From c0a216a7401610fd8be60f9aeb6c4ee8069e79df Mon Sep 17 00:00:00 2001 From: JianBo He Date: Wed, 15 Mar 2023 10:56:53 +0800 Subject: [PATCH] feat(bridge): support cassandra bridge --- .ci/docker-compose-file/cassandra/Dockerfile | 4 + .../cassandra/Dockerfile-tls | 4 + .../cassandra/cassandra-tls.yaml | 1236 ++++++++++++++++ .../cassandra/cassandra.yaml | 1237 +++++++++++++++++ .../docker-compose-cassandra-tcp.yaml | 27 + .../docker-compose-toxiproxy.yaml | 1 + .ci/docker-compose-file/toxiproxy.json | 12 + apps/emqx_bridge/src/emqx_bridge.erl | 3 +- lib-ee/emqx_ee_bridge/docker-ct | 1 + .../i18n/emqx_ee_bridge_cassa.conf | 72 + lib-ee/emqx_ee_bridge/rebar.config | 1 + lib-ee/emqx_ee_bridge/src/emqx_ee_bridge.erl | 17 +- .../src/emqx_ee_bridge_cassa.erl | 133 ++ .../test/emqx_ee_bridge_cassa_SUITE.erl | 540 +++++++ .../i18n/emqx_ee_connector_cassa.conf | 28 + .../include/emqx_ee_connector.hrl | 1 + .../src/emqx_ee_connector.app.src | 3 +- .../src/emqx_ee_connector_cassa.erl | 415 ++++++ .../test/emqx_ee_connector_cassa_SUITE.erl | 192 +++ scripts/ct/run.sh | 3 + 20 files changed, 3925 insertions(+), 5 deletions(-) create mode 100644 .ci/docker-compose-file/cassandra/Dockerfile create mode 100644 .ci/docker-compose-file/cassandra/Dockerfile-tls create mode 100644 .ci/docker-compose-file/cassandra/cassandra-tls.yaml create mode 100644 .ci/docker-compose-file/cassandra/cassandra.yaml create mode 100644 .ci/docker-compose-file/docker-compose-cassandra-tcp.yaml create mode 100644 lib-ee/emqx_ee_bridge/i18n/emqx_ee_bridge_cassa.conf create mode 100644 lib-ee/emqx_ee_bridge/src/emqx_ee_bridge_cassa.erl create mode 100644 lib-ee/emqx_ee_bridge/test/emqx_ee_bridge_cassa_SUITE.erl create mode 100644 lib-ee/emqx_ee_connector/i18n/emqx_ee_connector_cassa.conf create mode 100644 lib-ee/emqx_ee_connector/src/emqx_ee_connector_cassa.erl create mode 100644 lib-ee/emqx_ee_connector/test/emqx_ee_connector_cassa_SUITE.erl diff --git a/.ci/docker-compose-file/cassandra/Dockerfile b/.ci/docker-compose-file/cassandra/Dockerfile new file mode 100644 index 000000000..f974c1b6f --- /dev/null +++ b/.ci/docker-compose-file/cassandra/Dockerfile @@ -0,0 +1,4 @@ +ARG CASSANDRA_TAG=3.11.6 +FROM cassandra:${CASSANDRA_TAG} +COPY cassandra.yaml /etc/cassandra/cassandra.yaml +CMD ["cassandra", "-f"] diff --git a/.ci/docker-compose-file/cassandra/Dockerfile-tls b/.ci/docker-compose-file/cassandra/Dockerfile-tls new file mode 100644 index 000000000..434584ca6 --- /dev/null +++ b/.ci/docker-compose-file/cassandra/Dockerfile-tls @@ -0,0 +1,4 @@ +ARG CASSANDRA_TAG=3.11.6 +FROM cassandra:${CASSANDRA_TAG} +COPY cassandra-tls.yaml /etc/cassandra/cassandra.yaml +CMD ["cassandra", "-f"] diff --git a/.ci/docker-compose-file/cassandra/cassandra-tls.yaml b/.ci/docker-compose-file/cassandra/cassandra-tls.yaml new file mode 100644 index 000000000..d2d2a5d70 --- /dev/null +++ b/.ci/docker-compose-file/cassandra/cassandra-tls.yaml @@ -0,0 +1,1236 @@ +# Cassandra storage config YAML + +# NOTE: +# See http://wiki.apache.org/cassandra/StorageConfiguration for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# If you already have a cluster with 1 token per node, and wish to migrate to +# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations +num_tokens: 256 + +# 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 + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: PasswordAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: CassandraAuthorizer + +# 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 + +# 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: /var/lib/cassandra/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down 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 + +# commitlog_sync may be either "periodic" or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait +# commitlog_sync_batch_window_in_ms milliseconds between fsyncs. +# This window should be kept short because the writer threads will +# be unable to do extra work while waiting. (You may need to increase +# concurrent_writes for the same reason.) +# +# commitlog_sync: batch +# commitlog_sync_batch_window_in_ms: 2 +# +# the other option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 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 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. 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 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: false +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for 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. +# +# 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. +# +listen_address: localhost + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# 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. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# 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. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: 0.0.0.0 + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# 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 also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# 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: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# 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 + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: before enabling this property make sure to ntp is installed +# and the times are synchronized between the nodes. +cross_node_timeout: false + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero and read_repair_chance is < 1.0, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 0.1 + +# request_scheduler -- Set this to a class that implements +# RequestScheduler, which will schedule incoming client requests +# according to the specific policy. This is useful for multi-tenancy +# with a single Cassandra cluster. +# NOTE: This is specifically for requests from the client and does +# not affect inter node communication. +# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place +# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of +# client requests to a node with a separate queue for each +# request_scheduler_id. The scheduler is further customized by +# request_scheduler_options as described below. +request_scheduler: org.apache.cassandra.scheduler.NoScheduler + +# Scheduler Options vary based on the type of scheduler +# +# NoScheduler +# Has no options +# +# RoundRobin +# throttle_limit +# The throttle_limit is the number of in-flight +# requests per client. Requests beyond +# that limit are queued up until +# running requests can complete. +# The value of 80 here is twice the number of +# concurrent_reads + concurrent_writes. +# default_weight +# default_weight is optional and allows for +# overriding the default which is 1. +# weights +# Weights are optional and will default to 1 or the +# overridden default_weight. The weight translates into how +# many requests are handled during each turn of the +# RoundRobin, based on the scheduler id. +# +# request_scheduler_options: +# throttle_limit: 80 +# default_weight: 5 +# weights: +# Keyspace1: 1 +# Keyspace2: 5 + +# request_scheduler_id -- An identifier based on which to perform +# the request scheduling. Currently the only valid option is keyspace. +# request_scheduler_id: keyspace + +# Enable or disable inter-node encryption +# 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: true + # If enabled and optional is set to true encrypted and unencrypted connections are handled. + optional: true + keystore: /certs/cass.jks + keystore_password: nosecret + require_client_auth: true + # Set trustore and truststore_password if require_client_auth is true + truststore: /certs/truststore.jks + truststore_password: nosecret + # 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 + +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: false + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: true + +# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservationLowering 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 multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than 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. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Back-pressure settings # +# If enabled, the coordinator will apply the back-pressure strategy specified below to each mutation +# sent to replicas, with the aim of reducing pressure on overloaded replicas. +back_pressure_enabled: false +# The back-pressure strategy applied. +# The default implementation, RateBasedBackPressure, takes three arguments: +# high ratio, factor, and flow type, and uses the ratio between incoming mutation responses and outgoing mutation requests. +# If below high ratio, outgoing mutations are rate limited according to the incoming rate decreased by the given factor; +# if above high ratio, the rate limiting is increased by the given factor; +# such factor is usually best configured between 1 and 10, use larger values for a faster recovery +# at the expense of potentially more dropped mutations; +# the rate limiting is applied according to the flow type: if FAST, it's rate limited at the speed of the fastest replica, +# if SLOW at the speed of the slowest one. +# New strategies can be added. Implementors need to implement org.apache.cassandra.net.BackpressureStrategy and +# provide a public constructor accepting a Map. +back_pressure_strategy: + - class_name: org.apache.cassandra.net.RateBasedBackPressure + parameters: + - high_ratio: 0.90 + factor: 5 + flow: FAST + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 diff --git a/.ci/docker-compose-file/cassandra/cassandra.yaml b/.ci/docker-compose-file/cassandra/cassandra.yaml new file mode 100644 index 000000000..6059e9d64 --- /dev/null +++ b/.ci/docker-compose-file/cassandra/cassandra.yaml @@ -0,0 +1,1237 @@ +# Cassandra storage config YAML + +# NOTE: +# See http://wiki.apache.org/cassandra/StorageConfiguration for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# If you already have a cluster with 1 token per node, and wish to migrate to +# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations +num_tokens: 256 + +# 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 + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: AllowAllAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: AllowAllAuthorizer + +# Part of the Authentication & Authorization backend, implementing IRoleManager; used +# to maintain grants and memberships between roles. +# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager, +# which stores role information in the system_auth keyspace. Most functions of the +# IRoleManager require an authenticated login, so unless the configured IAuthenticator +# actually implements authentication, most of this functionality will be unavailable. +# +# - CassandraRoleManager stores role data in the system_auth keyspace. Please +# increase system_auth keyspace replication factor if you use this role manager. +role_manager: CassandraRoleManager + +# 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 + +# 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: /var/lib/cassandra/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down 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 + +# commitlog_sync may be either "periodic" or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait +# commitlog_sync_batch_window_in_ms milliseconds between fsyncs. +# This window should be kept short because the writer threads will +# be unable to do extra work while waiting. (You may need to increase +# concurrent_writes for the same reason.) +# +# commitlog_sync: batch +# commitlog_sync_batch_window_in_ms: 2 +# +# the other option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 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 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. 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 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: false +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for 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. +# +# 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. +# +listen_address: localhost + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# 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. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# 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. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: 0.0.0.0 + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# 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 also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# 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: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# 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 + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: before enabling this property make sure to ntp is installed +# and the times are synchronized between the nodes. +cross_node_timeout: false + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero and read_repair_chance is < 1.0, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 0.1 + +# request_scheduler -- Set this to a class that implements +# RequestScheduler, which will schedule incoming client requests +# according to the specific policy. This is useful for multi-tenancy +# with a single Cassandra cluster. +# NOTE: This is specifically for requests from the client and does +# not affect inter node communication. +# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place +# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of +# client requests to a node with a separate queue for each +# request_scheduler_id. The scheduler is further customized by +# request_scheduler_options as described below. +request_scheduler: org.apache.cassandra.scheduler.NoScheduler + +# Scheduler Options vary based on the type of scheduler +# +# NoScheduler +# Has no options +# +# RoundRobin +# throttle_limit +# The throttle_limit is the number of in-flight +# requests per client. Requests beyond +# that limit are queued up until +# running requests can complete. +# The value of 80 here is twice the number of +# concurrent_reads + concurrent_writes. +# default_weight +# default_weight is optional and allows for +# overriding the default which is 1. +# weights +# Weights are optional and will default to 1 or the +# overridden default_weight. The weight translates into how +# many requests are handled during each turn of the +# RoundRobin, based on the scheduler id. +# +# request_scheduler_options: +# throttle_limit: 80 +# default_weight: 5 +# weights: +# Keyspace1: 1 +# Keyspace2: 5 + +# request_scheduler_id -- An identifier based on which to perform +# the request scheduling. Currently the only valid option is keyspace. +# request_scheduler_id: keyspace + +# Enable or disable inter-node encryption +# 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 + +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: false + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: true + +# 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 multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than 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. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Back-pressure settings # +# If enabled, the coordinator will apply the back-pressure strategy specified below to each mutation +# sent to replicas, with the aim of reducing pressure on overloaded replicas. +back_pressure_enabled: false +# The back-pressure strategy applied. +# The default implementation, RateBasedBackPressure, takes three arguments: +# high ratio, factor, and flow type, and uses the ratio between incoming mutation responses and outgoing mutation requests. +# If below high ratio, outgoing mutations are rate limited according to the incoming rate decreased by the given factor; +# if above high ratio, the rate limiting is increased by the given factor; +# such factor is usually best configured between 1 and 10, use larger values for a faster recovery +# at the expense of potentially more dropped mutations; +# the rate limiting is applied according to the flow type: if FAST, it's rate limited at the speed of the fastest replica, +# if SLOW at the speed of the slowest one. +# New strategies can be added. Implementors need to implement org.apache.cassandra.net.BackpressureStrategy and +# provide a public constructor accepting a Map. +back_pressure_strategy: + - class_name: org.apache.cassandra.net.RateBasedBackPressure + parameters: + - high_ratio: 0.90 + factor: 5 + flow: FAST + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 diff --git a/.ci/docker-compose-file/docker-compose-cassandra-tcp.yaml b/.ci/docker-compose-file/docker-compose-cassandra-tcp.yaml new file mode 100644 index 000000000..ce0cb4de5 --- /dev/null +++ b/.ci/docker-compose-file/docker-compose-cassandra-tcp.yaml @@ -0,0 +1,27 @@ +version: '3.9' + +services: + cassandra_server: + container_name: cassa_tcp + build: + context: ./cassandra + args: + CASSANDRA_TAG: ${CASSANDRA_TAG} + image: emqx-cassandra + restart: always + environment: + CASSANDRA_BROADCAST_ADDRESS: "1.2.3.4" + CASSANDRA_RPC_ADDRESS: "0.0.0.0" + ports: + - "9042:9042" + command: + - /bin/bash + - -c + - | + /opt/cassandra/bin/cassandra -f -R > /cassandra.log & + /opt/cassandra/bin/cqlsh -e "CREATE KEYSPACE mqtt WITH REPLICATION = { 'class':'SimpleStrategy','replication_factor':1};" + while [[ $$? -ne 0 ]];do sleep 5; /opt/cassandra/bin/cqlsh -e "CREATE KEYSPACE mqtt WITH REPLICATION = { 'class':'SimpleStrategy','replication_factor':1};"; done + /opt/cassandra/bin/cqlsh -e "describe keyspaces;" + tail -f /cassandra.log + networks: + - emqx_bridge diff --git a/.ci/docker-compose-file/docker-compose-toxiproxy.yaml b/.ci/docker-compose-file/docker-compose-toxiproxy.yaml index 3dd30af52..dd8b91252 100644 --- a/.ci/docker-compose-file/docker-compose-toxiproxy.yaml +++ b/.ci/docker-compose-file/docker-compose-toxiproxy.yaml @@ -19,6 +19,7 @@ services: - 15433:5433 - 16041:6041 - 18000:8000 + - 19042:9042 command: - "-host=0.0.0.0" - "-config=/config/toxiproxy.json" diff --git a/.ci/docker-compose-file/toxiproxy.json b/.ci/docker-compose-file/toxiproxy.json index 6188eab17..79589c14a 100644 --- a/.ci/docker-compose-file/toxiproxy.json +++ b/.ci/docker-compose-file/toxiproxy.json @@ -53,5 +53,17 @@ "listen": "0.0.0.0:8000", "upstream": "dynamo:8000", "enabled": true + }, + { + "name": "cassa_tcp", + "listen": "0.0.0.0:9042", + "upstream": "cassa_tcp:9042", + "enabled": true + }, + { + "name": "cassa_tls", + "listen": "0.0.0.0:9043", + "upstream": "cassa_tls:9043", + "enabled": false } ] diff --git a/apps/emqx_bridge/src/emqx_bridge.erl b/apps/emqx_bridge/src/emqx_bridge.erl index ddf24d380..4b51a32b1 100644 --- a/apps/emqx_bridge/src/emqx_bridge.erl +++ b/apps/emqx_bridge/src/emqx_bridge.erl @@ -63,7 +63,8 @@ T == timescale; T == matrix; T == tdengine; - T == dynamo + T == dynamo; + T == cassandra ). load() -> diff --git a/lib-ee/emqx_ee_bridge/docker-ct b/lib-ee/emqx_ee_bridge/docker-ct index ac1728ad2..34ae9111f 100644 --- a/lib-ee/emqx_ee_bridge/docker-ct +++ b/lib-ee/emqx_ee_bridge/docker-ct @@ -10,3 +10,4 @@ pgsql tdengine clickhouse dynamo +cassandra diff --git a/lib-ee/emqx_ee_bridge/i18n/emqx_ee_bridge_cassa.conf b/lib-ee/emqx_ee_bridge/i18n/emqx_ee_bridge_cassa.conf new file mode 100644 index 000000000..3e9a9845e --- /dev/null +++ b/lib-ee/emqx_ee_bridge/i18n/emqx_ee_bridge_cassa.conf @@ -0,0 +1,72 @@ +emqx_ee_bridge_cassa { + + local_topic { + desc { + en: """The MQTT topic filter to be forwarded to Cassandra. All MQTT 'PUBLISH' messages with the topic +matching the local_topic will be forwarded.
+NOTE: if this bridge is used as the action of a rule (EMQX rule engine), and also local_topic is +configured, then both the data got from the rule and the MQTT messages that match local_topic +will be forwarded.""" + zh: """发送到 'local_topic' 的消息都会转发到 Cassandra。
+注意：如果这个 Bridge 被用作规则（EMQX 规则引擎）的输出，同时也配置了 'local_topic' ，那么这两部分的消息都会被转发。""" + } + label { + en: "Local Topic" + zh: "本地 Topic" + } + } + + sql_template { + desc { + en: """SQL Template""" + zh: """SQL 模板""" + } + label { + en: "SQL Template" + zh: "SQL 模板" + } + } + config_enable { + desc { + en: """Enable or disable this bridge""" + zh: """启用/禁用桥接""" + } + label { + en: "Enable Or Disable Bridge" + zh: "启用/禁用桥接" + } + } + + desc_config { + desc { + en: """Configuration for an Cassandra bridge.""" + zh: """Cassandra 桥接配置""" + } + label: { + en: "Cassandra Bridge Configuration" + zh: "Cassandra 桥接配置" + } + } + + desc_type { + desc { + en: """The Bridge Type""" + zh: """Bridge 类型""" + } + label { + en: "Bridge Type" + zh: "桥接类型" + } + } + + desc_name { + desc { + en: """Bridge name.""" + zh: """桥接名字""" + } + label { + en: "Bridge Name" + zh: "桥接名字" + } + } +} diff --git a/lib-ee/emqx_ee_bridge/rebar.config b/lib-ee/emqx_ee_bridge/rebar.config index fa6dd560e..ba9ae07aa 100644 --- a/lib-ee/emqx_ee_bridge/rebar.config +++ b/lib-ee/emqx_ee_bridge/rebar.config @@ -3,6 +3,7 @@ , {kafka_protocol, {git, "https://github.com/kafka4beam/kafka_protocol.git", {tag, "4.1.2"}}} , {brod_gssapi, {git, "https://github.com/kafka4beam/brod_gssapi.git", {tag, "v0.1.0-rc1"}}} , {brod, {git, "https://github.com/kafka4beam/brod.git", {tag, "3.16.7"}}} + , {ecql, {git, "https://github.com/emqx/ecql.git", {tag, "v0.4.2"}}} , {emqx_connector, {path, "../../apps/emqx_connector"}} , {emqx_resource, {path, "../../apps/emqx_resource"}} , {emqx_bridge, {path, "../../apps/emqx_bridge"}} diff --git a/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge.erl b/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge.erl index b5c656291..d89dc0bcc 100644 --- a/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge.erl +++ b/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge.erl @@ -31,7 +31,8 @@ api_schemas(Method) -> ref(emqx_ee_bridge_matrix, Method), ref(emqx_ee_bridge_tdengine, Method), ref(emqx_ee_bridge_clickhouse, Method), - ref(emqx_ee_bridge_dynamo, Method) + ref(emqx_ee_bridge_dynamo, Method), + ref(emqx_ee_bridge_cassa, Method) ]. schema_modules() -> @@ -48,7 +49,8 @@ schema_modules() -> emqx_ee_bridge_matrix, emqx_ee_bridge_tdengine, emqx_ee_bridge_clickhouse, - emqx_ee_bridge_dynamo + emqx_ee_bridge_dynamo, + emqx_ee_bridge_cassa ]. examples(Method) -> @@ -81,7 +83,8 @@ resource_type(timescale) -> emqx_connector_pgsql; resource_type(matrix) -> emqx_connector_pgsql; resource_type(tdengine) -> emqx_ee_connector_tdengine; resource_type(clickhouse) -> emqx_ee_connector_clickhouse; -resource_type(dynamo) -> emqx_ee_connector_dynamo. +resource_type(dynamo) -> emqx_ee_connector_dynamo; +resource_type(cassandra) -> emqx_ee_connector_cassa. fields(bridges) -> [ @@ -132,6 +135,14 @@ fields(bridges) -> desc => <<"Dynamo Bridge Config">>, required => false } + )}, + {cassandra, + mk( + hoconsc:map(name, ref(emqx_ee_bridge_cassa, "config")), + #{ + desc => <<"Cassandra Bridge Config">>, + required => false + } )} ] ++ mongodb_structs() ++ influxdb_structs() ++ redis_structs() ++ pgsql_structs() ++ clickhouse_structs(). diff --git a/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge_cassa.erl b/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge_cassa.erl new file mode 100644 index 000000000..295d2c3b5 --- /dev/null +++ b/lib-ee/emqx_ee_bridge/src/emqx_ee_bridge_cassa.erl @@ -0,0 +1,133 @@ +%%-------------------------------------------------------------------- +%% Copyright (c) 2023 EMQ Technologies Co., Ltd. All Rights Reserved. +%%-------------------------------------------------------------------- +-module(emqx_ee_bridge_cassa). + +-include_lib("typerefl/include/types.hrl"). +-include_lib("hocon/include/hoconsc.hrl"). +-include_lib("emqx_bridge/include/emqx_bridge.hrl"). +-include_lib("emqx_resource/include/emqx_resource.hrl"). + +-import(hoconsc, [mk/2, enum/1, ref/2]). + +%% schema examples +-export([ + conn_bridge_examples/1, + values/2, + fields/2 +]). + +%% schema +-export([ + namespace/0, + roots/0, + fields/1, + desc/1 +]). + +-define(DEFAULT_SQL, << + "insert into mqtt_msg(topic, msgid, sender, qos, payload, arrived, retain) " + "values (${topic}, ${id}, ${clientid}, ${qos}, ${payload}, ${timestamp}, ${flags.retain})" +>>). + +%%-------------------------------------------------------------------- +%% schema examples + +conn_bridge_examples(Method) -> + [ + #{ + <<"cassa">> => #{ + summary => <<"Cassandra Bridge">>, + value => values(Method, cassandra) + } + } + ]. + +values(get, Type) -> + maps:merge(values(post, Type), ?METRICS_EXAMPLE); +values(post, Type) -> + #{ + enable => true, + type => Type, + name => <<"foo">>, + servers => <<"127.0.0.1:9042">>, + keyspace => <<"mqtt">>, + pool_size => 8, + username => <<"root">>, + password => <<"public">>, + sql => ?DEFAULT_SQL, + local_topic => <<"local/topic/#">>, + resource_opts => #{ + worker_pool_size => 8, + health_check_interval => ?HEALTHCHECK_INTERVAL_RAW, + auto_restart_interval => ?AUTO_RESTART_INTERVAL_RAW, + batch_size => ?DEFAULT_BATCH_SIZE, + batch_time => ?DEFAULT_BATCH_TIME, + query_mode => sync, + max_queue_bytes => ?DEFAULT_QUEUE_SIZE + } + }; +values(put, Type) -> + values(post, Type). + +%%-------------------------------------------------------------------- +%% schema + +namespace() -> "bridge_cassa". + +roots() -> []. + +fields("config") -> + [ + {enable, mk(boolean(), #{desc => ?DESC("config_enable"), default => true})}, + {sql, + mk( + binary(), + #{desc => ?DESC("sql_template"), default => ?DEFAULT_SQL, format => <<"sql">>} + )}, + {local_topic, + mk( + binary(), + #{desc => ?DESC("local_topic"), default => undefined} + )}, + {resource_opts, + mk( + ref(?MODULE, "creation_opts"), + #{ + required => false, + default => #{}, + desc => ?DESC(emqx_resource_schema, <<"resource_opts">>) + } + )} + ] ++ + (emqx_ee_connector_cassa:fields(config) -- + emqx_connector_schema_lib:prepare_statement_fields()); +fields("creation_opts") -> + emqx_resource_schema:fields("creation_opts_sync_only"); +fields("post") -> + fields("post", cassa); +fields("put") -> + fields("config"); +fields("get") -> + emqx_bridge_schema:status_fields() ++ fields("post"). + +fields("post", Type) -> + [type_field(Type), name_field() | fields("config")]. + +desc("config") -> + ?DESC("desc_config"); +desc(Method) when Method =:= "get"; Method =:= "put"; Method =:= "post" -> + ["Configuration for Cassandra using `", string:to_upper(Method), "` method."]; +desc("creation_opts" = Name) -> + emqx_resource_schema:desc(Name); +desc(_) -> + undefined. + +%%-------------------------------------------------------------------- +%% utils + +type_field(Type) -> + {type, mk(enum([Type]), #{required => true, desc => ?DESC("desc_type")})}. + +name_field() -> + {name, mk(binary(), #{required => true, desc => ?DESC("desc_name")})}. diff --git a/lib-ee/emqx_ee_bridge/test/emqx_ee_bridge_cassa_SUITE.erl b/lib-ee/emqx_ee_bridge/test/emqx_ee_bridge_cassa_SUITE.erl new file mode 100644 index 000000000..b509b537b --- /dev/null +++ b/lib-ee/emqx_ee_bridge/test/emqx_ee_bridge_cassa_SUITE.erl @@ -0,0 +1,540 @@ +%%-------------------------------------------------------------------- +%% Copyright (c) 2022-2023 EMQ Technologies Co., Ltd. All Rights Reserved. +%%-------------------------------------------------------------------- + +-module(emqx_ee_bridge_cassa_SUITE). + +-compile(nowarn_export_all). +-compile(export_all). + +-include_lib("eunit/include/eunit.hrl"). +-include_lib("common_test/include/ct.hrl"). +-include_lib("snabbkaffe/include/snabbkaffe.hrl"). + +% SQL definitions +-define(SQL_BRIDGE, + "insert into mqtt_msg_test(topic, payload, arrived) " + "values (${topic}, ${payload}, ${timestamp})" +). +-define(SQL_CREATE_TABLE, + "" + "\n" + "CREATE TABLE mqtt.mqtt_msg_test (\n" + " topic text,\n" + " payload text,\n" + " arrived timestamp,\n" + " PRIMARY KEY (topic)\n" + ");\n" + "" +). +-define(SQL_DROP_TABLE, "DROP TABLE mqtt_msg_test"). +-define(SQL_DELETE, "TRUNCATE mqtt_msg_test"). +-define(SQL_SELECT, "SELECT payload FROM mqtt_msg_test"). + +% DB defaults +-define(CASSA_KEYSPACE, "mqtt"). +-define(CASSA_USERNAME, "root"). +-define(CASSA_PASSWORD, "public"). +-define(BATCH_SIZE, 10). + +%%------------------------------------------------------------------------------ +%% CT boilerplate +%%------------------------------------------------------------------------------ + +all() -> + [ + {group, tcp}, + {group, tls} + ]. + +groups() -> + TCs = emqx_common_test_helpers:all(?MODULE), + NonBatchCases = [t_write_timeout], + [ + {tcp, [ + %{group, with_batch}, + {group, without_batch} + ]}, + {tls, [ + %{group, with_batch}, + {group, without_batch} + ]}, + {with_batch, TCs -- NonBatchCases}, + {without_batch, TCs} + ]. + +init_per_group(tcp, Config) -> + Host = os:getenv("CASSA_TCP_HOST", "toxiproxy"), + Port = list_to_integer(os:getenv("CASSA_TCP_PORT", "9042")), + [ + {cassa_host, Host}, + {cassa_port, Port}, + {enable_tls, false}, + {query_mode, sync}, + {proxy_name, "cassa_tcp"} + | Config + ]; +init_per_group(tls, Config) -> + Host = os:getenv("CASSA_TLS_HOST", "toxiproxy"), + Port = list_to_integer(os:getenv("CASSA_TLS_PORT", "9043")), + [ + {cassa_host, Host}, + {cassa_port, Port}, + {enable_tls, true}, + {query_mode, sync}, + {proxy_name, "cassa_tls"} + | Config + ]; +init_per_group(with_batch, Config0) -> + Config = [{enable_batch, true} | Config0], + common_init(Config); +init_per_group(without_batch, Config0) -> + Config = [{enable_batch, false} | Config0], + common_init(Config); +init_per_group(_Group, Config) -> + Config. + +end_per_group(Group, Config) when + Group == without_batch; Group == without_batch +-> + connect_and_drop_table(Config), + ProxyHost = ?config(proxy_host, Config), + ProxyPort = ?config(proxy_port, Config), + emqx_common_test_helpers:reset_proxy(ProxyHost, ProxyPort), + ok; +end_per_group(_Group, _Config) -> + ok. + +init_per_suite(Config) -> + Config. + +end_per_suite(_Config) -> + emqx_mgmt_api_test_util:end_suite(), + ok = emqx_common_test_helpers:stop_apps([emqx_bridge, emqx_conf]), + ok. + +init_per_testcase(_Testcase, Config) -> + connect_and_clear_table(Config), + delete_bridge(Config), + Config. + +end_per_testcase(_Testcase, Config) -> + ProxyHost = ?config(proxy_host, Config), + ProxyPort = ?config(proxy_port, Config), + emqx_common_test_helpers:reset_proxy(ProxyHost, ProxyPort), + connect_and_clear_table(Config), + ok = snabbkaffe:stop(), + delete_bridge(Config), + ok. + +%%------------------------------------------------------------------------------ +%% Helper fns +%%------------------------------------------------------------------------------ + +common_init(Config0) -> + BridgeType = proplists:get_value(bridge_type, Config0, <<"cassandra">>), + Host = ?config(cassa_host, Config0), + Port = ?config(cassa_port, Config0), + case emqx_common_test_helpers:is_tcp_server_available(Host, Port) of + true -> + % Setup toxiproxy + ProxyHost = os:getenv("PROXY_HOST", "toxiproxy"), + ProxyPort = list_to_integer(os:getenv("PROXY_PORT", "8474")), + emqx_common_test_helpers:reset_proxy(ProxyHost, ProxyPort), + % Ensure EE bridge module is loaded + _ = application:load(emqx_ee_bridge), + _ = emqx_ee_bridge:module_info(), + ok = emqx_common_test_helpers:start_apps([emqx_conf, emqx_bridge]), + emqx_mgmt_api_test_util:init_suite(), + % Connect to cassnadra directly and create the table + connect_and_create_table(Config0), + {Name, CassaConf} = cassa_config(BridgeType, Config0), + Config = + [ + {cassa_config, CassaConf}, + {cassa_bridge_type, BridgeType}, + {cassa_name, Name}, + {proxy_host, ProxyHost}, + {proxy_port, ProxyPort} + | Config0 + ], + Config; + false -> + case os:getenv("IS_CI") of + "yes" -> + throw(no_cassandra); + _ -> + {skip, no_cassandra} + end + end. + +cassa_config(BridgeType, Config) -> + Port = integer_to_list(?config(cassa_port, Config)), + Server = ?config(cassa_host, Config) ++ ":" ++ Port, + Name = atom_to_binary(?MODULE), + BatchSize = + case ?config(enable_batch, Config) of + true -> ?BATCH_SIZE; + false -> 1 + end, + QueryMode = ?config(query_mode, Config), + TlsEnabled = ?config(enable_tls, Config), + ConfigString = + io_lib:format( + "bridges.