From 3c66fe78c9dd03741ea67670ba8e37f1c9e61ec2 Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Thu, 30 Nov 2017 18:10:36 -0800 Subject: [PATCH 1/7] Forked from autopilotpattern/postgres and partially working --- Dockerfile | 70 ++ README.md | 13 + etc/cassandra.yaml.ctmpl | 1232 +++++++++++++++++++++++++++ etc/containerpilot.json5 | 63 ++ etc/jmxremote.access | 1 + etc/jmxremote.password | 1 + etc/onChange.sh | 10 + etc/preStart.sh | 1 + examples/compose/docker-compose.yml | 34 + makefile | 24 + 10 files changed, 1449 insertions(+) create mode 100644 Dockerfile create mode 100644 README.md create mode 100644 etc/cassandra.yaml.ctmpl create mode 100644 etc/containerpilot.json5 create mode 100644 etc/jmxremote.access create mode 100644 etc/jmxremote.password create mode 100644 etc/onChange.sh create mode 100644 etc/preStart.sh create mode 100644 examples/compose/docker-compose.yml create mode 100644 makefile diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..7738e69 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,70 @@ +FROM cassandra:3.11.0 + +# install wget unzip and dig +RUN set -ex \ + && apt-get update \ + && apt-get install -y wget unzip dnsutils \ + && rm -rf /var/lib/apt/lists/* + +# Install Consul +# Releases at https://releases.hashicorp.com/consul +RUN set -ex \ + && export CONSUL_VERSION=1.0.1 \ + && export CONSUL_CHECKSUM=eac5755a1d19e4b93f6ce30caaf7b3bd8add4557b143890b1c07f5614a667a68 \ + && wget --quiet -O /tmp/consul.zip "https://releases.hashicorp.com/consul/${CONSUL_VERSION}/consul_${CONSUL_VERSION}_linux_amd64.zip" \ + && echo "${CONSUL_CHECKSUM} /tmp/consul.zip" | sha256sum -c \ + && unzip /tmp/consul -d /usr/local/bin \ + && rm /tmp/consul.zip \ + && mkdir -p /etc/consul \ + && mkdir -p /var/lib/consul \ + && mkdir /config + +# Install Consul template +# Releases at https://releases.hashicorp.com/consul-template/ +RUN set -ex \ + && export CONSUL_TEMPLATE_VERSION=0.19.0 \ + && export CONSUL_TEMPLATE_CHECKSUM=31dda6ebc7bd7712598c6ac0337ce8fd8c533229887bd58e825757af879c5f9f \ + && wget --quiet -O /tmp/consul-template.zip "https://releases.hashicorp.com/consul-template/${CONSUL_TEMPLATE_VERSION}/consul-template_${CONSUL_TEMPLATE_VERSION}_linux_amd64.zip" \ + && echo "${CONSUL_TEMPLATE_CHECKSUM} /tmp/consul-template.zip" | sha256sum -c \ + && unzip /tmp/consul-template.zip -d /usr/local/bin \ + && rm /tmp/consul-template.zip + +# Add Containerpilot and set its configuration +ENV CONTAINERPILOT /etc/containerpilot.json5 +ENV CONTAINERPILOT_VERSION 3.3.3 + +RUN export CONTAINERPILOT_CHECKSUM=8d680939a8a5c8b27e764d55a78f5e3ae7b42ef4 \ + && export archive=containerpilot-${CONTAINERPILOT_VERSION}.tar.gz \ + && wget --quiet -O /tmp/${archive} \ + "https://github.com/joyent/containerpilot/releases/download/${CONTAINERPILOT_VERSION}/${archive}" \ + && echo "${CONTAINERPILOT_CHECKSUM} /tmp/${archive}" | sha1sum -c \ + && tar zxf /tmp/${archive} -C /usr/local/bin \ + && rm /tmp/${archive} + +COPY etc/containerpilot.json5 /etc/containerpilot.json5 + +COPY etc/preStart.sh /etc/preStart.sh +COPY etc/onChange.sh /etc/onChange.sh +COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl + +### Cassandra-specific setup follows + +ENV LOCAL_JMX=no + +# only the access line actually seems to do anything +RUN echo 'if [ "$LOCAL_JMX" = "no" ]; then' "\n" \ + 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.authenticate=true"' "\n" \ + 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.password.file=/etc/cassandra/jmxremote.password"' "\n" \ + 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.access.file=/etc/cassandra/jmxremote.access"' "\n" \ + 'fi' "\n" >> /etc/cassandra/cassandra-env.sh + +COPY etc/jmxremote.password /etc/cassandra/jmxremote.password +COPY etc/jmxremote.access /etc/cassandra/jmxremote.access + +RUN chown cassandra:cassandra /etc/cassandra/jmxremote.password /etc/cassandra/jmxremote.access \ + && chmod 400 /etc/cassandra/jmxremote.access /etc/cassandra/jmxremote.password \ + && chmod +x /etc/preStart.sh /etc/onChange.sh + +EXPOSE 7000 7001 7199 9042 9160 + +ENTRYPOINT ["/usr/local/bin/containerpilot"] diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b9c17d --- /dev/null +++ b/README.md @@ -0,0 +1,13 @@ +# Autopilot Pattern Cassandra + + +``` +cd examples/compose +docker-compose up -d --scale cassandra=3 +# for a cqlsh shell: +docker-compose exec cassandra cqlsh cassandra + +cqlsh> CREATE KEYSPACE demo WITH replication = {'class': 'NetworkTopologyStrategy', 'datacenter1': 2 }; +USE demo; + +``` \ No newline at end of file diff --git a/etc/cassandra.yaml.ctmpl b/etc/cassandra.yaml.ctmpl new file mode 100644 index 0000000..8308595 --- /dev/null +++ b/etc/cassandra.yaml.ctmpl @@ -0,0 +1,1232 @@ +# 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. +# +# 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: {{ range service "cassandra" }}{{ .Address }},{{ end }} + +# 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: 172.20.0.3 + +# 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: 172.20.0.3 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# Please note that the address on which the native transport is bound is the +# same as the rpc_address. The port however is different and specified below. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests when the native transport is used. +# This is similar to rpc_max_threads though the default differs slightly (and +# there is no native_transport_min_threads, idle threads will always be stopped +# after 30 seconds). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Whether to start the thrift rpc server. +start_rpc: false + +# 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: 172.20.0.3 + +# 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 + +# 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. +# 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/etc/containerpilot.json5 b/etc/containerpilot.json5 new file mode 100644 index 0000000..4148ad1 --- /dev/null +++ b/etc/containerpilot.json5 @@ -0,0 +1,63 @@ +{ + consul: '{{ if .CONSUL_AGENT }}localhost{{ else }}{{ .CONSUL | default "consul"}}{{ end }}:8500', + logging: { + level: "DEBUG", + format: "text" + }, + jobs: [ + {{ if .CONSUL_AGENT }} + { + name: 'consul-agent', + exec: ['/usr/local/bin/consul', 'agent', + '-data-dir=/data', + '-config-dir=/config', + '-log-level=err', + '-rejoin', + '-retry-join', '{{ .CONSUL | default "consul" }}', + '-retry-max', '10', + '-retry-interval', '10s'], + health: { + exec: 'wget -O /dev/null http://localhost:8500', + interval: 10, + ttl: 25 + }, + restarts: 'unlimited' + }, + {{ end }} + { + // without a "when" field this will start first + name: "preStart", + exec: "sh /etc/preStart.sh" + }, + { + name: "cassandra", + exec: "/docker-entrypoint.sh -f", + restarts: "unlimited", + port: 9042, + health: { + exec: "nodetool -u cassandra -pw cassandra status", + interval: 5, + ttl: 15, + timeout: "10s" + }, + when: { + source: "preStart", + once: "exitSuccess", + }, + }, + { + name: 'onChange-cassandra', + exec: 'sh /etc/onChange.sh', + when: { + source: 'watch.cassandra', + each: 'changed' + } + } + ], + watches: [ + { + name: "cassandra", + interval: 5, + } + ] +} diff --git a/etc/jmxremote.access b/etc/jmxremote.access new file mode 100644 index 0000000..6c4e870 --- /dev/null +++ b/etc/jmxremote.access @@ -0,0 +1 @@ +cassandra readwrite diff --git a/etc/jmxremote.password b/etc/jmxremote.password new file mode 100644 index 0000000..3f65fa5 --- /dev/null +++ b/etc/jmxremote.password @@ -0,0 +1 @@ +cassandra cassandra diff --git a/etc/onChange.sh b/etc/onChange.sh new file mode 100644 index 0000000..30aae36 --- /dev/null +++ b/etc/onChange.sh @@ -0,0 +1,10 @@ +#!bin/sh +consul-template -once -template /etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml + +nodetool -u cassandra -pw cassandra stopdaemon + +# TODO: dont stopdaemon unless there are enough other nodes available +# if [ $((`nodetool -u cassandra -pw cassandra status | grep -v $HOSTNAME | grep UN | wc -l`)) -gt 1 ]; then +# nodetool -u cassandra -pw cassandra stopdaemon +# fi + diff --git a/etc/preStart.sh b/etc/preStart.sh new file mode 100644 index 0000000..f23adee --- /dev/null +++ b/etc/preStart.sh @@ -0,0 +1 @@ +echo preStart-cassandra fired diff --git a/examples/compose/docker-compose.yml b/examples/compose/docker-compose.yml new file mode 100644 index 0000000..827325d --- /dev/null +++ b/examples/compose/docker-compose.yml @@ -0,0 +1,34 @@ +version: '2.1' +# Cassandra demonstration of the Autopilot pattern + +services: + cassandra: + build: ../../ + image: autopilotpattern/cassandra:latest + mem_limit: 1g + restart: always + dns: + - 127.0.0.1 + environment: + - CONSUL=consul + - CONSUL_AGENT=1 + links: + - consul:consul + + # Start with a single host which will bootstrap the cluster. + # In production we'll want to use an HA cluster. + consul: + image: autopilotpattern/consul:0.7.2-r0.8 + restart: always + mem_limit: 128m + ports: + - 8500:8500 + dns: + - 127.0.0.1 + command: > + /usr/local/bin/containerpilot + /bin/consul agent -server + -config-dir=/etc/consul + -log-level=err + -bootstrap-expect 1 + -ui-dir /ui diff --git a/makefile b/makefile new file mode 100644 index 0000000..de8475a --- /dev/null +++ b/makefile @@ -0,0 +1,24 @@ +build: + docker-compose \ + -p autopilotpattern \ + -f examples/compose/docker-compose.yml \ + build cassandra + +up: + docker-compose \ + -p autopilotpattern \ + -f examples/compose/docker-compose.yml \ + up + +down: + docker-compose \ + -p autopilotpattern \ + -f examples/compose/docker-compose.yml \ + down --remove-orphans -v + +ps: + docker-compose \ + -p autopilotpattern \ + -f examples/compose/docker-compose.yml \ + ps + From b3d9a0cae1ab21ba4bc9478037fb393c11e02390 Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Mon, 4 Dec 2017 18:34:41 -0800 Subject: [PATCH 2/7] More onChange changes --- Dockerfile | 16 +++-- README.md | 19 ++++++ etc/containerpilot.json5 | 6 +- etc/onChange.py | 58 +++++++++++++++++++ etc/onChange.sh | 10 ---- etc/preStart.py | 2 + etc/preStart.sh | 1 - .../{docker-compose.yml => local-compose.yml} | 15 ++--- examples/triton/docker-compose.yaml | 39 +++++++++++++ examples/triton/setup.sh | 1 + makefile | 38 +++++++----- 11 files changed, 163 insertions(+), 42 deletions(-) create mode 100644 etc/onChange.py delete mode 100644 etc/onChange.sh create mode 100644 etc/preStart.py delete mode 100644 etc/preStart.sh rename examples/compose/{docker-compose.yml => local-compose.yml} (71%) create mode 100644 examples/triton/docker-compose.yaml create mode 100644 examples/triton/setup.sh diff --git a/Dockerfile b/Dockerfile index 7738e69..b0079f2 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,9 +1,15 @@ FROM cassandra:3.11.0 -# install wget unzip and dig +# install wget unzip and dig plus python modules RUN set -ex \ && apt-get update \ - && apt-get install -y wget unzip dnsutils \ + && apt-get install -y wget unzip dnsutils python-dev gcc \ + && wget --quiet -O /tmp/get-pip.py https://bootstrap.pypa.io/get-pip.py \ + && python /tmp/get-pip.py \ + && pip install \ + python-Consul==0.7.2 \ + manta==2.6.0 \ + && rm /tmp/get-pip.py \ && rm -rf /var/lib/apt/lists/* # Install Consul @@ -43,8 +49,8 @@ RUN export CONTAINERPILOT_CHECKSUM=8d680939a8a5c8b27e764d55a78f5e3ae7b42ef4 \ COPY etc/containerpilot.json5 /etc/containerpilot.json5 -COPY etc/preStart.sh /etc/preStart.sh -COPY etc/onChange.sh /etc/onChange.sh +COPY etc/preStart.py /etc/preStart.py +COPY etc/onChange.py /etc/onChange.py COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl ### Cassandra-specific setup follows @@ -63,7 +69,7 @@ COPY etc/jmxremote.access /etc/cassandra/jmxremote.access RUN chown cassandra:cassandra /etc/cassandra/jmxremote.password /etc/cassandra/jmxremote.access \ && chmod 400 /etc/cassandra/jmxremote.access /etc/cassandra/jmxremote.password \ - && chmod +x /etc/preStart.sh /etc/onChange.sh + && chmod +x /etc/preStart.py /etc/onChange.py EXPOSE 7000 7001 7199 9042 9160 diff --git a/README.md b/README.md index 4b9c17d..94db97a 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,24 @@ # Autopilot Pattern Cassandra +A blueprint for running Apache Cassandra using the [Autopilot Pattern](http://autopilotpattern.io/). + +Environment variables: + + - `CASSANDRA_CLUSTER_NAME`: Name of cluster. Cassandra instances can only join a cluster with the + same `CASSANDRA_CLUSTER_NAME`. Changing this to something other than "Test Cluster" + is **strongly recommended**. + - `CASSANDRA_USER`: New user account to create upon cluster initialization. Setting this parameter + to something other than "cassandra" is **strongly recommended**. + - `CASSANDRA_PASSWORD`: password for `CASSANDRA_USER`. + - `CASSANDRA_KEYSPACES`: Comma-seperated list of keyspaces. + - `CASSANDRA_TOPOLOGY`: JSON map describing keyspaces and their respective datacenters and + replication factors, e.g. for a cluster deployed with at least 2 nodes in `us-east-1` and + `us-sw-1` Triton datacenters having a single keyspace named `demo`: + ``` + { "demo": { "us-sw-1": 2 }, { "us-east-1": 2 } } + ``` + +Notes: ``` cd examples/compose diff --git a/etc/containerpilot.json5 b/etc/containerpilot.json5 index 4148ad1..a3537b6 100644 --- a/etc/containerpilot.json5 +++ b/etc/containerpilot.json5 @@ -27,7 +27,7 @@ { // without a "when" field this will start first name: "preStart", - exec: "sh /etc/preStart.sh" + exec: "python /etc/preStart.py" }, { name: "cassandra", @@ -35,7 +35,7 @@ restarts: "unlimited", port: 9042, health: { - exec: "nodetool -u cassandra -pw cassandra status", + exec: "nodetool -u {{ .CASSANDRA_USER }} -pw {{ .CASSANDRA_PASSWORD }} status", interval: 5, ttl: 15, timeout: "10s" @@ -47,7 +47,7 @@ }, { name: 'onChange-cassandra', - exec: 'sh /etc/onChange.sh', + exec: 'python /etc/onChange.py', when: { source: 'watch.cassandra', each: 'changed' diff --git a/etc/onChange.py b/etc/onChange.py new file mode 100644 index 0000000..57df349 --- /dev/null +++ b/etc/onChange.py @@ -0,0 +1,58 @@ +#!/usr/bin/env python +from sys import stderr +from os import environ, listdir +from subprocess import check_output, Popen, PIPE, CalledProcessError + +class termcolor: + HEADER = '\033[95m' + OKBLUE = '\033[94m' + OKGREEN = '\033[92m' + WARNING = '\033[93m' + FAIL = '\033[91m' + END = '\033[0m' + +def die(err): + if isinstance(err, CalledProcessError): + msg = err.output + else + msg = err + + print >> stderr, termcolor.FAIL + err + termcolor.END + exit(1) + +if 'CASSANDRA_USER' not in environ or 'CASSANDRA_PASSWORD' not in environ: + print >> stderr, '{} environment is missing CASSANDRA_USER or CASSANDRA_PASSWORD! {}'.format(termcolor.FAIL, termcolor.END) + exit(1) + +CASSANDRA_USER = environ["CASSANDRA_USER"] +CASSANDRA_PASSWORD = environ["CASSANDRA_PASSWORD"] + +status = "UNKNOWN" +try: + status = check_output([ + "nodetool", "-u", CASSANDRA_USER, "-pw", CASSANDRA_PASSWORD, "status"]) +except CalledProcessError as e: + die(e) + +print "node status: {} {} {}".format(termcolor.OKGREEN, status, termcolor.END) + +try: + check_call([ + "consul-template", "-once", "-template", "/etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml"]) +except CalledProcessError as e: + die(e) + +print "template ", template + +# calling stopdaemon brings down cassandra. +# it should be brought back up by containerpilot and read the new cassandra.yml +stopdaemon = check_output([ + "nodetool", "-u", "cassandra", "-pw", "cassandra", "stopdaemon"]) + +print "stopdaemon result: ", stopdaemon + +# TODO: dont stopdaemon unless there are enough other nodes available +# if [ $((`nodetool -u cassandra -pw cassandra status | grep -v $HOSTNAME | grep UN | wc -l`)) -gt 1 ]; then +# nodetool -u cassandra -pw cassandra stopdaemon +# fi + diff --git a/etc/onChange.sh b/etc/onChange.sh deleted file mode 100644 index 30aae36..0000000 --- a/etc/onChange.sh +++ /dev/null @@ -1,10 +0,0 @@ -#!bin/sh -consul-template -once -template /etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml - -nodetool -u cassandra -pw cassandra stopdaemon - -# TODO: dont stopdaemon unless there are enough other nodes available -# if [ $((`nodetool -u cassandra -pw cassandra status | grep -v $HOSTNAME | grep UN | wc -l`)) -gt 1 ]; then -# nodetool -u cassandra -pw cassandra stopdaemon -# fi - diff --git a/etc/preStart.py b/etc/preStart.py new file mode 100644 index 0000000..21ab3b1 --- /dev/null +++ b/etc/preStart.py @@ -0,0 +1,2 @@ +#!