From 7ab399e278878f92e557d60d853a640c8a9fc8ec Mon Sep 17 00:00:00 2001 From: Mark Paluch Date: Wed, 13 Feb 2019 15:12:28 +0100 Subject: [PATCH] Upgrade to Apache Cassandra 3.11.4 Closes gh-282 --- .travis.yml | 12 +- .../CassandraSecretIntegrationTests.java | 3 +- .../databases/VaultConfigCassandraTests.java | 3 +- .../src/test/resources/cassandra.yaml | 751 +++++++++++++----- 4 files changed, 567 insertions(+), 202 deletions(-) diff --git a/.travis.yml b/.travis.yml index 0d584e99..58a3b970 100644 --- a/.travis.yml +++ b/.travis.yml @@ -32,10 +32,10 @@ before_install: install: - mkdir -p download - - test -f download/apache-cassandra-2.2.8-bin.tar.gz || wget https://archive.apache.org/dist/cassandra/2.2.8/apache-cassandra-2.2.8-bin.tar.gz -O download/apache-cassandra-2.2.8-bin.tar.gz - - tar xzf download/apache-cassandra-2.2.8-bin.tar.gz - - cp -f spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml apache-cassandra-2.2.8/conf - - apache-cassandra-2.2.8/bin/cassandra + - test -f download/apache-cassandra-3.11.4-bin.tar.gz || wget https://archive.apache.org/dist/cassandra/3.11.4/apache-cassandra-3.11.4-bin.tar.gz -O download/apache-cassandra-3.11.4-bin.tar.gz + - tar xzf download/apache-cassandra-3.11.4-bin.tar.gz + - cp -f spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml apache-cassandra-3.11.4/conf + - apache-cassandra-3.11.4/bin/cassandra - src/test/bash/create_certificates.sh - src/test/bash/install_vault.sh - src/test/bash/install_consul.sh @@ -51,12 +51,12 @@ before_script: - |- mongo admin --eval "db.createUser({user: 'springvault', pwd:'springvault', roles:['root']});" - sleep 30 # wait until Cassandra is up - - apache-cassandra-2.2.8/bin/cqlsh localhost -u cassandra -p cassandra -e "CREATE USER 'springvault' WITH PASSWORD 'springvault' SUPERUSER" + - apache-cassandra-3.11.4/bin/cqlsh localhost -u cassandra -p cassandra -e "CREATE USER 'springvault' WITH PASSWORD 'springvault' SUPERUSER" script: mvn clean verify -Pspring,java8 after_script: - - apache-cassandra-2.2.8/bin/nodetool stopdaemon + - apache-cassandra-3.11.4/bin/nodetool stopdaemon - pkill vault - pkill consul diff --git a/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/CassandraSecretIntegrationTests.java b/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/CassandraSecretIntegrationTests.java index 690363f1..c77a8347 100644 --- a/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/CassandraSecretIntegrationTests.java +++ b/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/CassandraSecretIntegrationTests.java @@ -78,10 +78,11 @@ public class CassandraSecretIntegrationTests extends IntegrationTestSupport { VaultOperations vaultOperations = this.vaultRule.prepare().getVaultOperations(); - Map connection = new HashMap<>(); + Map connection = new HashMap<>(); connection.put("hosts", CASSANDRA_HOST); connection.put("username", CASSANDRA_USERNAME); connection.put("password", CASSANDRA_PASSWORD); + connection.put("protocol_version", 3); vaultOperations.write( String.format("%s/config/connection", this.cassandra.getBackend()), diff --git a/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/VaultConfigCassandraTests.java b/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/VaultConfigCassandraTests.java index 16745786..a2047e2e 100644 --- a/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/VaultConfigCassandraTests.java +++ b/spring-cloud-vault-config-databases/src/test/java/org/springframework/cloud/vault/config/databases/VaultConfigCassandraTests.java @@ -92,10 +92,11 @@ public class VaultConfigCassandraTests { VaultOperations vaultOperations = vaultRule.prepare().getVaultOperations(); - Map connection = new HashMap<>(); + Map connection = new HashMap<>(); connection.put("hosts", CASSANDRA_HOST); connection.put("username", CASSANDRA_USERNAME); connection.put("password", CASSANDRA_PASSWORD); + connection.put("protocol_version", 3); vaultOperations.write(String.format("%s/config/connection", "cassandra"), connection); diff --git a/spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml b/spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml index 9930e807..143a456e 100644 --- a/spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml +++ b/spring-cloud-vault-config-databases/src/test/resources/cassandra.yaml @@ -1,4 +1,4 @@ -# Cassandra storage config YAML +# Cassandra storage config YAML # NOTE: # See http://wiki.apache.org/cassandra/StorageConfiguration for @@ -20,36 +20,73 @@ cluster_name: 'Test Cluster' # 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 +# If you already have a cluster with 1 token per node, and wish to migrate to # multiple tokens per node, see http://wiki.apache.org/cassandra/Operations num_tokens: 256 -# initial_token allows you to specify tokens manually. While you can use # it with -# vnodes (num_tokens > 1, above) -- in which case you should