticServerIp=1.2.3.4",
+ * "--elasticServerPort=port",
+ * "--elasticUserName=user",
+ * "--elasticPassword=mypass" ]'
+ * </pre>
+ *
+ * <p>If you want to run this with a runner besides directrunner, there are profiles for dataflow
+ * and spark in the jdk1.8-tests pom. You'll want to activate those in addition to the normal test
+ * runner invocation pipeline options.
+ */
+
+@RunWith(JUnit4.class)
+public class HIFIOElasticIT implements Serializable {
+
+ private static final String ELASTIC_INTERNAL_VERSION = "5.x";
+ private static final String TRUE = "true";
+ private static final String ELASTIC_INDEX_NAME = "test_data";
+ private static final String ELASTIC_TYPE_NAME = "test_type";
+ private static final String ELASTIC_RESOURCE = "/" + ELASTIC_INDEX_NAME + "/" + ELASTIC_TYPE_NAME;
+ private static HIFTestOptions options;
+ @Rule
+ public final transient TestPipeline pipeline = TestPipeline.create();
+
+ @BeforeClass
+ public static void setUp() {
+ PipelineOptionsFactory.register(HIFTestOptions.class);
+ options = TestPipeline.testingPipelineOptions().as(HIFTestOptions.class);
+ }
+
+ /**
+ * This test reads data from the Elasticsearch instance and verifies whether data is read
+ * successfully.
+ */
+ @Test
+ public void testHifIOWithElastic() throws SecurityException, IOException {
+ // Expected hashcode is evaluated during insertion time one time and hardcoded here.
+ final long expectedRowCount = 1000L;
+ String expectedHashCode = "ed36c09b5e24a95fd8d3cc711a043a85320bb47d";
+ Configuration conf = getConfiguration(options);
+ PCollection<KV<Text, LinkedMapWritable>> esData =
+ pipeline.apply(HadoopInputFormatIO.<Text, LinkedMapWritable>read().withConfiguration(conf));
+ // Verify that the count of objects fetched using HIFInputFormat IO is correct.
+ PCollection<Long> count = esData.apply(Count.<KV<Text, LinkedMapWritable>>globally());
+ PAssert.thatSingleton(count).isEqualTo(expectedRowCount);
+ PCollection<LinkedMapWritable> values = esData.apply(Values.<LinkedMapWritable>create());
+ PCollection<String> textValues = values.apply(transformFunc);
+ // Verify the output values using checksum comparison.
+ PCollection<String> consolidatedHashcode =
+ textValues.apply(Combine.globally(new HashingFn()).withoutDefaults());
+ PAssert.that(consolidatedHashcode).containsInAnyOrder(expectedHashCode);
+ pipeline.run().waitUntilFinish();
+ }
+
+ MapElements<LinkedMapWritable, String> transformFunc =
+ MapElements.<LinkedMapWritable, String>via(new SimpleFunction<LinkedMapWritable, String>() {
+ @Override
+ public String apply(LinkedMapWritable mapw) {
+ String rowValue = "";
+ rowValue = convertMapWRowToString(mapw);
+ return rowValue;
+ }
+ });
+ /*
+ * Function to create a toString implementation of a MapWritable row by writing all field values
+ * in a string row.
+ */
+ private String convertMapWRowToString(LinkedMapWritable mapw) {
+ String rowValue = "";
+ rowValue = addFieldValuesToRow(rowValue, mapw, "User_Name");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Item_Code");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Txn_ID");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Item_ID");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "last_updated");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Price");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Title");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Description");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Age");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Item_Name");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Item_Price");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Availability");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Batch_Num");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "Last_Ordered");
+ rowValue = addFieldValuesToRow(rowValue, mapw, "City");
+ return rowValue;
+ }
+
+ /*
+ * Convert a MapWritable row field into a string, and append it to the row string with a
+ * separator.
+ */
+ private String addFieldValuesToRow(String row, MapWritable mapw, String columnName) {
+ Object valueObj = (Object) mapw.get(new Text(columnName));
+ row += valueObj.toString() + "|";
+ return row;
+ }
+
+ /**
+ * This test reads data from the Elasticsearch instance based on a query and verifies if data is
+ * read successfully.