/usr/bin/env python +print "cassandra-preStart complete" diff --git a/etc/preStart.sh b/etc/preStart.sh deleted file mode 100644 index f23adee..0000000 --- a/etc/preStart.sh +++ /dev/null @@ -1 +0,0 @@ -echo preStart-cassandra fired diff --git a/examples/compose/docker-compose.yml b/examples/compose/local-compose.yml similarity index 71% rename from examples/compose/docker-compose.yml rename to examples/compose/local-compose.yml index 827325d..693dbac 100644 --- a/examples/compose/docker-compose.yml +++ b/examples/compose/local-compose.yml @@ -3,15 +3,17 @@ version: '2.1' services: cassandra: - build: ../../ image: autopilotpattern/cassandra:latest - mem_limit: 1g restart: always - dns: - - 127.0.0.1 + mem_limit: 2g + dns: 127.0.0.1 environment: - CONSUL=consul - - CONSUL_AGENT=1 + - CASSANDRA_USER=cassandra + - CASSANDRA_PASSWORD=cassandra + - CASSANDRA_CLUSTER_NAME=Test Cluster + - CASSANDRA_KEYSPACES=demo + - CASSANDRA_TOPOLOGY={"demo":{"datacenter1":1}} links: - consul:consul @@ -23,8 +25,7 @@ services: mem_limit: 128m ports: - 8500:8500 - dns: - - 127.0.0.1 + dns: 127.0.0.1 command: > /usr/local/bin/containerpilot /bin/consul agent -server diff --git a/examples/triton/docker-compose.yaml b/examples/triton/docker-compose.yaml new file mode 100644 index 0000000..62bc8a6 --- /dev/null +++ b/examples/triton/docker-compose.yaml @@ -0,0 +1,39 @@ +version: '2.1' +# Cassandra demonstration of the Autopilot pattern + +services: + cassandra: + image: autopilotpattern/cassandra:latest + restart: always + mem_limit: 4g + network_mode: bridge + labels: + - triton.cns.services=cassandra + environment: + - CONSUL=cassandra-consul.svc.${TRITON_CNS_SEARCH_DOMAIN_PRIVATE} + - CASSANDRA_USER=cassandra + - CASSANDRA_PASSWORD=cassandra + - CASSANDRA_CLUSTER_NAME=Test Cluster + - CASSANDRA_KEYSPACES=demo + - CASSANDRA_TOPOLOGY={"demo":{"datacenter1":1}} + links: + - consul:consul + + # Start with a single host which will bootstrap the cluster. + # In production we'll want to use an HA cluster. + consul: + image: autopilotpattern/consul:0.7.2-r0.8 + restart: always + mem_limit: 128m + network_mode: bridge + ports: + - 8500:8500 + labels: + - triton.cns.services=cassandra-consul + command: > + /usr/local/bin/containerpilot + /bin/consul agent -server + -config-dir=/etc/consul + -log-level=err + -bootstrap-expect 1 + -ui-dir /ui diff --git a/examples/triton/setup.sh b/examples/triton/setup.sh new file mode 100644 index 0000000..a645eb3 --- /dev/null +++ b/examples/triton/setup.sh @@ -0,0 +1 @@ +setup.sh \ No newline at end of file diff --git a/makefile b/makefile index de8475a..7b47f07 100644 --- a/makefile +++ b/makefile @@ -1,24 +1,30 @@ +DC := docker-compose -p autopilotpattern -f examples/compose/local-compose.yml + +.PHONY: * + build: - docker-compose \ - -p autopilotpattern \ - -f examples/compose/docker-compose.yml \ - build cassandra + $(DC) build cassandra up: - docker-compose \ - -p autopilotpattern \ - -f examples/compose/docker-compose.yml \ - up + $(DC) up + +restart-cassandra: + $(DC) stop cassandra && $(DC) rm -vf cassandra && $(DC) build cassandra && $(DC) up cassandra + +consul: + $(DC) up -d consul down: - docker-compose \ - -p autopilotpattern \ - -f examples/compose/docker-compose.yml \ - down --remove-orphans -v + $(DC) down --remove-orphans -v ps: - docker-compose \ - -p autopilotpattern \ - -f examples/compose/docker-compose.yml \ - ps + $(DC) ps + +cqlsh: + $(DC) exec cassandra cqlsh + +pyrepl: + $(DC) exec cassandra env PYTHONSTARTUP=/.pythonrc python +bash: + $(DC) exec cassandra bash From faf4bb05ecd8bcf3e5f8bf57e4c7c13b9898ee04 Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Thu, 7 Dec 2017 18:07:45 -0800 Subject: [PATCH 3/7] Multi-DC peering almost working --- .gitignore | 3 + Dockerfile | 35 +++--- etc/cassandra.yaml.ctmpl | 4 +- etc/containerpilot.json5 | 18 ++- etc/containerpilot_handler.py | 104 +++++++++++++++ etc/containerpilot_handler/__init__.py | 0 etc/containerpilot_handler/cassandra.py | 161 ++++++++++++++++++++++++ etc/containerpilot_handler/storage.py | 32 +++++ etc/containerpilot_handler/utils.py | 89 +++++++++++++ etc/onChange.py | 58 --------- etc/preStart.py | 2 - examples/compose/local-compose.yml | 52 +++++--- examples/triton/setup.sh | 1 - 13 files changed, 453 insertions(+), 106 deletions(-) create mode 100644 .gitignore create mode 100644 etc/containerpilot_handler.py create mode 100644 etc/containerpilot_handler/__init__.py create mode 100644 etc/containerpilot_handler/cassandra.py create mode 100644 etc/containerpilot_handler/storage.py create mode 100644 etc/containerpilot_handler/utils.py delete mode 100644 etc/onChange.py delete mode 100644 etc/preStart.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..d4a80c8 --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +.DS_Store +*.pyc + diff --git a/Dockerfile b/Dockerfile index b0079f2..85a28ff 100644 --- a/Dockerfile +++ b/Dockerfile @@ -3,12 +3,16 @@ FROM cassandra:3.11.0 # install wget unzip and dig plus python modules RUN set -ex \ && apt-get update \ - && apt-get install -y wget unzip dnsutils python-dev gcc \ + && apt-get install --no-install-recommends -y wget unzip dnsutils python-dev gcc \ && wget --quiet -O /tmp/get-pip.py https://bootstrap.pypa.io/get-pip.py \ && python /tmp/get-pip.py \ && pip install \ - python-Consul==0.7.2 \ - manta==2.6.0 \ + # trying to use cqlsh to do this stuff, installing cassandra-driver takes _forever_ + # cassandra-driver==3.12.0 \ + python-Consul==0.7.2 \ + manta==2.6.0 \ + pyyaml==3.12 \ + && apt-get purge -y python-dev gcc \ && rm /tmp/get-pip.py \ && rm -rf /var/lib/apt/lists/* @@ -49,27 +53,18 @@ RUN export CONTAINERPILOT_CHECKSUM=8d680939a8a5c8b27e764d55a78f5e3ae7b42ef4 \ COPY etc/containerpilot.json5 /etc/containerpilot.json5 -COPY etc/preStart.py /etc/preStart.py -COPY etc/onChange.py /etc/onChange.py -COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl - ### Cassandra-specific setup follows -ENV LOCAL_JMX=no - -# only the access line actually seems to do anything -RUN echo 'if [ "$LOCAL_JMX" = "no" ]; then' "\n" \ - 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.authenticate=true"' "\n" \ - 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.password.file=/etc/cassandra/jmxremote.password"' "\n" \ - 'JVM_OPTS="$JVM_OPTS -Dcom.sun.management.jmxremote.access.file=/etc/cassandra/jmxremote.access"' "\n" \ - 'fi' "\n" >> /etc/cassandra/cassandra-env.sh +COPY etc/containerpilot_handler /usr/local/bin/containerpilot_handler +COPY etc/containerpilot_handler.py /usr/local/bin/containerpilot_handler.py +COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl -COPY etc/jmxremote.password /etc/cassandra/jmxremote.password -COPY etc/jmxremote.access /etc/cassandra/jmxremote.access +# disable the automatic seed configuration that enables single-node bootstrapping +# the first line corresponds to "always set self as seed" +# the second line actually inserts CASSANDRA_SEEDS into the cassandra.yaml +RUN sed -ri '/CASSANDRA_SEEDS.*CASSANDRA_BROADCAST_ADDRESS/d' /docker-entrypoint.sh && \ + sed -ri '/sed -ri.*CASSANDRA_SEEDS.*\/cassandra.yaml/d' /docker-entrypoint.sh -RUN chown cassandra:cassandra /etc/cassandra/jmxremote.password /etc/cassandra/jmxremote.access \ - && chmod 400 /etc/cassandra/jmxremote.access /etc/cassandra/jmxremote.password \ - && chmod +x /etc/preStart.py /etc/onChange.py EXPOSE 7000 7001 7199 9042 9160 diff --git a/etc/cassandra.yaml.ctmpl b/etc/cassandra.yaml.ctmpl index 8308595..bebfe7a 100644 --- a/etc/cassandra.yaml.ctmpl +++ b/etc/cassandra.yaml.ctmpl @@ -421,7 +421,9 @@ seed_provider: parameters: # seeds is actually a comma-delimited list of addresses. # Ex: ",," - - seeds: {{ range service "cassandra" }}{{ .Address }},{{ end }} + - seeds: {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds@%s" . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} + +# {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s" . }}{{ $seedKey }}:{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} # For workloads with more data than can fit in memory, Cassandra's # bottleneck will be reads that need to fetch data from diff --git a/etc/containerpilot.json5 b/etc/containerpilot.json5 index a3537b6..cfcb37e 100644 --- a/etc/containerpilot.json5 +++ b/etc/containerpilot.json5 @@ -1,11 +1,10 @@ { - consul: '{{ if .CONSUL_AGENT }}localhost{{ else }}{{ .CONSUL | default "consul"}}{{ end }}:8500', + consul: 'localhost:8500', logging: { level: "DEBUG", - format: "text" + format: "default" }, jobs: [ - {{ if .CONSUL_AGENT }} { name: 'consul-agent', exec: ['/usr/local/bin/consul', 'agent', @@ -23,11 +22,10 @@ }, restarts: 'unlimited' }, - {{ end }} { // without a "when" field this will start first - name: "preStart", - exec: "python /etc/preStart.py" + name: 'cassandra-preStart', + exec: ['python', '/usr/local/bin/containerpilot_handler.py', 'preStart'], }, { name: "cassandra", @@ -41,13 +39,13 @@ timeout: "10s" }, when: { - source: "preStart", - once: "exitSuccess", + source: 'cassandra-preStart', + once: 'exitSuccess', }, }, { - name: 'onChange-cassandra', - exec: 'python /etc/onChange.py', + name: 'cassandra-onChange', + exec: ['python', '/usr/local/bin/containerpilot_handler.py', 'onChange'], when: { source: 'watch.cassandra', each: 'changed' diff --git a/etc/containerpilot_handler.py b/etc/containerpilot_handler.py new file mode 100644 index 0000000..8de03ee --- /dev/null +++ b/etc/containerpilot_handler.py @@ -0,0 +1,104 @@ +#!