provide a -# comma-separated list -- it's primarily used when adding nodes # to legacy clusters +# 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, or contain a list -# of data centers to enable per-datacenter. -# hinted_handoff_enabled: DC1,DC2 +# 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 @@ -60,7 +97,7 @@ batchlog_replay_throttle_in_kb: 1024 # # - AllowAllAuthenticator performs no checks - set it to disable authentication. # - PasswordAuthenticator relies on username/password pairs to authenticate -# users. It keeps usernames and hashed passwords in system_auth.credentials table. +# 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 @@ -71,7 +108,7 @@ authenticator: PasswordAuthenticator # CassandraAuthorizer}. # # - AllowAllAuthorizer allows any action to any user - set it to disable authorization. -# - CassandraAuthorizer stores permissions in system_auth.permissions table. Please +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please # increase system_auth keyspace replication factor if you use this authorizer. #authorizer: CassandraAuthorizer authorizer: CassandraAuthorizer @@ -87,11 +124,11 @@ authorizer: CassandraAuthorizer # increase system_auth keyspace replication factor if you use this role manager. role_manager: CassandraRoleManager -# Validity period for roles cache (fetching permissions can be an -# expensive operation depending on the authorizer). Granted roles are cached for -# authenticated sessions in AuthenticatedUser and after the period specified -# here, become eligible for (async) reload. -# Defaults to 2000, set to 0 to disable. +# 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 @@ -101,7 +138,7 @@ roles_validity_in_ms: 2000 # completes. If roles_validity_in_ms is non-zero, then this must be # also. # Defaults to the same value as roles_validity_in_ms. -# roles_update_interval_in_ms: 1000 +# roles_update_interval_in_ms: 2000 # Validity period for permissions cache (fetching permissions can be an # expensive operation depending on the authorizer, CassandraAuthorizer is @@ -115,7 +152,26 @@ permissions_validity_in_ms: 2000 # completes. If permissions_validity_in_ms is non-zero, then this must be # also. # Defaults to the same value as permissions_validity_in_ms. -# permissions_update_interval_in_ms: 1000 +# 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 @@ -141,28 +197,85 @@ partitioner: org.apache.cassandra.dht.Murmur3Partitioner # If not set, the default directory is $CASSANDRA_HOME/data/commitlog. # commitlog_directory: /var/lib/cassandra/commitlog -# policy for data disk failures: -# die: shut down gossip and client transports and kill the JVM for any fs errors or -# single-sstable errors, so the node can be replaced. -# stop_paranoid: shut down gossip and client transports even for single-sstable errors, -# kill the JVM for errors during startup. -# stop: shut down gossip and client transports, leaving the node effectively dead, but -# can still be inspected via JMX, kill the JVM for errors during startup. -# best_effort: stop using the failed disk and respond to requests based on -# remaining available sstables. This means you WILL see obsolete -# data at CL.ONE! -# ignore: ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +# 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 +# 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 @@ -192,11 +305,14 @@ key_cache_save_period: 14400 # 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 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. @@ -253,8 +369,8 @@ counter_cache_save_period: 7200 # 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." -# +# 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. @@ -267,25 +383,32 @@ counter_cache_save_period: 7200 # # the other option is "periodic" where writes may be acked immediately # and the CommitLog is simply synced every commitlog_sync_period_in_ms -# milliseconds. +# 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. +# 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: +# commitlog_compression: # - class_name: LZ4Compressor # parameters: # - @@ -293,15 +416,15 @@ commitlog_segment_size_in_mb: 32 # 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" + # 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 @@ -318,17 +441,43 @@ concurrent_reads: 32 concurrent_writes: 32 concurrent_counter_writes: 32 -# Total memory to use for sstable-reading buffers. Defaults to -# the smaller of 1/4 of heap or 512MB. +# 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 -# Total permitted memory to use for memtables. Cassandra will stop +# 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 @@ -340,9 +489,15 @@ concurrent_counter_writes: 32 # Specify the way Cassandra allocates and manages memtable memory. # Options are: -# heap_buffers: on heap nio buffers -# offheap_buffers: off heap (direct) nio