+ */
+ @Test
+ public void testHifIOWithElasticQuery() {
+ String expectedHashCode = "83c108ff81e87b6f3807c638e6bb9a9e3d430dc7";
+ Long expectedRecordsCount = 1L;
+ Configuration conf = getConfiguration(options);
+ String query = "{"
+ + " \"query\": {"
+ + " \"match\" : {"
+ + " \"Title\" : {"
+ + " \"query\" : \"Title9\","
+ + " \"type\" : \"boolean\""
+ + " }"
+ + " }"
+ + " }"
+ + "}";
+ conf.set(ConfigurationOptions.ES_QUERY, query);
+ PCollection<KV<Text, LinkedMapWritable>> esData =
+ pipeline.apply(HadoopInputFormatIO.<Text, LinkedMapWritable>read().withConfiguration(conf));
+ PCollection<Long> count = esData.apply(Count.<KV<Text, LinkedMapWritable>>globally());
+ // Verify that the count of objects fetched using HIFInputFormat IO is correct.
+ PAssert.thatSingleton(count).isEqualTo(expectedRecordsCount);
+ PCollection<LinkedMapWritable> values = esData.apply(Values.<LinkedMapWritable>create());
+ PCollection<String> textValues = values.apply(transformFunc);
+ // Verify the output values using checksum comparison.
+ PCollection<String> consolidatedHashcode =
+ textValues.apply(Combine.globally(new HashingFn()).withoutDefaults());
+ PAssert.that(consolidatedHashcode).containsInAnyOrder(expectedHashCode);
+ pipeline.run().waitUntilFinish();
+ }
+
+ /**
+ * Returns Hadoop configuration for reading data from Elasticsearch. Configuration object should
+ * have InputFormat class, key class and value class to be set. Mandatory fields for ESInputFormat
+ * to be set are es.resource, es.nodes, es.port, es.internal.es.version, es.nodes.wan.only. Please
+ * refer <a href="https://www.elastic.co/guide/en/elasticsearch/hadoop/current/configuration.html"
+ * >Elasticsearch Configuration</a> for more details.
+ */
+ private static Configuration getConfiguration(HIFTestOptions options) {
+ Configuration conf = new Configuration();
+ conf.set(ConfigurationOptions.ES_NODES, options.getElasticServerIp());
+ conf.set(ConfigurationOptions.ES_PORT, options.getElasticServerPort().toString());
+ conf.set(ConfigurationOptions.ES_NODES_WAN_ONLY, TRUE);
+ // Set username and password if Elasticsearch is configured with security.
+ conf.set(ConfigurationOptions.ES_NET_HTTP_AUTH_USER, options.getElasticUserName());
+ conf.set(ConfigurationOptions.ES_NET_HTTP_AUTH_PASS, options.getElasticPassword());
+ conf.set(ConfigurationOptions.ES_RESOURCE, ELASTIC_RESOURCE);
+ conf.set("es.internal.es.version", ELASTIC_INTERNAL_VERSION);
+ conf.set(ConfigurationOptions.ES_INDEX_AUTO_CREATE, TRUE);
+ conf.setClass("mapreduce.job.inputformat.class",
+ org.elasticsearch.hadoop.mr.EsInputFormat.class, InputFormat.class);
+ conf.setClass("key.class", Text.class, Object.class);
+ conf.setClass("value.class", LinkedMapWritable.class, Object.class);
+ // Optimizations added to change the max docs per partition, scroll size and batch size of
+ // bytes to improve the test time for large data
+ conf.set("es.input.max.docs.per.partition", "50000");
+ conf.set("es.scroll.size", "400");
+ conf.set("es.batch.size.bytes", "8mb");
+ return conf;
+ }
+}
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/cassandra.yaml
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/cassandra.yaml b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/cassandra.yaml
new file mode 100644
index 0000000..ca1e48f
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/cassandra.yaml
@@ -0,0 +1,1074 @@
+#
+# 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 required for Embedded Cassandra server test
+
+# 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: 'beam'
+
+# 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: 1
+
+# 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 replication strategy used by the specified
+# keyspace.
+#
+# The load assigned to each node will be close to proportional to its number of
+# vnodes.
+#
+# Only supported with the Murmur3Partitioner.