~s.~s {\n" + " enable = true\n" + " servers = ~p\n" + " keyspace = ~p\n" + " username = ~p\n" + " password = ~p\n" + " sql = ~p\n" + " resource_opts = {\n" + " request_timeout = 500ms\n" + " batch_size = ~b\n" + " query_mode = ~s\n" + " }\n" + " ssl = {\n" + " enable = ~w\n" + " }\n" + "}", + [ + BridgeType, + Name, + Server, + ?CASSA_KEYSPACE, + ?CASSA_USERNAME, + ?CASSA_PASSWORD, + ?SQL_BRIDGE, + BatchSize, + QueryMode, + TlsEnabled + ] + ), + {Name, parse_and_check(ConfigString, BridgeType, Name)}. + +parse_and_check(ConfigString, BridgeType, Name) -> + {ok, RawConf} = hocon:binary(ConfigString, #{format => map}), + hocon_tconf:check_plain(emqx_bridge_schema, RawConf, #{required => false, atom_key => false}), + #{<<"bridges">> := #{BridgeType := #{Name := Config}}} = RawConf, + Config. + +create_bridge(Config) -> + BridgeType = ?config(cassa_bridge_type, Config), + Name = ?config(cassa_name, Config), + PGConfig = ?config(cassa_config, Config), + emqx_bridge:create(BridgeType, Name, PGConfig). + +delete_bridge(Config) -> + BridgeType = ?config(cassa_bridge_type, Config), + Name = ?config(cassa_name, Config), + emqx_bridge:remove(BridgeType, Name). + +create_bridge_http(Params) -> + Path = emqx_mgmt_api_test_util:api_path(["bridges"]), + AuthHeader = emqx_mgmt_api_test_util:auth_header_(), + case emqx_mgmt_api_test_util:request_api(post, Path, "", AuthHeader, Params) of + {ok, Res} -> {ok, emqx_json:decode(Res, [return_maps])}; + Error -> Error + end. + +send_message(Config, Payload) -> + Name = ?config(cassa_name, Config), + BridgeType = ?config(cassa_bridge_type, Config), + BridgeID = emqx_bridge_resource:bridge_id(BridgeType, Name), + emqx_bridge:send_message(BridgeID, Payload). + +query_resource(Config, Request) -> + Name = ?config(cassa_name, Config), + BridgeType = ?config(cassa_bridge_type, Config), + ResourceID = emqx_bridge_resource:resource_id(BridgeType, Name), + emqx_resource:query(ResourceID, Request, #{timeout => 1_000}). + +connect_direct_cassa(Config) -> + Opts = #{ + host => ?config(cassa_host, Config), + port => ?config(cassa_port, Config), + username => ?CASSA_USERNAME, + password => ?CASSA_PASSWORD, + keyspace => ?CASSA_KEYSPACE + }, + + SslOpts = + case ?config(enable_tls, Config) of + true -> + Opts#{ + ssl => true, + ssl_opts => emqx_tls_lib:to_client_opts(#{enable => true}) + }; + false -> + Opts + end, + {ok, Con} = ecql:connect(maps:to_list(SslOpts)), + Con. + +% These funs connect and then stop the cassandra connection +connect_and_create_table(Config) -> + Con = connect_direct_cassa(Config), + {ok, _} = ecql:query(Con, ?SQL_CREATE_TABLE), + ok = ecql:close(Con). + +connect_and_drop_table(Config) -> + Con = connect_direct_cassa(Config), + {ok, _} = ecql:query(Con, ?SQL_DROP_TABLE), + ok = ecql:close(Con). + +connect_and_clear_table(Config) -> + Con = connect_direct_cassa(Config), + ok = ecql:query(Con, ?SQL_DELETE), + ok = ecql:close(Con). + +connect_and_get_payload(Config) -> + Con = connect_direct_cassa(Config), + {ok, {_Keyspace, _ColsSpec, [[Result]]}} = ecql:query(Con, ?SQL_SELECT), + ok = ecql:close(Con), + Result. + +%%------------------------------------------------------------------------------ +%% Testcases +%%------------------------------------------------------------------------------ + +t_setup_via_config_and_publish(Config) -> + ?assertMatch( + {ok, _}, + create_bridge(Config) + ), + Val = integer_to_binary(erlang:unique_integer()), + SentData = #{ + topic => atom_to_binary(?FUNCTION_NAME), + payload => Val, + timestamp => 1668602148000 + }, + ?check_trace( + begin + ?wait_async_action( + ?assertEqual(ok, send_message(Config, SentData)), + #{?snk_kind := cassandra_connector_query_return}, + 10_000 + ), + ?assertMatch( + Val, + connect_and_get_payload(Config) + ), + ok + end, + fun(Trace0) -> + Trace = ?of_kind(cassandra_connector_query_return, Trace0), + case ?config(enable_batch, Config) of + true -> + ?assertMatch([#{result := {_, [ok]}}], Trace); + false -> + ?assertMatch([#{result := ok}], Trace) + end, + ok + end + ), + ok. + +t_setup_via_http_api_and_publish(Config) -> + BridgeType = ?config(cassa_bridge_type, Config), + Name = ?config(cassa_name, Config), + PgsqlConfig0 = ?config(cassa_config, Config), + PgsqlConfig = PgsqlConfig0#{ + <<"name">> => Name, + <<"type">> => BridgeType + }, + ?assertMatch( + {ok, _}, + create_bridge_http(PgsqlConfig) + ), + Val = integer_to_binary(erlang:unique_integer()), + SentData = #{ + topic => atom_to_binary(?FUNCTION_NAME), + payload => Val, + timestamp => 1668602148000 + }, + ?check_trace( + begin + ?wait_async_action( + ?assertEqual(ok, send_message(Config, SentData)), + #{?snk_kind := cassandra_connector_query_return}, + 10_000 + ), + ?assertMatch( + Val, + connect_and_get_payload(Config) + ), + ok + end, + fun(Trace0) -> + Trace = ?of_kind(cassandra_connector_query_return, Trace0), + case ?config(enable_batch, Config) of + true -> + ?assertMatch([#{result := {_, [{ok, 1}]}}], Trace); + false -> + ?assertMatch([#{result := ok}], Trace) + end, + ok + end + ), + ok. + +t_get_status(Config) -> + ?assertMatch( + {ok, _}, + create_bridge(Config) + ), + ProxyPort = ?config(proxy_port, Config), + ProxyHost = ?config(proxy_host, Config), + ProxyName = ?config(proxy_name, Config), + + Name = ?config(cassa_name, Config), + BridgeType = ?config(cassa_bridge_type, Config), + ResourceID = emqx_bridge_resource:resource_id(BridgeType, Name), + + ?assertEqual({ok, connected}, emqx_resource_manager:health_check(ResourceID)), + emqx_common_test_helpers:with_failure(down, ProxyName, ProxyHost, ProxyPort, fun() -> + ?assertMatch( + {ok, Status} when Status =:= disconnected orelse Status =:= connecting, + emqx_resource_manager:health_check(ResourceID) + ) + end), + ok. + +t_create_disconnected(Config) -> + ProxyPort = ?config(proxy_port, Config), + ProxyHost = ?config(proxy_host, Config), + ProxyName = ?config(proxy_name, Config), + ?check_trace( + emqx_common_test_helpers:with_failure(down, ProxyName, ProxyHost, ProxyPort, fun() -> + ?assertMatch({ok, _}, create_bridge(Config)) + end), + fun(Trace) -> + ?assertMatch( + [#{error := {start_pool_failed, _, _}}], + ?of_kind(cassandra_connector_start_failed, Trace) + ), + ok + end + ), + ok. + +t_write_failure(Config) -> + ProxyName = ?config(proxy_name, Config), + ProxyPort = ?config(proxy_port, Config), + ProxyHost = ?config(proxy_host, Config), + QueryMode = ?config(query_mode, Config), + {ok, _} = create_bridge(Config), + Val = integer_to_binary(erlang:unique_integer()), + SentData = #{ + topic => atom_to_binary(?FUNCTION_NAME), + payload => Val, + timestamp => 1668602148000 + }, + ?check_trace( + emqx_common_test_helpers:with_failure(down, ProxyName, ProxyHost, ProxyPort, fun() -> + {_, {ok, _}} = + ?wait_async_action( + case QueryMode of + sync -> + ?assertMatch({error, _}, send_message(Config, SentData)); + async -> + send_message(Config, SentData) + end, + #{?snk_kind := buffer_worker_flush_nack}, + 1_000 + ) + end), + fun(Trace0) -> + ct:pal("trace: ~p", [Trace0]), + Trace = ?of_kind(buffer_worker_flush_nack, Trace0), + ?assertMatch([#{result := {error, _}} | _], Trace), + [#{result := {error, Error}} | _] = Trace, + case Error of + {resource_error, _} -> + ok; + {recoverable_error, disconnected} -> + ok; + _ -> + ct:fail("unexpected error: ~p", [Error]) + end + end + ), + ok. + +%% This test doesn't work with batch enabled since it is not possible +%% to set the timeout directly for batch queries +%% +%% XXX: parameter with request timeout is not supported yet. +%% +%t_write_timeout(Config) -> +% ProxyName = ?config(proxy_name, Config), +% ProxyPort = ?config(proxy_port, Config), +% ProxyHost = ?config(proxy_host, Config), +% {ok, _} = create_bridge(Config), +% Val = integer_to_binary(erlang:unique_integer()), +% SentData = #{payload => Val, timestamp => 1668602148000}, +% Timeout = 1000, +% emqx_common_test_helpers:with_failure(timeout, ProxyName, ProxyHost, ProxyPort, fun() -> +% ?assertMatch( +% {error, {resource_error, #{reason := timeout}}}, +% query_resource(Config, {send_message, SentData, [], Timeout}) +% ) +% end), +% ok. + +t_simple_sql_query(Config) -> + ?assertMatch( + {ok, _}, + create_bridge(Config) + ), + Request = {query, <<"SELECT count(1) AS T FROM system.local">>}, + Result = query_resource(Config, Request), + case ?config(enable_batch, Config) of + true -> ?assertEqual({error, {unrecoverable_error, batch_prepare_not_implemented}}, Result); + false -> ?assertMatch({ok, {<<"system.local">>, _, [[1]]}}, Result) + end, + ok. + +t_missing_data(Config) -> + ?assertMatch( + {ok, _}, + create_bridge(Config) + ), + %% emqx_ee_connector_cassa will send missed data as a `null` atom + %% to ecql driver + Result = send_message(Config, #{}), + ?assertMatch( + %% TODO: match error msgs + {error, {unrecoverable_error, {8704, <<"Expected 8 or 0 byte long for date (4)">>}}}, + Result + ), + ok. + +t_bad_sql_parameter(Config) -> + ?assertMatch( + {ok, _}, + create_bridge(Config) + ), + Request = {query, <<"">>, [bad_parameter]}, + Result = query_resource(Config, Request), + case ?config(enable_batch, Config) of + true -> + ?assertEqual({error, {unrecoverable_error, invalid_request}}, Result); + false -> + ?assertMatch( + {error, {unrecoverable_error, _}}, Result + ) + end, + ok. + +t_nasty_sql_string(Config) -> + ?assertMatch({ok, _}, create_bridge(Config)), + Payload = list_to_binary(lists:seq(1, 127)), + Message = #{ + topic => atom_to_binary(?FUNCTION_NAME), + payload => Payload, + timestamp => erlang:system_time(millisecond) + }, + %% XXX: why ok instead of {ok, AffectedLines}? + ?assertEqual(ok, send_message(Config, Message)), + ?assertEqual(Payload, connect_and_get_payload(Config)). diff --git a/lib-ee/emqx_ee_connector/i18n/emqx_ee_connector_cassa.conf b/lib-ee/emqx_ee_connector/i18n/emqx_ee_connector_cassa.conf new file mode 100644 index 000000000..ecf004722 --- /dev/null +++ b/lib-ee/emqx_ee_connector/i18n/emqx_ee_connector_cassa.conf @@ -0,0 +1,28 @@ +emqx_ee_connector_cassa { + + servers { + desc { + en: """The IPv4 or IPv6 address or the hostname to connect to.
+A host entry has the following form: `Host[:Port][,Host2:Port]`.
+The Cassandra default port 9042 is used if `[:Port]` is not specified.""" + zh: """将要连接的 IPv4 或 IPv6 地址，或者主机名。
+主机名具有以下形式：`Host[:Port][,Host2:Port]`。
+如果未指定 `[:Port]`，则使用 Cassandra 默认端口 9042。""" + } + label: { + en: "Servers" + zh: "Servers" + } + } + + keyspace { + desc { + en: """Keyspace name to connect to.""" + zh: """要连接到的 Keyspace 名称。""" + } + label: { + en: "Keyspace" + zh: "Keyspace" + } + } +} diff --git a/lib-ee/emqx_ee_connector/include/emqx_ee_connector.hrl b/lib-ee/emqx_ee_connector/include/emqx_ee_connector.hrl index 4b6fbbd92..2a91d2524 100644 --- a/lib-ee/emqx_ee_connector/include/emqx_ee_connector.hrl +++ b/lib-ee/emqx_ee_connector/include/emqx_ee_connector.hrl @@ -3,3 +3,4 @@ %%------------------------------------------------------------------- -define(INFLUXDB_DEFAULT_PORT, 8086). +-define(CASSANDRA_DEFAULT_PORT, 9042). diff --git a/lib-ee/emqx_ee_connector/src/emqx_ee_connector.app.src b/lib-ee/emqx_ee_connector/src/emqx_ee_connector.app.src index 6f40f7158..ebe43d8d9 100644 --- a/lib-ee/emqx_ee_connector/src/emqx_ee_connector.app.src +++ b/lib-ee/emqx_ee_connector/src/emqx_ee_connector.app.src @@ -11,7 +11,8 @@ wolff, brod, clickhouse, - erlcloud + erlcloud, + ecql ]}, {env, []}, {modules, []}, diff --git a/lib-ee/emqx_ee_connector/src/emqx_ee_connector_cassa.erl b/lib-ee/emqx_ee_connector/src/emqx_ee_connector_cassa.erl new file mode 100644 index 000000000..d1901e462 --- /dev/null +++ b/lib-ee/emqx_ee_connector/src/emqx_ee_connector_cassa.erl @@ -0,0 +1,415 @@ +%%-------------------------------------------------------------------- +%% Copyright (c) 2023 EMQ Technologies Co., Ltd. All Rights Reserved. +%% +%% Licensed under the Apache License, Version 2.0 (the "License"); +%% you may not use this file except in compliance with the License. +%% You may obtain a copy of the License at +%% +%% http://www.apache.org/licenses/LICENSE-2.0 +%% +%% Unless required by applicable law or agreed to in writing, software +%% distributed under the License is distributed on an "AS IS" BASIS, +%% WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +%% See the License for the specific language governing permissions and +%% limitations under the License. +%%-------------------------------------------------------------------- +-module(emqx_ee_connector_cassa). + +-behaviour(emqx_resource). + +-include_lib("emqx_connector/include/emqx_connector.hrl"). +-include_lib("emqx_ee_connector/include/emqx_ee_connector.hrl"). +-include_lib("typerefl/include/types.hrl"). +-include_lib("emqx/include/logger.hrl"). +-include_lib("hocon/include/hoconsc.hrl"). +-include_lib("snabbkaffe/include/snabbkaffe.hrl"). + +%% schema +-export([roots/0, fields/1]). + +%% callbacks of behaviour emqx_resource +-export([ + callback_mode/0, + on_start/2, + on_stop/2, + on_query/3, + %% TODO: now_supported_now + %%on_batch_query/3, + on_get_status/2 +]). + +%% callbacks of ecpool +-export([ + connect/1, + prepare_sql_to_conn/2 +]). + +%% callbacks for query executing +-export([query/3, prepared_query/3]). + +-export([do_get_status/1]). + +-type prepares() :: #{atom() => binary()}. +-type params_tokens() :: #{atom() => list()}. + +-type state() :: + #{ + poolname := atom(), + prepare_sql := prepares(), + params_tokens := params_tokens(), + %% returned by ecql:prepare/2 + prepare_statement := binary() + }. + +-define(DEFAULT_SERVER_OPTION, #{default_port => ?CASSANDRA_DEFAULT_PORT}). + +%%-------------------------------------------------------------------- +%% schema + +roots() -> + [{config, #{type => hoconsc:ref(?MODULE, config)}}]. + +fields(config) -> + cassandra_db_fields() ++ + emqx_connector_schema_lib:ssl_fields() ++ + emqx_connector_schema_lib:prepare_statement_fields(). + +cassandra_db_fields() -> + [ + {servers, servers()}, + {keyspace, fun keyspace/1}, + {pool_size, fun emqx_connector_schema_lib:pool_size/1}, + {username, fun emqx_connector_schema_lib:username/1}, + {password, fun emqx_connector_schema_lib:password/1}, + {auto_reconnect, fun emqx_connector_schema_lib:auto_reconnect/1} + ]. + +servers() -> + Meta = #{desc => ?DESC("servers")}, + emqx_schema:servers_sc(Meta, ?DEFAULT_SERVER_OPTION). + +keyspace(type) -> binary(); +keyspace(desc) -> ?DESC("keyspace"); +keyspace(required) -> true; +keyspace(_) -> undefined. + +%%-------------------------------------------------------------------- +%% callbacks for emqx_resource + +callback_mode() -> always_sync. + +-spec on_start(binary(), hoconsc:config()) -> {ok, state()} | {error, _}. +on_start( + InstId, + #{ + servers := Servers, + keyspace := Keyspace, + username := Username, + pool_size := PoolSize, + ssl := SSL + } = Config +) -> + {ok, _} = application:ensure_all_started(ecpool), + {ok, _} = application:ensure_all_started(ecql), + + ?SLOG(info, #{ + msg => "starting_cassandra_connector", + connector => InstId, + config => emqx_misc:redact(Config) + }), + + Options = [ + {nodes, emqx_schema:parse_servers(Servers, ?DEFAULT_SERVER_OPTION)}, + {username, Username}, + {password, emqx_secret:wrap(maps:get(password, Config, ""))}, + {keyspace, Keyspace}, + {auto_reconnect, ?AUTO_RECONNECT_INTERVAL}, + {pool_size, PoolSize} + ], + + %% FIXME: how to set tls options + SslOpts = + case maps:get(enable, SSL) of + true -> + [ + %% note: type defined at ecql:option/0 + {ssl, emqx_tls_lib:to_client_opts(SSL)} + ]; + false -> + [] + end, + + PoolName = emqx_plugin_libs_pool:pool_name(InstId), + Prepares = parse_prepare_sql(Config), + InitState = #{poolname => PoolName, prepare_statement => #{}}, + State = maps:merge(InitState, Prepares), + case emqx_plugin_libs_pool:start_pool(PoolName, ?MODULE, Options ++ SslOpts) of + ok -> + {ok, init_prepare(State)}; + {error, Reason} -> + ?tp( + cassandra_connector_start_failed, + #{error => Reason} + ), + {error, Reason} + end. + +on_stop(InstId, #{poolname := PoolName}) -> + ?SLOG(info, #{ + msg => "stopping_cassandra_connector", + connector => InstId + }), + emqx_plugin_libs_pool:stop_pool(PoolName). + +-type request() :: + % emqx_bridge.erl + {send_message, Params :: map()} + % common query + | {query, SQL :: binary()} + | {query, SQL :: binary(), Params :: map()}. + +-spec on_query( + emqx_resource:resource_id(), + request(), + state() +) -> emqx_resource:query_result(). +on_query( + InstId, + Request, + #{poolname := PoolName} = State +) -> + {Type, PreparedKeyOrSQL, Params} = parse_request_to_sql(Request), + ?tp( + debug, + cassandra_connector_received_sql_query, + #{ + connector => InstId, + type => Type, + params => Params, + prepared_key_or_sql => PreparedKeyOrSQL, + state => State + } + ), + {PreparedKeyOrSQL1, Data} = proc_sql_params(Type, PreparedKeyOrSQL, Params, State), + Res = exec_sql_query(InstId, PoolName, Type, PreparedKeyOrSQL1, Data), + handle_result(Res). + +parse_request_to_sql({send_message, Params}) -> + {prepared_query, _Key = send_message, Params}; +parse_request_to_sql({query, SQL}) -> + parse_request_to_sql({query, SQL, #{}}); +parse_request_to_sql({query, SQL, Params}) -> + {query, SQL, Params}. + +proc_sql_params( + prepared_query, + PreparedKey0, + Params, + #{prepare_statement := Prepares, params_tokens := ParamsTokens} +) -> + PreparedKey = maps:get(PreparedKey0, Prepares), + Tokens = maps:get(PreparedKey0, ParamsTokens), + {PreparedKey, assign_type_for_params(emqx_plugin_libs_rule:proc_sql(Tokens, Params))}; +proc_sql_params(query, SQL, Params, _State) -> + {SQL1, Tokens} = emqx_plugin_libs_rule:preproc_sql(SQL, '?'), + {SQL1, assign_type_for_params(emqx_plugin_libs_rule:proc_sql(Tokens, Params))}. + +exec_sql_query(InstId, PoolName, Type, PreparedKey, Data) when + Type == query; Type == prepared_query +-> + case ecpool:pick_and_do(PoolName, {?MODULE, Type, [PreparedKey, Data]}, no_handover) of + {error, Reason} = Result -> + ?tp( + error, + cassandra_connector_query_return, + #{connector => InstId, error => Reason} + ), + Result; + Result -> + ?tp(debug, cassandra_connector_query_return, #{result => Result}), + Result + end. + +on_get_status(_InstId, #{poolname := Pool} = State) -> + case emqx_plugin_libs_pool:health_check_ecpool_workers(Pool, fun ?MODULE:do_get_status/1) of + true -> + case do_check_prepares(State) of + ok -> + connected; + {ok, NState} -> + %% return new state with prepared statements + {connected, NState}; + false -> + %% do not log error, it is logged in prepare_sql_to_conn + connecting + end; + false -> + connecting + end. + +do_get_status(Conn) -> + ok == element(1, ecql:query(Conn, "SELECT count(1) AS T FROM system.local")). + +do_check_prepares(#{prepare_sql := Prepares}) when is_map(Prepares) -> + ok; +do_check_prepares(State = #{poolname := PoolName, prepare_sql := {error, Prepares}}) -> + %% retry to prepare + case prepare_sql(Prepares, PoolName) of + {ok, Sts} -> + %% remove the error + {ok, State#{prepare_sql => Prepares, prepare_statement := Sts}}; + _Error -> + false + end. + +%%-------------------------------------------------------------------- +%% callbacks query + +query(Conn, SQL, Params) -> + ecql:query(Conn, SQL, Params). + +prepared_query(Conn, PreparedKey, Params) -> + ecql:execute(Conn, PreparedKey, Params). + +%%-------------------------------------------------------------------- +%% callbacks for ecpool + +connect(Opts) -> + case ecql:connect(conn_opts(Opts)) of + {ok, _Conn} = Ok -> + Ok; + {error, Reason} -> + {error, Reason} + end. + +conn_opts(Opts) -> + conn_opts(Opts, []). + +conn_opts([], Acc) -> + Acc; +conn_opts([{password, Password} | Opts], Acc) -> + conn_opts(Opts, [{password, emqx_secret:unwrap(Password)} | Acc]); +conn_opts([Opt | Opts], Acc) -> + conn_opts(Opts, [Opt | Acc]). + +%%-------------------------------------------------------------------- +%% prepare + +%% XXX: hardcode +%% note: the `sql` param is passed by emqx_ee_bridge_cassa +parse_prepare_sql(#{sql := SQL}) -> + parse_prepare_sql([{send_message, SQL}], #{}, #{}); +parse_prepare_sql(_) -> + #{prepare_sql => #{}, params_tokens => #{}}. + +parse_prepare_sql([{Key, H} | T], Prepares, Tokens) -> + {PrepareSQL, ParamsTokens} = emqx_plugin_libs_rule:preproc_sql(H, '?'), + parse_prepare_sql( + T, Prepares#{Key => PrepareSQL}, Tokens#{Key => ParamsTokens} + ); +parse_prepare_sql([], Prepares, Tokens) -> + #{ + prepare_sql => Prepares, + params_tokens => Tokens + }. + +init_prepare(State = #{prepare_sql := Prepares, poolname := PoolName}) -> + case maps:size(Prepares) of + 0 -> + State; + _ -> + case prepare_sql(Prepares, PoolName) of + {ok, Sts} -> + State#{prepare_statement := Sts}; + Error -> + ?tp( + error, + cassandra_prepare_sql_failed, + #{prepares => Prepares, reason => Error} + ), + %% mark the prepare_sqlas failed + State#{prepare_sql => {error, Prepares}} + end + end. + +prepare_sql(Prepares, PoolName) when is_map(Prepares) -> + prepare_sql(maps:to_list(Prepares), PoolName); +prepare_sql(Prepares, PoolName) -> + case do_prepare_sql(Prepares, PoolName) of + {ok, _Sts} = Ok -> + %% prepare for reconnect + ecpool:add_reconnect_callback(PoolName, {?MODULE, prepare_sql_to_conn, [Prepares]}), + Ok; + Error -> + Error + end. + +do_prepare_sql(Prepares, PoolName) -> + do_prepare_sql(ecpool:workers(PoolName), Prepares, PoolName, #{}). + +do_prepare_sql([{_Name, Worker} | T], Prepares, PoolName, _LastSts) -> + {ok, Conn} = ecpool_worker:client(Worker), + case prepare_sql_to_conn(Conn, Prepares) of + {ok, Sts} -> + do_prepare_sql(T, Prepares, PoolName, Sts); + Error -> + Error + end; +do_prepare_sql([], _Prepares, _PoolName, LastSts) -> + {ok, LastSts}. + +prepare_sql_to_conn(Conn, Prepares) -> + prepare_sql_to_conn(Conn, Prepares, #{}). + +prepare_sql_to_conn(Conn, [], Statements) when is_pid(Conn) -> {ok, Statements}; +prepare_sql_to_conn(Conn, [{Key, SQL} | PrepareList], Statements) when is_pid(Conn) -> + ?SLOG(info, #{msg => "cassandra_prepare_sql", name => Key, prepare_sql => SQL}), + case ecql:prepare(Conn, Key, SQL) of + {ok, Statement} -> + prepare_sql_to_conn(Conn, PrepareList, Statements#{Key => Statement}); + {error, Error} = Other -> + ?SLOG(error, #{ + msg => "cassandra_prepare_sql_failed", + worker_pid => Conn, + name => Key, + prepare_sql => SQL, + error => Error + }), + Other + end. + +handle_result({error, disconnected}) -> + {error, {recoverable_error, disconnected}}; +handle_result({error, Error}) -> + {error, {unrecoverable_error, Error}}; +handle_result(Res) -> + Res. + +%%-------------------------------------------------------------------- +%% utils + +%% see ecql driver requirements +assign_type_for_params(Params) -> + assign_type_for_params(Params, []). + +assign_type_for_params([], Acc) -> + lists:reverse(Acc); +assign_type_for_params([Param | More], Acc) -> + assign_type_for_params(More, [may_assign_type(Param) | Acc]). + +may_assign_type(V) when is_boolean(V) -> + {int, + if + V -> 1; + true -> 0 + end}; +may_assign_type(V) when is_binary(V); is_list(V); is_atom(V) -> V; +may_assign_type(V) when is_integer(V) -> + %% The max value of signed int(4) is 2147483647 + case V > 2147483647 orelse V < -2147483647 of + true -> {bigint, V}; + false -> {int, V} + end; +may_assign_type(V) when is_float(V) -> {double, V}; +may_assign_type(V) -> + V. diff --git a/lib-ee/emqx_ee_connector/test/emqx_ee_connector_cassa_SUITE.erl b/lib-ee/emqx_ee_connector/test/emqx_ee_connector_cassa_SUITE.erl new file mode 100644 index 000000000..8a001b865 --- /dev/null +++ b/lib-ee/emqx_ee_connector/test/emqx_ee_connector_cassa_SUITE.erl @@ -0,0 +1,192 @@ +%%-------------------------------------------------------------------- +%% Copyright (c) 2020-2023 EMQ Technologies Co., Ltd. All Rights Reserved. +%% +%% Licensed under the Apache License, Version 2.0 (the "License"); +%% you may not use this file except in compliance with the License. +%% You may obtain a copy of the License at +%% http://www.apache.org/licenses/LICENSE-2.0 +%% +%% Unless required by applicable law or agreed to in writing, software +%% distributed under the License is distributed on an "AS IS" BASIS, +%% WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +%% See the License for the specific language governing permissions and +%% limitations under the License. +%%-------------------------------------------------------------------- + +-module(emqx_ee_connector_cassa_SUITE). + +-compile(nowarn_export_all). +-compile(export_all). + +-include("emqx_connector.hrl"). +-include("emqx_ee_connector.hrl"). +-include_lib("eunit/include/eunit.hrl"). +-include_lib("emqx/include/emqx.hrl"). +-include_lib("stdlib/include/assert.hrl"). + +-define(CASSANDRA_HOST, "127.0.0.1"). +-define(CASSANDRA_RESOURCE_MOD, emqx_ee_connector_cassa). + +%% This test SUITE requires a running cassandra instance. If you don't want to +%% bring up the whole CI infrastuctucture with the `scripts/ct/run.sh` script +%% you can create a cassandra instance with the following command (execute it +%% from root of the EMQX directory.). You also need to set ?CASSANDRA_HOST and +%% ?CASSANDRA_PORT to appropriate values. +%% +%% sudo docker run --rm -d --name cassandra --network host cassandra:3.11.14 + +all() -> + emqx_common_test_helpers:all(?MODULE). + +groups() -> + []. + +cassandra_servers() -> + emqx_schema:parse_servers( + iolist_to_binary([?CASSANDRA_HOST, ":", erlang:integer_to_list(?CASSANDRA_DEFAULT_PORT)]), + #{default_port => ?CASSANDRA_DEFAULT_PORT} + ). + +init_per_suite(Config) -> + case + emqx_common_test_helpers:is_tcp_server_available(?CASSANDRA_HOST, ?CASSANDRA_DEFAULT_PORT) + of + true -> + ok = emqx_common_test_helpers:start_apps([emqx_conf]), + ok = emqx_connector_test_helpers:start_apps([emqx_resource]), + {ok, _} = application:ensure_all_started(emqx_connector), + {ok, _} = application:ensure_all_started(emqx_ee_connector), + %% keyspace `mqtt` must be created in advance + {ok, Conn} = + ecql:connect([ + {nodes, cassandra_servers()}, + {username, <<"admin">>}, + {password, <<"public">>}, + {keyspace, "mqtt"} + ]), + ecql:close(Conn), + Config; + false -> + case os:getenv("IS_CI") of + "yes" -> + throw(no_cassandra); + _ -> + {skip, no_cassandra} + end + end. + +end_per_suite(_Config) -> + ok = emqx_common_test_helpers:stop_apps([emqx_conf]), + ok = emqx_connector_test_helpers:stop_apps([emqx_resource]), + _ = application:stop(emqx_connector). + +init_per_testcase(_, Config) -> + Config. + +end_per_testcase(_, _Config) -> + ok. + +%%-------------------------------------------------------------------- +%% cases +%%-------------------------------------------------------------------- + +t_lifecycle(_Config) -> + perform_lifecycle_check( + <<"emqx_connector_cassandra_SUITE">>, + cassandra_config() + ). + +show(X) -> + erlang:display(X), + X. + +show(Label, What) -> + erlang:display({Label, What}), + What. + +perform_lifecycle_check(PoolName, InitialConfig) -> + {ok, #{config := CheckedConfig}} = + emqx_resource:check_config(?CASSANDRA_RESOURCE_MOD, InitialConfig), + {ok, #{ + state := #{poolname := ReturnedPoolName} = State, + status := InitialStatus + }} = + emqx_resource:create_local( + PoolName, + ?CONNECTOR_RESOURCE_GROUP, + ?CASSANDRA_RESOURCE_MOD, + CheckedConfig, + #{} + ), + ?assertEqual(InitialStatus, connected), + % Instance should match the state and status of the just started resource + {ok, ?CONNECTOR_RESOURCE_GROUP, #{ + state := State, + status := InitialStatus + }} = + emqx_resource:get_instance(PoolName), + ?assertEqual({ok, connected}, emqx_resource:health_check(PoolName)), + % % Perform query as further check that the resource is working as expected + (fun() -> + erlang:display({pool_name, PoolName}), + QueryNoParamsResWrapper = emqx_resource:query(PoolName, test_query_no_params()), + ?assertMatch({ok, _}, QueryNoParamsResWrapper) + end)(), + ?assertEqual(ok, emqx_resource:stop(PoolName)), + % Resource will be listed still, but state will be changed and healthcheck will fail + % as the worker no longer exists. + {ok, ?CONNECTOR_RESOURCE_GROUP, #{ + state := State, + status := StoppedStatus + }} = + emqx_resource:get_instance(PoolName), + ?assertEqual(stopped, StoppedStatus), + ?assertEqual({error, resource_is_stopped}, emqx_resource:health_check(PoolName)), + % Resource healthcheck shortcuts things by checking ets. Go deeper by checking pool itself. + ?assertEqual({error, not_found}, ecpool:stop_sup_pool(ReturnedPoolName)), + % Can call stop/1 again on an already stopped instance + ?assertEqual(ok, emqx_resource:stop(PoolName)), + % Make sure it can be restarted and the healthchecks and queries work properly + ?assertEqual(ok, emqx_resource:restart(PoolName)), + % async restart, need to wait resource + timer:sleep(500), + {ok, ?CONNECTOR_RESOURCE_GROUP, #{status := InitialStatus}} = + emqx_resource:get_instance(PoolName), + ?assertEqual({ok, connected}, emqx_resource:health_check(PoolName)), + (fun() -> + QueryNoParamsResWrapper = + emqx_resource:query(PoolName, test_query_no_params()), + ?assertMatch({ok, _}, QueryNoParamsResWrapper) + end)(), + % Stop and remove the resource in one go. + ?assertEqual(ok, emqx_resource:remove_local(PoolName)), + ?assertEqual({error, not_found}, ecpool:stop_sup_pool(ReturnedPoolName)), + % Should not even be able to get the resource data out of ets now unlike just stopping. + ?assertEqual({error, not_found}, emqx_resource:get_instance(PoolName)). + +%%-------------------------------------------------------------------- +%% utils +%%-------------------------------------------------------------------- + +cassandra_config() -> + Config = + #{ + auto_reconnect => true, + keyspace => <<"mqtt">>, + username => <<"default">>, + password => <<"public">>, + pool_size => 8, + servers => iolist_to_binary( + io_lib:format( + "~s:~b", + [ + ?CASSANDRA_HOST, + ?CASSANDRA_DEFAULT_PORT + ] + ) + ) + }, + #{<<"config">> => Config}. + +test_query_no_params() -> + {query, <<"SELECT count(1) AS T FROM system.local">>}. diff --git a/scripts/ct/run.sh b/scripts/ct/run.sh index b3c424ea1..01c148c13 100755 --- a/scripts/ct/run.sh +++ b/scripts/ct/run.sh @@ -168,6 +168,9 @@ for dep in ${CT_DEPS}; do dynamo) FILES+=( '.ci/docker-compose-file/docker-compose-dynamo.yaml' ) ;; + cassandra) + FILES+=( '.ci/docker-compose-file/docker-compose-cassandra-tcp.yaml' ) + ;; *) echo "unknown_ct_dependency $dep" exit 1