buffers -# offheap_objects: native memory, eliminating nio buffer heap overhead +# +# 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. @@ -356,16 +511,49 @@ memtable_allocation_type: heap_buffers # # commitlog_total_space_in_mb: 8192 -# This sets the amount of memtable flush writer threads. These will -# be blocked by disk io, and each one will hold a memtable in memory -# while blocked. +# 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_flush_writers defaults to the smaller of (number of disks, -# number of cores), with a minimum of 2 and a maximum of 8. -# -# If your data directories are backed by SSD, you should increase this -# to the number of cores. -#memtable_flush_writers: 8 +# 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 @@ -401,8 +589,7 @@ ssl_storage_port: 7001 # Address or interface to bind to and tell other Cassandra nodes to connect to. # You _must_ change this if you want multiple nodes to be able to communicate! # -# Set listen_address OR listen_interface, not both. Interfaces must correspond -# to a single address, IP aliasing is not supported. +# 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 @@ -411,12 +598,16 @@ ssl_storage_port: 7001 # # 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_address: localhost -# listen_interface: eth0 # listen_interface_prefer_ipv6: false # Address to broadcast to other Cassandra nodes @@ -442,6 +633,14 @@ 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 @@ -449,7 +648,8 @@ native_transport_port: 9042 # 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. +# 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. @@ -466,8 +666,7 @@ start_rpc: false # The address or interface to bind the Thrift RPC service and native transport # server to. # -# Set rpc_address OR rpc_interface, not both. Interfaces must correspond -# to a single address, IP aliasing is not supported. +# 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). @@ -476,13 +675,16 @@ start_rpc: false # set broadcast_rpc_address to a value other than 0.0.0.0. # # For security reasons, you should not expose this port to the internet. Firewall it if needed. -# +rpc_address: localhost + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + # If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address # you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 # address will be used. If true the first ipv6 address will be used. Defaults to false preferring # ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. -rpc_address: localhost -# rpc_interface: eth1 # rpc_interface_prefer_ipv6: false # port for Thrift to listen for clients on @@ -499,16 +701,18 @@ 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). +# 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. +# 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. @@ -537,13 +741,17 @@ rpc_server_type: sync # 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: +# 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 +# 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). @@ -562,41 +770,31 @@ incremental_backups: false 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 +# or dropping of column families. The STRONGLY advised default of true # should be used to provide data safety. If you set this flag to false, you will # lose data on truncation or drop. auto_snapshot: true -# When executing a scan, within or across a partition, we need to keep the -# tombstones seen in memory so we can return them to the coordinator, which -# will use them to make sure other replicas also know about the deleted rows. -# With workloads that generate a lot of tombstones, this can cause performance -# problems and even exaust the server heap. -# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) -# Adjust the thresholds here if you understand the dangers and want to -# scan more tombstones anyway. These thresholds may also be adjusted at runtime -# using the StorageService mbean. -tombstone_warn_threshold: 1000 -tombstone_failure_threshold: 100000 - # Granularity of the collation index of rows within a partition. # Increase if your rows are large, or if you have a very large # number of rows per partition. The competing goals are these: -# 1) a smaller granularity means more index entries are generated -# and looking up rows withing the partition by collation column -# is faster -# 2) but, Cassandra will keep the collation index in memory for hot -# rows (as part of the key cache), so a larger granularity means -# you can cache more hot rows +# +# - 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 - -# Log WARN on any batch size exceeding this value. 5kb per batch by default. -# Caution should be taken on increasing the size of this threshold as it can lead to node instability. -batch_size_warn_threshold_in_kb: 5 - -# Fail any batch exceeding this value. 