+# allocate_tokens_for_keyspace: KEYSPACE
+
+# 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
+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
+hints_directory: target/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.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 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. 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
+data_file_directories:
+ - target/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
+commitlog_directory: target/cassandra/commitlog
+cdc_raw_directory: target/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 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 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 Thrift prepared statement cache
+#
+# If you do not use Thrift at all, it is safe to leave this value at "auto".
+#
+# See description of 'prepared_statements_cache_size_mb' above for more information.
+#
+# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater
+thrift_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
+saved_caches_directory: target/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: 1
+
+# 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.
+#
+# 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: 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
+
+# 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 sstable chunk cache and buffer pooling.
+# 32MB of this are reserved for pooling buffers, the rest is used as an
+# 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
+
+# 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
+
+# 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 one per data_file_directory.
+#
+# If your data directories are backed by SSD, you can increase this, but
+# avoid having memtable_flush_writers * data_file_directories > number of cores
+#memtable_flush_writers: 1
+
+# 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
+# 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 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. If you're changing this parameter,
+# you may want to adjust max_value_size_in_mb accordingly.
+# 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: true
+
+# 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: 127.0.0.1
+# 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
+
+# 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
+# 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
+
+# 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
+
+# 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)
+#
+# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
+# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
+# ARE PLACED.
+#
+# IF THE RACK A REPLICA IS PLACED IN CHANGES AFTER THE REPLICA HAS BEEN
+# ADDED TO A RING, THE NODE MUST BE DECOMMISSIONED AND REBOOTSTRAPPED.
+#
+# 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
+# JVM 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: 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
+ # require_endpoint_verification: 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: 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
+
+# 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
+
+# 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
+
+# Log a warning when compacting partitions larger than this value
+compaction_large_partition_warning_threshold_mb: 100
+
+# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level
+# Adjust the threshold based on your application throughput requirement
+# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level
+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.
+# max_value_size_in_mb: 256
+
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/cassandra-svc-rc.yaml
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/cassandra-svc-rc.yaml b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/cassandra-svc-rc.yaml
new file mode 100644
index 0000000..7c36e34
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/cassandra-svc-rc.yaml
@@ -0,0 +1,88 @@
+# 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.
+
+# Headless service that allows us to get the IP addresses of our Cassandra nodes
+apiVersion: v1
+kind: Service
+metadata:
+ labels:
+ name: cassandra-peers
+ name: cassandra-peers
+spec:
+ clusterIP: None
+ ports:
+ - port: 7000
+ name: intra-node-communication
+ - port: 7001
+ name: tls-intra-node-communication
+ selector:
+ name: cassandra
+---
+# Kubernetes service file exposing Cassandra endpoint used by clients.
+apiVersion: v1
+kind: Service
+metadata:
+ labels:
+ name: cassandra
+ name: cassandra
+spec:
+ ports:
+ - port: 9042
+ name: cql
+ selector:
+ name: cassandra
+ type: LoadBalancer
+---
+# Replication Controller for Cassandra which tracks the Cassandra pods.
+apiVersion: v1
+kind: ReplicationController
+metadata:
+ labels:
+ name: cassandra
+ name: cassandra
+spec:
+ replicas: 1
+ selector:
+ name: cassandra
+ template:
+ metadata:
+ labels:
+ name: cassandra
+ spec:
+ containers:
+ - image: cassandra
+ name: cassandra
+ env:
+ - name: PEER_DISCOVERY_SERVICE
+ value: cassandra-peers
+ - name: CASSANDRA_CLUSTER_NAME
+ value: Cassandra
+ - name: CASSANDRA_DC
+ value: DC1
+ - name: CASSANDRA_RACK
+ value: Kubernetes Cluster
+# Number of tokens currently configured to 1. If this is not configured, default value is 256. You can change it as per requirement.
+ - name: CASSANDRA_NUM_TOKENS
+ value: '1'
+ ports:
+ - containerPort: 9042
+ name: cql
+ volumeMounts:
+ - mountPath: /var/lib/cassandra/data
+ name: data
+ volumes:
+ - name: data
+ emptyDir: {}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/start-up.sh
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/start-up.sh b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/start-up.sh
new file mode 100644
index 0000000..c05b771
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/start-up.sh
@@ -0,0 +1,21 @@
+# 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.
+
+#!/bin/bash
+set -e
+
+# Create Cassandra services and Replication controller.
+kubectl create -f cassandra-svc-rc.yaml
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/teardown.sh
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/teardown.sh b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/teardown.sh
new file mode 100644
index 0000000..f538a75
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/SmallITCluster/teardown.sh
@@ -0,0 +1,21 @@
+#
+# 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.
+#
+#!/bin/bash
+set -e
+
+# Delete Cassandra services and Replication controller.
+kubectl delete -f cassandra-svc-rc.yaml
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load-setup.sh
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load-setup.sh b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load-setup.sh
new file mode 100644
index 0000000..4e12f89
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load-setup.sh
@@ -0,0 +1,29 @@
+# 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.
+
+#!/bin/bash
+set -e
+
+# Load YCSB tool
+echo "Downloading YCSB tool"
+echo "------------------------------"
+curl -O --location https://github.com/brianfrankcooper/YCSB/releases/download/0.12.0/ycsb-0.12.0.tar.gz
+tar xfz ycsb-0.12.0.tar.gz
+wget https://www.slf4j.org/dist/slf4j-1.7.22.tar.gz
+tar xfz slf4j-1.7.22.tar.gz
+cp slf4j-1.7.22/slf4j-simple-*.jar ycsb-0.12.0/lib/
+cp slf4j-1.7.22/slf4j-api-*.jar ycsb-0.12.0/lib/
+echo "YCSB tool loaded"
http://git-wip-us.apache.org/repos/asf/beam/blob/174436bc/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load.sh
----------------------------------------------------------------------
diff --git a/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load.sh b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load.sh
new file mode 100644
index 0000000..59d0e22
--- /dev/null
+++ b/sdks/java/io/hadoop/jdk1.8-tests/src/test/resources/kubernetes/cassandra/data-load.sh
@@ -0,0 +1,67 @@
+# 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.
+
+#!/bin/bash
+set -e
+
+recordcount=1000
+# Identify the pod
+cassandra_pods="kubectl get pods -l name=cassandra"
+running_seed="$(kubectl get pods -o json -l name=cassandra -o jsonpath=\
+'{.items[0].metadata.name}')"
+echo "Detected Running Pod $running_seed"
+
+# After starting the service, it takes couple of minutes to generate the external IP for the
+# service. Hence, wait for sometime.
+
+# Identify external IP of the pod
+external_ip="$(kubectl get svc cassandra -o jsonpath='{.status.loadBalancer.ingress[0].ip}')"
+echo "Waiting for the Cassandra service to come up ........"
+while [ -z "$external_ip" ]
+do
+ sleep 10s
+ external_ip="$(kubectl get svc cassandra -o jsonpath='{.status.loadBalancer.ingress[0].ip}')"
+ echo "."
+done
+echo "External IP - $external_ip"
+
+# Create keyspace
+keyspace_creation_command="drop keyspace if exists ycsb;create keyspace ycsb WITH REPLICATION = {\
+'class' : 'SimpleStrategy', 'replication_factor': 3 };"
+kubectl exec -ti $running_seed -- cqlsh -e "$keyspace_creation_command"
+echo "Keyspace creation............"
+echo "-----------------------------"
+echo "$keyspace_creation_command"
+echo
+
+# Create table
+table_creation_command="use ycsb;drop table if exists usertable;create table usertable (\
+y_id varchar primary key,field0 varchar,field1 varchar,field2 varchar,field3 varchar,\
+field4 varchar,field5 varchar,field6 varchar,field7 varchar,field8 varchar,field9 varchar);"
+kubectl exec -ti $running_seed -- cqlsh -e "$table_creation_command"
+echo "Table creation .............."
+echo "-----------------------------"
+echo "$table_creation_command"
+
+cd ycsb-0.12.0
+
+echo "Starting to load data on ${external_ip}"
+echo "-----------------------------"
+# Record count set to 1000, change this value to load as per requirement.
+# dataintegrity flag is set to true to load deterministic data
+./bin/ycsb load cassandra-cql -p hosts=${external_ip} -p dataintegrity=true -p recordcount=\
+${recordcount} -p insertorder=ordered -p fieldlength=20 -P workloads/workloadd \
+-s > workloada_load_res.txt