/usr/bin/env python +from __future__ import print_function +from sys import argv, stderr, path +from consul import Consul +from socket import gethostname +from os.path import exists, isdir + +from containerpilot_handler.cassandra import Cassandra +from containerpilot_handler.utils import resolve_home, resolve_cluster_name, resolve_credentials, resolve_datacenter, resolve_storage, await_leader, log + + +def main(args): + log('containerpilot_handler started') + + CASSANDRA_HOME = resolve_home() + CASSANDRA_USER, CASSANDRA_PASSWORD = resolve_credentials() + consul = Consul() + CASSANDRA_DC = resolve_datacenter(consul) + + storage = resolve_storage() + + await_leader(consul) + + node = Cassandra(consul, storage, CASSANDRA_HOME, CASSANDRA_USER, CASSANDRA_PASSWORD, CASSANDRA_DC, resolve_cluster_name()) + + log('node configuration: {}'.format(node)) + + + current_seeds = node.query_seeds() + + if not node.enough_seeds_exist(current_seeds) and not node.already_registered_as_seed(current_seeds): + log('volunteering as seed node') + node.register_as_seed(current_seeds) + + + if 'preStart' in args: + # render our template in case there are existing seeds + log('rendering configuration during preStart') + + # attempting to render the config immediately can result in our own volunteering being omitted + # TODO: figure out what consul-template config would work like this (and not block indefinitely) + from time import sleep + sleep(1) + + node.render_config() + + # create a lock to track our snapshots + if node.storage is None: + log('no storage configured, skipping snapshots') + else: + _, snapshot_lock = consul.kv.get(node.build_snapshot_key()) + if snapshot_lock is None: + log('FLAG_SNAPSHOT_REQUIRED was missing') + snapshot_set = consul.kv.put(node.build_snapshot_key(), Cassandra.FLAG_SNAPSHOT_REQUIRED, acquire=node.session_id) + if not snapshot_set: + raise ValueError('error occurred while setting FLAG_SNAPSHOT_REQUIRED') + else: + log('FLAG_SNAPSHOT_REQUIRED recorded for {}'.format(node.id)) + + log('preStart complete') + return + + if 'onChange' in args: + + if node.storage is None: + log('no storage configured, skipping snapshots') + else: + tag = node.record_snapshots() + snapshot_dirs = ['{}/data/{}/snapshots/{}'.format(node.home, k, tag) for k in node.list_keyspaces()] + + log('snapshot dirs: {}'.format(str(snapshot_dirs))) + + for d in snapshot_dirs: + if not isdir(d): + log('snapshot directory missing: {}'.format(d)) + + # snapshot_state = node.query_snapshot_state() + # log('snapshot state: {}'.format(snapshot_state)) + + # if snapshot_state is None or snapshot_state == Cassandra.FLAG_SNAPSHOT_REQUIRED: + # log('recording snapshot') + # # node.record_snapshots() + # # node.ship_snapshots() + + log('onChange complete') + return + + +# snapshot_available = node.query_snapshot_state() + + +# current_peers = node.query_peers() + + +# # TODO: dont stopdaemon unless there are enough other nodes available +# # if [ $((`nodetool -u cassandra -pw cassandra status | grep -v $HOSTNAME | grep UN | wc -l`)) -gt 1 ]; then +# # nodetool -u cassandra -pw cassandra stopdaemon +# # fi + +# https://stackoverflow.com/questions/6323860/sibling-package-imports +# Ugly hack to allow absolute import from the root folder +# whatever its name is. Please forgive the heresy. +if __name__ == "__main__": + main(argv[1:]) \ No newline at end of file diff --git a/etc/containerpilot_handler/__init__.py b/etc/containerpilot_handler/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/etc/containerpilot_handler/cassandra.py b/etc/containerpilot_handler/cassandra.py new file mode 100644 index 0000000..5ed4f86 --- /dev/null +++ b/etc/containerpilot_handler/cassandra.py @@ -0,0 +1,161 @@ +from __future__ import print_function +from os import listdir +from sys import stderr +from socket import gethostname, gethostbyname +from datetime import datetime +from containerpilot_handler.utils import log +import yaml +from subprocess import check_output, check_call, STDOUT, PIPE, CalledProcessError + +class Cassandra(object): + + FLAG_SNAPSHOT_REQUIRED = 'SNAPSHOT_REQUIRED' + + def __init__(self, consul, storage, home, user, password, datacenter, cluster_name): + self.id = "cassandra-{}".format(gethostname()) + self.consul = consul + self.storage = storage + self.home = home + self.user = user + self.password = password + self.datacenter = datacenter + self.cluster_name = cluster_name + + self.session_id = self.consul.session.create(self.id, behavior='delete', ttl=120) + + def __str__(self): + return 'Cassandra '.format( + self.id, self.consul, self.storage, self.user, self.datacenter, self.cluster_name, self.session_id) + + def build_seeds_key(self): + return 'cassandra-seeds-{}-{}'.format(self.cluster_name, self.datacenter) + + def build_snapshot_key(self): + return 'cassandra-snapshot-{}-{}'.format(self.datacenter, gethostname()) + + def query_snapshot_state(self): + _, snapshot = self.consul.kv.get(self.build_snapshot_key()) + + if snapshot is None: + return None + + return snapshot['Value'] + + def query_seeds(self): + _, seeds = self.consul.kv.get(self.build_seeds_key()) + if seeds is None: + return None + + return seeds['Value'].split(',') + + def read_saved_seeds(self, should_retry=True): + loaded_conf = None + seed_list = [] + with open('/etc/cassandra/cassandra.yaml', 'r') as conf: + try: + loaded_conf = yaml.load(conf) + except YAMLError as exc: + log('error occurred while reading cassandra configuration:', exc) + return [] + + if loaded_conf is None: + if should_retry: + log('our configuration file was missing!?') + self.render_config() + return self.read_saved_seeds(should_retry=False) + else: + log('config file missing after retry! raising error') + raise ValueError('failed to render and load configuration') + + try: + seed_list = loaded_conf['seed_provider'][0]['parameters'][0] + except KeyError as e: + log('error occurred while accessing configuration file seed list:', e) + + return seed_list + + def enough_seeds_exist(self, seeds): + if seeds is None: + return False + + parsed_seeds = [s.strip() for s in seeds] + return 1 < len(parsed_seeds) + + def already_registered_as_seed(self, seeds): + if seeds is None: + return False + + return gethostbyname(gethostname()) in [s.strip() for s in seeds] + + def register_as_seed(self, seeds): + if seeds is None: + seeds = [] + + own_ip = gethostbyname(gethostname()) + + seeds.append(own_ip) + + registered = self.consul.kv.put(self.build_seeds_key(), ','.join(seeds)) + if not registered: + raise ValueError('Failed to register ourselves as a seed') + + def render_config(self): + log('SO CLOSE') + check_call([ + 'consul-template', '-once', '-template', '/etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml']) + log('template rendered to: {}'.format('/etc/cassandra/cassandra.yaml')) + + def record_snapshots(self): + """ + records a snapshot of all keyspaces tagged with the current UTC datetime + :return the snapshot tag, as ISO8601 UTC (condensed) datetime + """ + if self.storage is None: + return None + + dt = datetime.utcnow().strftime('%Y%m%dT%H%M%S') + + try: + snapshot = check_output([ + 'nodetool', '-u', self.user, '-pw', self.password, 'snapshot', '--tag', dt], + stderr=STDOUT) + log('snapshot result: {}'.format(snapshot)) + except CalledProcessError as e: + log('snapshot failed: {}'.format(e.output)) + + + return dt + + def ship_snapshots(self, snapshot_tag, keyspaces=None): + + zipped_snapshot = None + + if keyspaces is None: + keyspaces = self.list_keyspaces() + + if 0 == len(keyspaces): + raise Exception('no keyspaces to search for snapshots') + + log('shipping snapshots for keyspaces: {}'.format(str(keyspaces))) + + # for ks in keyspaces: + # self.home() + + def list_keyspaces(self): + keyspaces = [] + + try: + keyspace_output = check_output([ + 'cqlsh', '-u', self.user, '-pw', self.password, '--no-color', '-e', 'DESCRIBE KEYSPACES'], + stderr=STDOUT) + + keyspaces = keyspace_output.strip().split() + except CalledProcessError as e: + raise Exception('error occurred while listing keyspaces: {}'.format(e.output)) + + return keyspaces + + def stop(self): + stopdaemon = check_output([ + 'nodetool', '-u', self.user, '-pw', self.password, 'stopdaemon']) + log('stopdaemon result: {}'.format(stopdaemon)) diff --git a/etc/containerpilot_handler/storage.py b/etc/containerpilot_handler/storage.py new file mode 100644 index 0000000..36d6a3a --- /dev/null +++ b/etc/containerpilot_handler/storage.py @@ -0,0 +1,32 @@ +from __future__ import print_function +from abc import ABCMeta, abstractmethod + +class Storage(object): + __metaclass__ = ABCMeta + @abstractmethod + def store(self, path): + pass + @abstractmethod + def load(self, path): + pass + +class Local(Storage): + def __init__(self, base_path): + self.base_path = base_path + + def store(self, path): + pass + + def load(self, path): + pass + +class Manta(Storage): + def __init__(self, base_path, private_key_content): + self.base_path = base_path + self.private_key_content = private_key_content + + def store(self, path): + pass + + def load(self, path): + pass \ No newline at end of file diff --git a/etc/containerpilot_handler/utils.py b/etc/containerpilot_handler/utils.py new file mode 100644 index 0000000..5f13090 --- /dev/null +++ b/etc/containerpilot_handler/utils.py @@ -0,0 +1,89 @@ +from __future__ import print_function +from os import environ +from os.path import exists +from sys import stderr +from time import sleep +from urlparse import urlparse +from consul import Consul, ConsulException +from containerpilot_handler.storage import Local, Manta + +class termcolor: + HEADER = '\033[95m' + OKBLUE = '\033[94m' + OKGREEN = '\033[92m' + WARNING = '\033[93m' + FAIL = '\033[91m' + END = '\033[0m' + +def log(s): + print('HANDLER: {}{}{}'.format(termcolor.OKBLUE, s, termcolor.END)) + +def die(err): + if isinstance(err, Exception): + msg = err.output + else: + msg = err + + print(termcolor.FAIL + err + termcolor.END, file=stderr) + exit(1) + +def resolve_home(): + if 'CASSANDRA_HOME' in environ: + return environ['CASSANDRA_HOME'] + + return '/var/lib/cassandra' + +def resolve_cluster_name(): + if 'CASSANDRA_CLUSTER_NAME' in environ: + return environ['CASSANDRA_CLUSTER_NAME'] + + return 'test' + +def resolve_credentials(): + if 'CASSANDRA_USER' not in environ or 'CASSANDRA_PASSWORD' not in environ: + die('environment is missing CASSANDRA_USER or CASSANDRA_PASSWORD!') + + return environ["CASSANDRA_USER"], environ["CASSANDRA_PASSWORD"] + +def resolve_datacenter(c): + if 'CASSANDRA_DC' in environ: + return environ['CASSANDRA_DC'] + + if not isinstance(c, Consul): + raise ValueError('unexpected type for consul instance when resolving datacenter: {}'.format(type(c))) + + consulAgentInfo = c.agent.self() + + if 'Config' in consulAgentInfo and 'Datacenter' in consulAgentInfo['Config']: + return consulAgentInfo['Config']['Datacenter'] + else: + return None + +def resolve_storage(): + if 'SNAPSHOT_TARGET' not in environ: + return None + + uri = urlparse(environ['SNAPSHOT_TARGET']) + if 'manta' in uri.scheme: + return Manta() + + if environ['SNAPSHOT_TARGET'].startswith('local'): + return Local() + + return None + +def await_leader(consul, max_duration=10, attempts=6): + known_leader = '' + + while known_leader == '' and 0 < attempts: + + try: + known_leader = consul.status.leader() + except ConsulException as e: + log('no leader elected yet', file=stderr) + + sleep(max_duration / attempts) + attempts -= 1 + + if consul.status.leader() == '': + raise Exception('no leader elected in time') diff --git a/etc/onChange.py b/etc/onChange.py deleted file mode 100644 index 57df349..0000000 --- a/etc/onChange.py +++ /dev/null @@ -1,58 +0,0 @@ -#!/usr/bin/env python -from sys import stderr -from os import environ, listdir -from subprocess import check_output, Popen, PIPE, CalledProcessError - -class termcolor: - HEADER = '\033[95m' - OKBLUE = '\033[94m' - OKGREEN = '\033[92m' - WARNING = '\033[93m' - FAIL = '\033[91m' - END = '\033[0m' - -def die(err): - if isinstance(err, CalledProcessError): - msg = err.output - else - msg = err - - print >> stderr, termcolor.FAIL + err + termcolor.END - exit(1) - -if 'CASSANDRA_USER' not in environ or 'CASSANDRA_PASSWORD' not in environ: - print >> stderr, '{} environment is missing CASSANDRA_USER or CASSANDRA_PASSWORD! {}'.format(termcolor.FAIL, termcolor.END) - exit(1) - -CASSANDRA_USER = environ["CASSANDRA_USER"] -CASSANDRA_PASSWORD = environ["CASSANDRA_PASSWORD"] - -status = "UNKNOWN" -try: - status = check_output([ - "nodetool", "-u", CASSANDRA_USER, "-pw", CASSANDRA_PASSWORD, "status"]) -except CalledProcessError as e: - die(e) - -print "node status: {} {} {}".format(termcolor.OKGREEN, status, termcolor.END) - -try: - check_call([ - "consul-template", "-once", "-template", "/etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml"]) -except CalledProcessError as e: - die(e) - -print "template ", template - -# calling stopdaemon brings down cassandra. -# it should be brought back up by containerpilot and read the new cassandra.yml -stopdaemon = check_output([ - "nodetool", "-u", "cassandra", "-pw", "cassandra", "stopdaemon"]) - -print "stopdaemon result: ", stopdaemon - -# TODO: dont stopdaemon unless there are enough other nodes available -# if [ $((`nodetool -u cassandra -pw cassandra status | grep -v $HOSTNAME | grep UN | wc -l`)) -gt 1 ]; then -# nodetool -u cassandra -pw cassandra stopdaemon -# fi - diff --git a/etc/preStart.py b/etc/preStart.py deleted file mode 100644 index 21ab3b1..0000000 --- a/etc/preStart.py +++ /dev/null @@ -1,2 +0,0 @@ -#!/usr/bin/env python -print "cassandra-preStart complete" diff --git a/examples/compose/local-compose.yml b/examples/compose/local-compose.yml index 693dbac..7c860d2 100644 --- a/examples/compose/local-compose.yml +++ b/examples/compose/local-compose.yml @@ -3,33 +3,57 @@ version: '2.1' services: cassandra: + build: ../../ image: autopilotpattern/cassandra:latest restart: always mem_limit: 2g dns: 127.0.0.1 + # uncomment the following lines for more rapid development + volumes: + - ../../etc/containerpilot_handler:/usr/local/bin/containerpilot_handler + - ../../etc/containerpilot_handler.py:/usr/local/bin/containerpilot_handler.py + - ../../etc/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml.ctmpl + - ../../tmp:/tmp/snapshots environment: - - CONSUL=consul + - CONSUL=consuldc1 - CASSANDRA_USER=cassandra - CASSANDRA_PASSWORD=cassandra - - CASSANDRA_CLUSTER_NAME=Test Cluster + - CASSANDRA_CLUSTER_NAME=demo - CASSANDRA_KEYSPACES=demo - CASSANDRA_TOPOLOGY={"demo":{"datacenter1":1}} + - CASSANDRA_ENDPOINT_SNITCH=SimpleSnitch + - SNAPSHOT_TARGET=file:///tmp/snapshots + # the following options pertain to multi-datacenter deployments + # - CASSANDRA_ENDPOINT_SNITCH=GossipingPropertyFileSnitch + # - CASSANDRA_DC= + # - CASSANDRA_RACK= links: - - consul:consul + - consuldc1:consul - # Start with a single host which will bootstrap the cluster. - # In production we'll want to use an HA cluster. - consul: - image: autopilotpattern/consul:0.7.2-r0.8 + consuldc1: + build: . + image: autopilotpattern/consul:${TAG:-latest} restart: always mem_limit: 128m ports: - - 8500:8500 - dns: 127.0.0.1 + - 8500 + environment: + - CONSUL=consuldc1 + - CONSUL_DATACENTER_NAME=dc1 + command: > + /usr/local/bin/containerpilot + + consuldc2: + image: autopilotpattern/consul:${TAG:-latest} + restart: always + mem_limit: 128m + ports: + - 8500 + environment: + - CONSUL=consuldc2 + - CONSUL_DATACENTER_NAME=dc2 + - CONSUL_RETRY_JOIN_WAN="consuldc1" command: > /usr/local/bin/containerpilot - /bin/consul agent -server - -config-dir=/etc/consul - -log-level=err - -bootstrap-expect 1 - -ui-dir /ui + links: + - consuldc1 diff --git a/examples/triton/setup.sh b/examples/triton/setup.sh index a645eb3..e69de29 100644 --- a/examples/triton/setup.sh +++ b/examples/triton/setup.sh @@ -1 +0,0 @@ -setup.sh \ No newline at end of file From da0e66ba2b3eab58910407c8f10b5f5fe9a7d0cb Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Thu, 7 Dec 2017 18:22:58 -0800 Subject: [PATCH 4/7] Fix seeds key format --- etc/cassandra.yaml.ctmpl | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/etc/cassandra.yaml.ctmpl b/etc/cassandra.yaml.ctmpl index bebfe7a..e24c53c 100644 --- a/etc/cassandra.yaml.ctmpl +++ b/etc/cassandra.yaml.ctmpl @@ -421,9 +421,10 @@ seed_provider: parameters: # seeds is actually a comma-delimited list of addresses. # Ex: ",," - - seeds: {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds@%s" . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} + {{ $clusterName := env "CASSANDRA_CLUSTER_NAME" }} + - seeds: {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s-%s@%s" $clusterName . . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} -# {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s" . }}{{ $seedKey }}:{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} +# {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s-%s@%s" $clusterName . . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} # For workloads with more data than can fit in memory, Cassandra's # bottleneck will be reads that need to fetch data from From 156ac19c9e5a829398eef627084e6e0749120819 Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Fri, 8 Dec 2017 16:52:40 -0800 Subject: [PATCH 5/7] Preventing every node from bootstrapping itself. One node can grab the seeds lock at a time and all others will render their configs to include the seed node (even if it is still bootstrapping) --- Dockerfile | 4 +-- etc/containerpilot_handler.py | 21 +++++++++++----- etc/containerpilot_handler/cassandra.py | 33 ++++++++++++++++++++----- makefile | 11 +++++++-- 4 files changed, 53 insertions(+), 16 deletions(-) diff --git a/Dockerfile b/Dockerfile index 85a28ff..65a1125 100644 --- a/Dockerfile +++ b/Dockerfile @@ -41,9 +41,9 @@ RUN set -ex \ # Add Containerpilot and set its configuration ENV CONTAINERPILOT /etc/containerpilot.json5 -ENV CONTAINERPILOT_VERSION 3.3.3 +ENV CONTAINERPILOT_VERSION 3.6.1 -RUN export CONTAINERPILOT_CHECKSUM=8d680939a8a5c8b27e764d55a78f5e3ae7b42ef4 \ +RUN export CONTAINERPILOT_CHECKSUM=57857530356708e9e8672d133b3126511fb785ab \ && export archive=containerpilot-${CONTAINERPILOT_VERSION}.tar.gz \ && wget --quiet -O /tmp/${archive} \ "https://github.com/joyent/containerpilot/releases/download/${CONTAINERPILOT_VERSION}/${archive}" \ diff --git a/etc/containerpilot_handler.py b/etc/containerpilot_handler.py index 8de03ee..59356c9 100644 --- a/etc/containerpilot_handler.py +++ b/etc/containerpilot_handler.py @@ -1,5 +1,6 @@ #!/usr/bin/env python from __future__ import print_function +from time import sleep from sys import argv, stderr, path from consul import Consul from socket import gethostname @@ -10,7 +11,7 @@ def main(args): - log('containerpilot_handler started') + log('containerpilot_handler started: {}'.format(str(args))) CASSANDRA_HOME = resolve_home() CASSANDRA_USER, CASSANDRA_PASSWORD = resolve_credentials() @@ -25,21 +26,29 @@ def main(args): log('node configuration: {}'.format(node)) - current_seeds = node.query_seeds() - if not node.enough_seeds_exist(current_seeds) and not node.already_registered_as_seed(current_seeds): - log('volunteering as seed node') - node.register_as_seed(current_seeds) + if 'fakeBoot' in args: + log('pretending to boot') + sleep(10) + log('fakeBoot complete') + return if 'preStart' in args: + # loop while we try to grab a lock on the seeds list + while not node.enough_seeds_exist(current_seeds) and not node.register_as_seed(current_seeds): + sleep(5) + current_seeds = node.query_seeds() + log('waiting for seeds lock, current seed list: {}'.format(str(current_seeds))) + + # either enough seed nodes appeared in consul kv or we managed to add ourselves and grab the lock + # render our template in case there are existing seeds log('rendering configuration during preStart') # attempting to render the config immediately can result in our own volunteering being omitted # TODO: figure out what consul-template config would work like this (and not block indefinitely) - from time import sleep sleep(1) node.render_config() diff --git a/etc/containerpilot_handler/cassandra.py b/etc/containerpilot_handler/cassandra.py index 5ed4f86..7459cb6 100644 --- a/etc/containerpilot_handler/cassandra.py +++ b/etc/containerpilot_handler/cassandra.py @@ -1,5 +1,5 @@ from __future__ import print_function -from os import listdir +from os.path import exists from sys import stderr from socket import gethostname, gethostbyname from datetime import datetime @@ -11,6 +11,8 @@ class Cassandra(object): FLAG_SNAPSHOT_REQUIRED = 'SNAPSHOT_REQUIRED' + FILE_SESSION_ID = '/tmp/consul.session' + def __init__(self, consul, storage, home, user, password, datacenter, cluster_name): self.id = "cassandra-{}".format(gethostname()) self.consul = consul @@ -21,7 +23,8 @@ def __init__(self, consul, storage, home, user, password, datacenter, cluster_na self.datacenter = datacenter self.cluster_name = cluster_name - self.session_id = self.consul.session.create(self.id, behavior='delete', ttl=120) + self.session_id = self.load_or_create_session() + self.persist_session() def __str__(self): return 'Cassandra '.format( @@ -33,6 +36,22 @@ def build_seeds_key(self): def build_snapshot_key(self): return 'cassandra-snapshot-{}-{}'.format(self.datacenter, gethostname()) + def load_or_create_session(self): + if exists(Cassandra.FILE_SESSION_ID): + log('found session file') + with open(Cassandra.FILE_SESSION_ID, 'r') as session_file: + return session_file.read() + + log('creating new session') + return self.consul.session.create(self.id, behavior='delete', ttl=120) + + def persist_session(self): + with open(Cassandra.FILE_SESSION_ID, 'w') as session_file: + session_file.write(self.session_id) + + log('renewing persisted session: {}'.format(self.session_id)) + self.consul.session.renew(self.session_id) + def query_snapshot_state(self): _, snapshot = self.consul.kv.get(self.build_snapshot_key()) @@ -46,6 +65,9 @@ def query_seeds(self): if seeds is None: return None + if seeds['Value'] is None: + return [] + return seeds['Value'].split(',') def read_saved_seeds(self, should_retry=True): @@ -79,7 +101,8 @@ def enough_seeds_exist(self, seeds): return False parsed_seeds = [s.strip() for s in seeds] - return 1 < len(parsed_seeds) + # ideally there should be two (three max) seeds per DC, but we'll start with just one + return 0 < len(parsed_seeds) def already_registered_as_seed(self, seeds): if seeds is None: @@ -95,9 +118,7 @@ def register_as_seed(self, seeds): seeds.append(own_ip) - registered = self.consul.kv.put(self.build_seeds_key(), ','.join(seeds)) - if not registered: - raise ValueError('Failed to register ourselves as a seed') + return self.consul.kv.put(self.build_seeds_key(), ','.join(seeds), acquire=self.session_id) def render_config(self): log('SO CLOSE') diff --git a/makefile b/makefile index 7b47f07..05eccb3 100644 --- a/makefile +++ b/makefile @@ -1,5 +1,8 @@ DC := docker-compose -p autopilotpattern -f examples/compose/local-compose.yml +CONSUL_ADDR := $(shell $(DC) ps consuldc1 | egrep -o '0.0.0.0:\d+' | head -1) +CONSUL_URL := $(shell echo "http://$(CONSUL_ADDR)") + .PHONY: * build: @@ -9,10 +12,14 @@ up: $(DC) up restart-cassandra: - $(DC) stop cassandra && $(DC) rm -vf cassandra && $(DC) build cassandra && $(DC) up cassandra + $(DC) stop cassandra + $(DC) rm -vf cassandra + $(DC) build cassandra + $(DC) up -d --scale=cassandra=2 --scale=consuldc1=3 cassandra consuldc1 + $(DC) logs -f cassandra consul: - $(DC) up -d consul + open $(CONSUL_URL) down: $(DC) down --remove-orphans -v From f459b69a20abc9d9c3867aeee498bc0b80613d5a Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Fri, 8 Dec 2017 18:26:52 -0800 Subject: [PATCH 6/7] Configuration for smaller cassandra nodes --- Dockerfile | 9 +- etc/cassandra.tiny.yaml.ctmpl | 1248 +++++++++++++++++++++++ etc/containerpilot.json5 | 6 +- etc/containerpilot_handler.py | 2 +- etc/containerpilot_handler/cassandra.py | 3 +- examples/compose/local-compose.yml | 2 +- 6 files changed, 1262 insertions(+), 8 deletions(-) create mode 100644 etc/cassandra.tiny.yaml.ctmpl diff --git a/Dockerfile b/Dockerfile index 65a1125..833ed80 100644 --- a/Dockerfile +++ b/Dockerfile @@ -57,7 +57,10 @@ COPY etc/containerpilot.json5 /etc/containerpilot.json5 COPY etc/containerpilot_handler /usr/local/bin/containerpilot_handler COPY etc/containerpilot_handler.py /usr/local/bin/containerpilot_handler.py -COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl +# COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl + +# the following COPY should be used for minimal-memory installations (as low as 256m?) +COPY etc/cassandra.tiny.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl # disable the automatic seed configuration that enables single-node bootstrapping # the first line corresponds to "always set self as seed" @@ -65,6 +68,10 @@ COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl RUN sed -ri '/CASSANDRA_SEEDS.*CASSANDRA_BROADCAST_ADDRESS/d' /docker-entrypoint.sh && \ sed -ri '/sed -ri.*CASSANDRA_SEEDS.*\/cassandra.yaml/d' /docker-entrypoint.sh +# TODO: uncomment for tiny cassandra nodes (don't forget to change the COPY above to cassandra.tiny.yaml.ctmpl) +RUN sed -ri 's/^#MAX_HEAP_SIZE.*/MAX_HEAP_SIZE="64M"/' /etc/cassandra/cassandra-env.sh && \ + sed -ri 's/^#HEAP_NEWSIZE.