50kb (10x warn threshold) by default. -batch_size_fail_threshold_in_kb: 50 +# 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 @@ -609,7 +807,7 @@ batch_size_fail_threshold_in_kb: 50 # # 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 @@ -622,12 +820,9 @@ batch_size_fail_threshold_in_kb: 50 # of compaction, including validation compaction. compaction_throughput_mb_per_sec: 16 -# Log a warning when compacting partitions larger than this value -compaction_large_partition_warning_threshold_mb: 100 - # When compacting, the replacement sstable(s) can be opened before they # are completely written, and used in place of the prior sstables for -# any range that has been written. This helps to smoothly transfer reads +# 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 @@ -663,22 +858,28 @@ 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 +# 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 -# Enable socket timeout for streaming operation. -# When a timeout occurs during streaming, streaming is retried from the start -# of the current file. This _can_ involve re-streaming an important amount of -# data, so you should avoid setting the value too low. -# Default value is 3600000, which means streams timeout after an hour. -# streaming_socket_timeout_in_ms: 3600000 +# 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. @@ -686,6 +887,7 @@ cross_node_timeout: false # 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 @@ -694,41 +896,50 @@ cross_node_timeout: false # more than one replica on the same "rack" (which may not actually # be a physical location) # -# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER, -# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS -# ARE PLACED. +# 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. # -# IF THE RACK A REPLICA IS PLACED IN CHANGES AFTER THE REPLICA HAS BEEN -# ADDED TO A RING, THE NODE MUST BE DECOMMISSIONED AND REBOOTSTRAPPED. +# Out of the box, Cassandra provides: # -# Out of the box, Cassandra provides -# - SimpleSnitch: +# SimpleSnitch: # Treats Strategy order as proximity. This can improve cache # locality when disabling read repair. Only appropriate for # single-datacenter deployments. -# - GossipingPropertyFileSnitch +# +# 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: +# +# PropertyFileSnitch: # Proximity is determined by rack and data center, which are # explicitly configured in cassandra-topology.properties. -# - Ec2Snitch: +# +# 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: +# +# 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: +# +# 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 @@ -768,20 +979,26 @@ dynamic_snitch_badness_threshold: 0.1 request_scheduler: org.apache.cassandra.scheduler.NoScheduler # Scheduler Options vary based on the type of scheduler -# NoScheduler - Has no options +# +# 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. +# 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 @@ -795,11 +1012,15 @@ request_scheduler: org.apache.cassandra.scheduler.NoScheduler # request_scheduler_id: keyspace # Enable or disable inter-node encryption -# Default settings are TLS v1, RSA 1024-bit keys (it is imperative that -# users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher -# suite for authentication, key exchange and encryption of the actual data transfers. -# Use the DHE/ECDHE ciphers if running in FIPS 140 compliant mode. -# NOTE: No custom encryption options are enabled at the moment +# 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 @@ -810,41 +1031,49 @@ request_scheduler: org.apache.cassandra.scheduler.NoScheduler # 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 + 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] + enabled: false + # If enabled and optional is set to true encrypted and unencrypted connections are handled. + optional: false + keystore: conf/.keystore + keystore_password: cassandra + # require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] # internode_compression controls whether traffic between nodes is # compressed. -# can be: all - all traffic is compressed -# dc - traffic between different datacenters is compressed -# none - nothing is compressed. -internode_compression: all +# 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, @@ -856,21 +1085,155 @@ inter_dc_tcp_nodelay: false tracetype_query_ttl: 86400 tracetype_repair_ttl: 604800 -# 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 +# 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 2.2, there is no security manager or anything else in place that -# prevents execution of evil code. CASSANDRA-9402 will fix this issue for Cassandra 3.0. -# This will inherently be backwards-incompatible with any 2.2 UDF that perform insecure -# operations such as opening a socket or writing to the filesystem. +# 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