From 75e2763054ed80aeeef0954dc549ad10aebb3d0c Mon Sep 17 00:00:00 2001 From: Mark Paluch Date: Wed, 28 Apr 2021 10:03:49 +0200 Subject: [PATCH] Use Testcontainers for Cassandra examples. See #606. --- cassandra/util/pom.xml | 36 +- .../cassandra/util/CassandraExtension.java | 44 +- .../cassandra/util/CassandraServer.java | 24 +- .../cassandra/util/CassandraVersion.java | 4 +- .../main/resources/embedded-cassandra.yaml | 652 ------------------ pom.xml | 14 + 6 files changed, 63 insertions(+), 711 deletions(-) delete mode 100644 cassandra/util/src/main/resources/embedded-cassandra.yaml diff --git a/cassandra/util/pom.xml b/cassandra/util/pom.xml index 296b9514..8fa717fa 100644 --- a/cassandra/util/pom.xml +++ b/cassandra/util/pom.xml @@ -21,23 +21,13 @@ - org.apache.cassandra - cassandra-all - 3.11.5 - - - guava - com.google.guava - - - io.netty - netty-all - - - com.addthis.metrics - reporter-config3 - - + junit + junit + + + + org.testcontainers + cassandra @@ -45,18 +35,6 @@ java-driver-core - - org.cassandraunit - cassandra-unit - 4.3.1.0 - - - io.netty - netty-handler - - - - com.google.guava guava diff --git a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraExtension.java b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraExtension.java index d8ff1727..3b1a54ff 100644 --- a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraExtension.java +++ b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraExtension.java @@ -22,6 +22,10 @@ import org.junit.jupiter.api.extension.BeforeAllCallback; import org.junit.jupiter.api.extension.ExtensionContext; import org.junit.platform.commons.util.AnnotationUtils; +import org.springframework.util.StringUtils; + +import org.testcontainers.containers.CassandraContainer; + import com.datastax.oss.driver.api.core.CqlSession; /** @@ -36,20 +40,26 @@ class CassandraExtension implements BeforeAllCallback { .create(CassandraExtension.class); @Override - public void beforeAll(ExtensionContext context) throws Exception { + public void beforeAll(ExtensionContext context) { - ExtensionContext.Store store = context.getStore(NAMESPACE); - CassandraKeyspace cassandra = findAnnotation(context); + var store = context.getStore(NAMESPACE); + var cassandra = findAnnotation(context); - CassandraServer keyspace = store.getOrComputeIfAbsent(CassandraServer.class, it -> { - return CassandraServer.embeddedIfNotRunning("localhost", 9042); + var keyspace = store.getOrComputeIfAbsent(CassandraServer.class, it -> { + + CassandraContainer container = runTestcontainer(); + System.setProperty("spring.data.cassandra.port", "" + container.getMappedPort(9042)); + System.setProperty("spring.data.cassandra.contact-points", "" + container.getHost()); + + return new CassandraServer(container.getHost(), container.getMappedPort(9042), + CassandraServer.RuntimeMode.EMBEDDED_IF_NOT_RUNNING); }, CassandraServer.class); keyspace.before(); - CqlSession session = store.getOrComputeIfAbsent(CqlSession.class, it -> { + var session = store.getOrComputeIfAbsent(CqlSession.class, it -> { - return CqlSession.builder().addContactPoint(new InetSocketAddress("localhost", 9042)) + return CqlSession.builder().addContactPoint(new InetSocketAddress(keyspace.host(), keyspace.port())) .withLocalDatacenter("datacenter1").build(); }, CqlSession.class); @@ -59,10 +69,26 @@ class CassandraExtension implements BeforeAllCallback { private static CassandraKeyspace findAnnotation(ExtensionContext context) { - Class testClass = context.getRequiredTestClass(); + var testClass = context.getRequiredTestClass(); - Optional annotation = AnnotationUtils.findAnnotation(testClass, CassandraKeyspace.class); + var annotation = AnnotationUtils.findAnnotation(testClass, CassandraKeyspace.class); return annotation.orElseThrow(() -> new IllegalStateException("Test class not annotated with @Cassandra")); } + + private CassandraContainer runTestcontainer() { + + var container = new CassandraContainer<>(getCassandraDockerImageName()); + container.withReuse(true); + + container.start(); + + return container; + } + + private String getCassandraDockerImageName() { + + return String.format("cassandra:%s", + Optional.ofNullable(System.getenv("CASSANDRA_VERSION")).filter(StringUtils::hasText).orElse("3.11.10")); + } } diff --git a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraServer.java b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraServer.java index 3619af68..bb5a6cbb 100644 --- a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraServer.java +++ b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraServer.java @@ -19,7 +19,6 @@ import java.net.InetSocketAddress; import java.net.Socket; import java.util.concurrent.TimeUnit; -import org.cassandraunit.utils.EmbeddedCassandraServerHelper; import org.junit.jupiter.api.Assumptions; import org.springframework.util.Assert; @@ -30,18 +29,8 @@ import org.springframework.util.Assert; * * @author Mark Paluch */ -class CassandraServer { - - private final String host; - private final int port; - private final RuntimeMode runtimeMode; - - private CassandraServer(String host, int port, RuntimeMode runtimeMode) { - - this.host = host; - this.port = port; - this.runtimeMode = runtimeMode; - } +record CassandraServer(String host, int port, + example.springdata.cassandra.util.CassandraServer.RuntimeMode runtimeMode) { /** * Require a running instance on {@code host:port}. Fails with {@link AssumptionViolatedException} if Cassandra is not @@ -75,7 +64,7 @@ class CassandraServer { Assert.hasText(host, "Host must not be null or empty!"); - try (Socket socket = new Socket()) { + try (var socket = new Socket()) { socket.setSoLinger(true, 0); socket.connect(new InetSocketAddress(host, port), (int) TimeUnit.MILLISECONDS.convert(10, TimeUnit.SECONDS)); @@ -95,7 +84,7 @@ class CassandraServer { return port; } - protected void before() throws Exception { + protected void before() { if (runtimeMode == RuntimeMode.REQUIRE_RUNNING_INSTANCE) { Assumptions.assumeTrue(isConnectable(getHost(), getPort()), @@ -107,12 +96,9 @@ class CassandraServer { return; } } - - EmbeddedCassandraServerHelper.startEmbeddedCassandra("embedded-cassandra.yaml", "target/embeddedCassandra", - TimeUnit.SECONDS.toMillis(60)); } - private enum RuntimeMode { + enum RuntimeMode { REQUIRE_RUNNING_INSTANCE, EMBEDDED_IF_NOT_RUNNING; } } diff --git a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraVersion.java b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraVersion.java index 391eee47..77a99d40 100644 --- a/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraVersion.java +++ b/cassandra/util/src/main/java/example/springdata/cassandra/util/CassandraVersion.java @@ -42,8 +42,8 @@ public class CassandraVersion { Assert.notNull(session, "Session must not be null"); - ResultSet resultSet = session.execute("SELECT release_version FROM system.local;"); - Row row = resultSet.one(); + var resultSet = session.execute("SELECT release_version FROM system.local;"); + var row = resultSet.one(); return Version.parse(row.getString(0)); } diff --git a/cassandra/util/src/main/resources/embedded-cassandra.yaml b/cassandra/util/src/main/resources/embedded-cassandra.yaml deleted file mode 100644 index 2db7850c..00000000 --- a/cassandra/util/src/main/resources/embedded-cassandra.yaml +++ /dev/null @@ -1,652 +0,0 @@ -# Cassandra storage config YAML - -# 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. -# -# 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 - -# If you haven't specified num_tokens, or have set it to the default of 1 then -# you should always specify InitialToken when setting up a production -# cluster for the first time, and often when adding capacity later. -# The principle is that each node should be given an equal slice of -# the token ring; see http://wiki.apache.org/cassandra/Operations -# for more details. -# -# If blank, Cassandra will request a token bisecting the range of -# the heaviest-loaded existing node. If there is no load information -# available, such as is the case with a new cluster, it will pick -# a random token, which will lead to hot spots. -initial_token: - -# See http://wiki.apache.org/cassandra/HintedHandoff -hinted_handoff_enabled: false - -# 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 -# throttle in KBs per second, per delivery thread -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 - -# The following setting populates the page cache on memtable flush and compaction -# WARNING: Enable this setting only when the whole node's data fits in memory. -# Defaults to: false -# populate_io_cache_on_flush: false - -# 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. -authenticator: org.apache.cassandra.auth.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: org.apache.cassandra.auth.AllowAllAuthorizer - -# 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 - -# The partitioner is responsible for distributing rows (by key) across -# nodes in the cluster. Any IPartitioner may be used, including your -# own as long as it is on the classpath. Out of the box, Cassandra -# provides org.apache.cassandra.dht.{Murmur3Partitioner, RandomPartitioner -# ByteOrderedPartitioner, OrderPreservingPartitioner (deprecated)}. -# -# - RandomPartitioner distributes rows across the cluster evenly by md5. -# This is the default prior to 1.2 and is retained for compatibility. -# - Murmur3Partitioner is similar to RandomPartioner but uses Murmur3_128 -# Hash Function instead of md5. When in doubt, this is the best option. -# - ByteOrderedPartitioner orders rows lexically by key bytes. BOP allows -# scanning rows in key order, but the ordering can generate hot spots -# for sequential insertion workloads. -# - OrderPreservingPartitioner is an obsolete form of BOP, that stores -# - keys in a less-efficient format and only works with keys that are -# UTF8-encoded Strings. -# - CollatingOPP collates according to EN,US rules rather than lexical byte -# ordering. Use this as an example if you need custom collation. -# -# See http://wiki.apache.org/cassandra/Operations for more on -# partitioners and token selection. -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 - -# Enable / disable CDC functionality on a per-node basis. This modifies the logic used -# for write path allocation rejection (standard: never reject. cdc: reject Mutation -# containing a CDC-enabled table if at space limit in cdc_raw_directory). -cdc_enabled: false - -# CommitLogSegments are moved to this directory on flush if cdc_enabled: true and the -# segment contains mutations for a CDC-enabled table. This should be placed on a -# separate spindle than the data directories. If not set, the default directory is -# $CASSANDRA_HOME/data/cdc_raw. -cdc_raw_directory: target/embeddedCassandra/data/cdc_raw - - -# Directories where Cassandra should store data on disk. Cassandra -# will spread data evenly across them, subject to the granularity of -# the configured compaction strategy. -data_file_directories: - - target/embeddedCassandra/data - -hints_directory: - - target/embeddedCassandra/hints - -# commit log -commitlog_directory: target/embeddedCassandra/commitlog - -# policy for data disk failures: -# stop: shut down gossip and Thrift, leaving the node effectively dead, but -# can still be inspected via JMX. -# 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 - -# 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 - -# Maximum size of the row cache in memory. -# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. -# -# Default value is 0, to disable row caching. -row_cache_size_in_mb: 0 - -# Duration in seconds after which Cassandra should -# safe 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 -# Disabled by default, meaning all keys are going to be saved -# row_cache_keys_to_save: 100 - -# saved caches -saved_caches_directory: target/embeddedCassandra/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 up to -# commitlog_sync_batch_window_in_ms milliseconds for other writes, before -# performing the sync. -# -# commitlog_sync: batch -# commitlog_sync_batch_window_in_ms: 50 -# -# 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: 5000 - -# 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: 8 - -# any class that implements the SeedProvider interface and has a -# constructor that takes a Map of parameters will do. -seed_provider: - # Addresses of hosts that are deemed contact points. - # Cassandra nodes use this list of hosts to find each other and learn - # the topology of the ring. You must change this if you are running - # multiple nodes! - - class_name: org.apache.cassandra.locator.SimpleSeedProvider - parameters: - # seeds is actually a comma-delimited list of addresses. - # Ex: ",," - - seeds: "127.0.0.1" - -# 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. -# -# 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: 4 -concurrent_writes: 4 - -# Total memory to use for memtables. Cassandra will flush the largest -# memtable when this much memory is used. -# If omitted, Cassandra will set it to 1/3 of the heap. -# memtable_total_space_in_mb: 2048 - -# Total space to use for commitlogs. Since commitlog segments are -# mmapped, and hence use up address space, the default size is 32 -# on 32-bit JVMs, and 1024 on 64-bit JVMs. -# -# If space gets above this value (it will round up to the next nearest -# segment multiple), 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. -# commitlog_total_space_in_mb: 4096 - -# 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. If you have a large heap and many data directories, -# you can increase this value for better flush performance. -# By default this will be set to the amount of data directories defined. -#memtable_flush_writers: 1 - -# 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 -storage_port: 7000 - -# SSL port, for encrypted communication. Unused unless enabled in -# encryption_options -ssl_storage_port: 7001 - -# Address 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! -# -# 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 this to 0.0.0.0 is always wrong. -listen_address: localhost - -# 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 - -# 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 -native_transport_port: 9042 -# The minimum and maximum threads for handling requests when the native -# transport is used. They are similar to rpc_min_threads and rpc_max_threads, -# though the defaults differ slightly. -# native_transport_min_threads: 16 -#native_transport_max_threads: 48 - -# Whether to start the thrift rpc server. -start_rpc: false - -# The address to bind the Thrift RPC service to -- clients connect -# here. Unlike ListenAddress above, you _can_ specify 0.0.0.0 here if -# you want Thrift to