*/HEAP_NEWSIZE="12M"/' /etc/cassandra/cassandra-env.sh + EXPOSE 7000 7001 7199 9042 9160 diff --git a/etc/cassandra.tiny.yaml.ctmpl b/etc/cassandra.tiny.yaml.ctmpl new file mode 100644 index 0000000..2f2ec61 --- /dev/null +++ b/etc/cassandra.tiny.yaml.ctmpl @@ -0,0 +1,1248 @@ +# 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: 0 + +# 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. +# +# 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: ",," + {{ $clusterName := env "CASSANDRA_CLUSTER_NAME" }} + - seeds: {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s-%s@%s" $clusterName . . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} + +# {{ range datacenters }}{{ $seedKey := printf "cassandra-seeds-%s-%s@%s" $clusterName . . }}{{ if keyExists $seedKey }}{{ key $seedKey }},{{ end }}{{ end }} + +# 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 +concurrent_reads: 2 +concurrent_writes: 2 +concurrent_counter_writes: 2 + +# 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 +concurrent_materialized_view_writes: 2 + +# 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: 128 +memtable_offheap_space_in_mb: 128 + +# 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: 172.20.0.3 + +# 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: 172.20.0.3 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# Please note that the address on which the native transport is bound is the +# same as the rpc_address. The port however is different and specified below. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests when the native transport is used. +# This is similar to rpc_max_threads though the default differs slightly (and +# there is no native_transport_min_threads, idle threads will always be stopped +# after 30 seconds). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Whether to start the thrift rpc server. +start_rpc: false + +# 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: 172.20.0.3 + +# 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 +rpc_server_type: hsha + +# 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 + +rpc_min_threads: 1 +rpc_max_threads: 2 + +# 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 +compaction_throughput_mb_per_sec: 0 + +# 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 + +# 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. +# 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 \ No newline at end of file diff --git a/etc/containerpilot.json5 b/etc/containerpilot.json5 index cfcb37e..fd342ad 100644 --- a/etc/containerpilot.json5 +++ b/etc/containerpilot.json5 @@ -1,7 +1,7 @@ { consul: 'localhost:8500', logging: { - level: "DEBUG", + level: "INFO", format: "default" }, jobs: [ @@ -34,9 +34,9 @@ port: 9042, health: { exec: "nodetool -u {{ .CASSANDRA_USER }} -pw {{ .CASSANDRA_PASSWORD }} status", - interval: 5, + interval: 15, ttl: 15, - timeout: "10s" + timeout: "1m" }, when: { source: 'cassandra-preStart', diff --git a/etc/containerpilot_handler.py b/etc/containerpilot_handler.py index 59356c9..5420ad0 100644 --- a/etc/containerpilot_handler.py +++ b/etc/containerpilot_handler.py @@ -45,7 +45,7 @@ def main(args): # either enough seed nodes appeared in consul kv or we managed to add ourselves and grab the lock # render our template in case there are existing seeds - log('rendering configuration during preStart') + log('rendering configuration during preStart, seeds: {}'.format(str(current_seeds))) # attempting to render the config immediately can result in our own volunteering being omitted # TODO: figure out what consul-template config would work like this (and not block indefinitely) diff --git a/etc/containerpilot_handler/cassandra.py b/etc/containerpilot_handler/cassandra.py index 7459cb6..0bf4482 100644 --- a/etc/containerpilot_handler/cassandra.py +++ b/etc/containerpilot_handler/cassandra.py @@ -118,10 +118,9 @@ def register_as_seed(self, seeds): seeds.append(own_ip) - return self.consul.kv.put(self.build_seeds_key(), ','.join(seeds), acquire=self.session_id) + return self.consul.kv.put(self.build_seeds_key(), ','.join(seeds)) def render_config(self): - log('SO CLOSE') check_call([ 'consul-template', '-once', '-template', '/etc/cassandra/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml']) log('template rendered to: {}'.format('/etc/cassandra/cassandra.yaml')) diff --git a/examples/compose/local-compose.yml b/examples/compose/local-compose.yml index 7c860d2..2662612 100644 --- a/examples/compose/local-compose.yml +++ b/examples/compose/local-compose.yml @@ -6,7 +6,7 @@ services: build: ../../ image: autopilotpattern/cassandra:latest restart: always - mem_limit: 2g + mem_limit: 512m dns: 127.0.0.1 # uncomment the following lines for more rapid development volumes: From 28b890ea526c5d6d7d01fd00acebe259e6b80307 Mon Sep 17 00:00:00 2001 From: Tomas Celaya Date: Fri, 15 Dec 2017 16:17:48 -0800 Subject: [PATCH 7/7] Fix session expiration issue --- Dockerfile | 10 ++-- README.md | 7 ++- etc/containerpilot.json5 | 2 +- etc/containerpilot_handler.py | 6 +-- etc/containerpilot_handler/cassandra.py | 25 ++++++---- etc/containerpilot_handler/utils.py | 4 ++ ...se.yml => docker-compose-multi-region.yml} | 46 ++++++++++++++----- examples/compose/docker-compose.yml | 40 ++++++++++++++++ examples/triton/docker-compose.yaml | 9 +--- makefile | 6 +-- 10 files changed, 115 insertions(+), 40 deletions(-) rename examples/compose/{local-compose.yml => docker-compose-multi-region.yml} (54%) create mode 100644 examples/compose/docker-compose.yml diff --git a/Dockerfile b/Dockerfile index 833ed80..483a007 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,5 +1,9 @@ FROM cassandra:3.11.0 +# trying to use cqlsh to interact with cassandra since installing cassandra-driver takes _forever_ +# if the pip module is needed the package is: +# cassandra-driver==3.12.0 + # install wget unzip and dig plus python modules RUN set -ex \ && apt-get update \ @@ -7,8 +11,6 @@ RUN set -ex \ && wget --quiet -O /tmp/get-pip.py https://bootstrap.pypa.io/get-pip.py \ && python /tmp/get-pip.py \ && pip install \ - # trying to use cqlsh to do this stuff, installing cassandra-driver takes _forever_ - # cassandra-driver==3.12.0 \ python-Consul==0.7.2 \ manta==2.6.0 \ pyyaml==3.12 \ @@ -59,7 +61,7 @@ COPY etc/containerpilot_handler /usr/local/bin/containerpilot_handler COPY etc/containerpilot_handler.py /usr/local/bin/containerpilot_handler.py # COPY etc/cassandra.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl -# the following COPY should be used for minimal-memory installations (as low as 256m?) +# the following COPY should be used for minimal-memory installations, potentially as low as 256m COPY etc/cassandra.tiny.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl # disable the automatic seed configuration that enables single-node bootstrapping @@ -68,7 +70,7 @@ COPY etc/cassandra.tiny.yaml.ctmpl /etc/cassandra/cassandra.yaml.ctmpl RUN sed -ri '/CASSANDRA_SEEDS.*CASSANDRA_BROADCAST_ADDRESS/d' /docker-entrypoint.sh && \ sed -ri '/sed -ri.*CASSANDRA_SEEDS.*\/cassandra.yaml/d' /docker-entrypoint.sh -# TODO: uncomment for tiny cassandra nodes (don't forget to change the COPY above to cassandra.tiny.yaml.ctmpl) +# TODO: uncomment for tiny cassandra nodes, don't forget to change the COPY above to cassandra.tiny.yaml.ctmpl RUN sed -ri 's/^#MAX_HEAP_SIZE.*/MAX_HEAP_SIZE="64M"/' /etc/cassandra/cassandra-env.sh && \ sed -ri 's/^#HEAP_NEWSIZE.*/HEAP_NEWSIZE="12M"/' /etc/cassandra/cassandra-env.sh diff --git a/README.md b/README.md index 94db97a..c482c8f 100644 --- a/README.md +++ b/README.md @@ -29,4 +29,9 @@ docker-compose exec cassandra cqlsh cassandra cqlsh> CREATE KEYSPACE demo WITH replication = {'class': 'NetworkTopologyStrategy', 'datacenter1': 2 }; USE demo; -``` \ No newline at end of file +``` + + +# Credits + +- Minimal Cassandra configuration based on John Berryman's [Building the Perfect Cassandra Test Environment](http://opensourceconnections.com/blog/2013/08/31/building-the-perfect-cassandra-test-environment/) diff --git a/etc/containerpilot.json5 b/etc/containerpilot.json5 index fd342ad..20a6729 100644 --- a/etc/containerpilot.json5 +++ b/etc/containerpilot.json5 @@ -1,5 +1,5 @@ { - consul: 'localhost:8500', + consul: '{{ if .CONSUL_AGENT }}localhost{{ else }}{{ .CONSUL }}{{ end }}:{{ .CONSUL_PORT | default "8500" }}', logging: { level: "INFO", format: "default" diff --git a/etc/containerpilot_handler.py b/etc/containerpilot_handler.py index 5420ad0..7075202 100644 --- a/etc/containerpilot_handler.py +++ b/etc/containerpilot_handler.py @@ -26,7 +26,7 @@ def main(args): log('node configuration: {}'.format(node)) - current_seeds = node.query_seeds() + seeds_modify_idx, current_seeds = node.query_seeds() if 'fakeBoot' in args: log('pretending to boot') @@ -37,9 +37,9 @@ def