listen on all interfaces. -# -# Leaving this blank has the same effect it does for ListenAddress, -# (i.e. it will be based on the configured hostname of the node). -rpc_address: localhost -# port for Thrift to listen for clients on -rpc_port: 9160 - -# enable or disable keepalive on rpc connections -rpc_keepalive: true - -# Cassandra provides three 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). -# -# 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 field length). -thrift_framed_transport_size_in_mb: 15 - -# The max length of a thrift message, including all fields and -# internal thrift overhead. -thrift_max_message_length_in_mb: 16 - -# 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: false - -# Add column indexes to a row after its contents reach this size. -# Increase if your column values are large, or if you have a very large -# number of columns. The competing causes are, Cassandra has to -# deserialize this much of the row to read a single column, so you want -# it to be small - at least if you do many partial-row reads - but all -# the index data is read for each access, so you don't want to generate -# that wastefully either. -column_index_size_in_kb: 64 - -# 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 number of cores. -# Uncomment to make compaction mono-threaded, the pre-0.8 default. -#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 - -# 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 - -# How long the coordinator should wait for read operations to complete -read_request_timeout_in_ms: 120000 -# How long the coordinator should wait for seq or index scans to complete -range_request_timeout_in_ms: 120000 -# How long the coordinator should wait for writes to complete -write_request_timeout_in_ms: 120000 -# 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: 120000 -# The default timeout for other, miscellaneous operations -request_timeout_in_ms: 120000 - -# Enable operation timeout information exchange between nodes to accurately -# measure request timeouts, If disabled cassandra will assuming the request -# was forwarded to the replica instantly by the coordinator -# -# Warning: before enabling this property make sure to ntp is installed -# and the times are synchronized between the nodes. -cross_node_timeout: false - -# Enable socket timeout for streaming operation. -# When a timeout occurs during streaming, streaming is retried from the start -# of the current file. This _can_ involve re-streaming an important amount of -# data, so you should avoid setting the value too low. -# Default value is 0, which never timeout streams. -# streaming_socket_timeout_in_ms: 0 - -# 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. -# -# Out of the box, Cassandra provides -# - SimpleSnitch: -# Treats Strategy order as proximity. This improves cache locality -# when disabling read repair, which can further improve throughput. -# Only appropriate for single-datacenter deployments. -# - PropertyFileSnitch: -# Proximity is determined by rack and data center, which are -# explicitly configured in cassandra-topology.properties. -# - GossipingPropertyFileSnitch -# 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. -# - 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 (as it did Facebook's), this is best used -# as an example of writing a custom Snitch class. -# - 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.) -# -# 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 - -# index_interval controls the sampling of entries from the primrary -# row index in terms of space versus time. The larger the interval, -# the smaller and less effective the sampling will be. In technicial -# terms, the interval coresponds to the number of index entries that -# are skipped between taking each sample. All the sampled entries -# must fit in memory. Generally, a value between 128 and 512 here -# coupled with a large key cache size on CFs results in the best trade -# offs. This value is not often changed, however if you have many -# very small rows (many to an OS page), then increasing this will -# often lower memory usage without a impact on performance. -index_interval: 128 - -# 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. -# 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] - # require_client_auth: false - -# enable or disable client/server encryption. -client_encryption_options: - enabled: 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] - -# 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: none - -# 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: true diff --git a/pom.xml b/pom.xml index ba66c224..5ce20450 100644 --- a/pom.xml +++ b/pom.xml @@ -19,6 +19,7 @@ bom + cassandra elasticsearch jdbc jpa @@ -37,6 +38,7 @@ 16 16 1.11.0 + 1.15.3 1.1.3 UTF-8 @@ -92,6 +94,18 @@ + + + + org.testcontainers + testcontainers-bom + ${testcontainers.version} + pom + import + + + +