main(args): if 'preStart' in args: # loop while we try to grab a lock on the seeds list - while not node.enough_seeds_exist(current_seeds) and not node.register_as_seed(current_seeds): + while not node.enough_seeds_exist(current_seeds) and not node.register_as_seed(current_seeds, seeds_modify_idx): sleep(5) - current_seeds = node.query_seeds() + seeds_modify_idx, current_seeds = node.query_seeds() log('waiting for seeds lock, current seed list: {}'.format(str(current_seeds))) # either enough seed nodes appeared in consul kv or we managed to add ourselves and grab the lock diff --git a/etc/containerpilot_handler/cassandra.py b/etc/containerpilot_handler/cassandra.py index 0bf4482..d2832e6 100644 --- a/etc/containerpilot_handler/cassandra.py +++ b/etc/containerpilot_handler/cassandra.py @@ -1,6 +1,7 @@ from __future__ import print_function from os.path import exists from sys import stderr +from consul.base import NotFound from socket import gethostname, gethostbyname from datetime import datetime from containerpilot_handler.utils import log @@ -24,7 +25,11 @@ def __init__(self, consul, storage, home, user, password, datacenter, cluster_na self.cluster_name = cluster_name self.session_id = self.load_or_create_session() - self.persist_session() + try: + self.persist_session() + except NotFound as e: + self.session_id = self.load_or_create_session(forceNew=True) + self.persist_session() def __str__(self): return 'Cassandra '.format( @@ -36,11 +41,13 @@ def build_seeds_key(self): def build_snapshot_key(self): return 'cassandra-snapshot-{}-{}'.format(self.datacenter, gethostname()) - def load_or_create_session(self): - if exists(Cassandra.FILE_SESSION_ID): + def load_or_create_session(self, forceNew=False): + if exists(Cassandra.FILE_SESSION_ID) and forceNew: log('found session file') with open(Cassandra.FILE_SESSION_ID, 'r') as session_file: return session_file.read() + else: + log('skipping cached session load') log('creating new session') return self.consul.session.create(self.id, behavior='delete', ttl=120) @@ -61,14 +68,14 @@ def query_snapshot_state(self): return snapshot['Value'] def query_seeds(self): - _, seeds = self.consul.kv.get(self.build_seeds_key()) + midx, seeds = self.consul.kv.get(self.build_seeds_key()) if seeds is None: - return None + return midx, None if seeds['Value'] is None: - return [] + return midx, [] - return seeds['Value'].split(',') + return midx, seeds['Value'].split(',') def read_saved_seeds(self, should_retry=True): loaded_conf = None @@ -110,7 +117,7 @@ def already_registered_as_seed(self, seeds): return gethostbyname(gethostname()) in [s.strip() for s in seeds] - def register_as_seed(self, seeds): + def register_as_seed(self, seeds, modify_index): if seeds is None: seeds = [] @@ -118,7 +125,7 @@ def register_as_seed(self, seeds): seeds.append(own_ip) - return self.consul.kv.put(self.build_seeds_key(), ','.join(seeds)) + return self.consul.kv.put(self.build_seeds_key(), ','.join(seeds), cas=modify_index) def render_config(self): check_call([ diff --git a/etc/containerpilot_handler/utils.py b/etc/containerpilot_handler/utils.py index 5f13090..8494d73 100644 --- a/etc/containerpilot_handler/utils.py +++ b/etc/containerpilot_handler/utils.py @@ -49,6 +49,10 @@ def resolve_datacenter(c): if 'CASSANDRA_DC' in environ: return environ['CASSANDRA_DC'] + # TODO: figure out what priority this mdata-get call should have relative to Consul + # if exists('/native/usr/sbin/mdata-get') and consul is None: + # return check_output('/native/usr/sbin/mdata-get sdc:datacenter_name') + if not isinstance(c, Consul): raise ValueError('unexpected type for consul instance when resolving datacenter: {}'.format(type(c))) diff --git a/examples/compose/local-compose.yml b/examples/compose/docker-compose-multi-region.yml similarity index 54% rename from examples/compose/local-compose.yml rename to examples/compose/docker-compose-multi-region.yml index 2662612..5082754 100644 --- a/examples/compose/local-compose.yml +++ b/examples/compose/docker-compose-multi-region.yml @@ -2,7 +2,7 @@ version: '2.1' # Cassandra demonstration of the Autopilot pattern services: - cassandra: + cassandra-dc1: build: ../../ image: autopilotpattern/cassandra:latest restart: always @@ -16,23 +16,45 @@ services: - ../../tmp:/tmp/snapshots environment: - CONSUL=consuldc1 - - CASSANDRA_USER=cassandra - - CASSANDRA_PASSWORD=cassandra + - CASSANDRA_USER=c + - CASSANDRA_PASSWORD=c - CASSANDRA_CLUSTER_NAME=demo - - CASSANDRA_KEYSPACES=demo - - CASSANDRA_TOPOLOGY={"demo":{"datacenter1":1}} - - CASSANDRA_ENDPOINT_SNITCH=SimpleSnitch - SNAPSHOT_TARGET=file:///tmp/snapshots # the following options pertain to multi-datacenter deployments # - CASSANDRA_ENDPOINT_SNITCH=GossipingPropertyFileSnitch # - CASSANDRA_DC= # - CASSANDRA_RACK= links: - - consuldc1:consul + - consul-dc1:consul - consuldc1: + cassandra-dc2: + build: ../../ + image: autopilotpattern/cassandra:latest + restart: always + mem_limit: 512m + dns: 127.0.0.1 + # uncomment the following lines for more rapid development + volumes: + - ../../etc/containerpilot_handler:/usr/local/bin/containerpilot_handler + - ../../etc/containerpilot_handler.py:/usr/local/bin/containerpilot_handler.py + - ../../etc/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml.ctmpl + - ../../tmp:/tmp/snapshots + environment: + - CONSUL=consuldc1 + - CASSANDRA_USER=c + - CASSANDRA_PASSWORD=c + - CASSANDRA_CLUSTER_NAME=demo + - SNAPSHOT_TARGET=file:///tmp/snapshots + # the following options pertain to multi-datacenter deployments + # - CASSANDRA_ENDPOINT_SNITCH=GossipingPropertyFileSnitch + # - CASSANDRA_DC= + # - CASSANDRA_RACK= + links: + - consul-dc1:consul + + consul-dc1: build: . - image: autopilotpattern/consul:${TAG:-latest} + image: autopilotpattern/consul:latest restart: always mem_limit: 128m ports: @@ -43,8 +65,8 @@ services: command: > /usr/local/bin/containerpilot - consuldc2: - image: autopilotpattern/consul:${TAG:-latest} + consul-dc2: + image: autopilotpattern/consul:latest restart: always mem_limit: 128m ports: @@ -56,4 +78,4 @@ services: command: > /usr/local/bin/containerpilot links: - - consuldc1 + - consul-dc1 diff --git a/examples/compose/docker-compose.yml b/examples/compose/docker-compose.yml new file mode 100644 index 0000000..050e573 --- /dev/null +++ b/examples/compose/docker-compose.yml @@ -0,0 +1,40 @@ +version: '2.1' +# Cassandra demonstration of the Autopilot pattern + +services: + cassandra: + build: ../../ + image: tjcelaya/cassandra + restart: always + mem_limit: 512m + dns: 127.0.0.1 + # uncomment the following lines for more rapid development + volumes: + - ../../etc/containerpilot_handler:/usr/local/bin/containerpilot_handler + - ../../etc/containerpilot_handler.py:/usr/local/bin/containerpilot_handler.py + - ../../etc/cassandra.yaml.ctmpl:/etc/cassandra/cassandra.yaml.ctmpl + - ../../tmp:/tmp/snapshots + environment: + - CONSUL_AGENT=1 + - CONSUL=consul + - CASSANDRA_USER=c + - CASSANDRA_PASSWORD=c + - CASSANDRA_CLUSTER_NAME=demo + - CASSANDRA_ENDPOINT_SNITCH=SimpleSnitch + - SNAPSHOT_TARGET=file:///tmp/snapshots + links: + - consul:consul + + consul: + build: . + image: tjcelaya/consul + restart: always + mem_limit: 128m + ports: + - 8500 + environment: + - CONSUL_DEV=1 + - CONSUL=consul + - CONSUL_DATACENTER_NAME=dc1 + command: > + /usr/local/bin/containerpilot diff --git a/examples/triton/docker-compose.yaml b/examples/triton/docker-compose.yaml index 62bc8a6..024264a 100644 --- a/examples/triton/docker-compose.yaml +++ b/examples/triton/docker-compose.yaml @@ -27,13 +27,8 @@ services: mem_limit: 128m network_mode: bridge ports: - - 8500:8500 + - 8500 labels: - triton.cns.services=cassandra-consul command: > - /usr/local/bin/containerpilot - /bin/consul agent -server - -config-dir=/etc/consul - -log-level=err - -bootstrap-expect 1 - -ui-dir /ui + /usr/local/bin/containerpilot \ No newline at end of file diff --git a/makefile b/makefile index 05eccb3..9536f12 100644 --- a/makefile +++ b/makefile @@ -1,6 +1,6 @@ -DC := docker-compose -p autopilotpattern -f examples/compose/local-compose.yml +DC := docker-compose -CONSUL_ADDR := $(shell $(DC) ps consuldc1 | egrep -o '0.0.0.0:\d+' | head -1) +CONSUL_ADDR := $(shell $(DC) ps consul | egrep -o '0.0.0.0:\d+' | head -1) CONSUL_URL := $(shell echo "http://$(CONSUL_ADDR)") .PHONY: * @@ -15,7 +15,7 @@ restart-cassandra: $(DC) stop cassandra $(DC) rm -vf cassandra $(DC) build cassandra - $(DC) up -d --scale=cassandra=2 --scale=consuldc1=3 cassandra consuldc1 + $(DC) up -d --scale=cassandra=1 --scale=consul=3 cassandra consul $(DC) logs -f cassandra consul: