ciborg 0.0.1 → 3.0.0

data/chef/travis-cookbooks/ci_environment/cassandra/templates/default/cassandra.yaml.erb

@@ -0,0 +1,567 @@
+# 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'
+
+# You should always specify InitialToken when setting up a production
+# cluster for the first time, and often when adding capacity later.
+# The principle is that each node should be given an equal slice of
+# the token ring; see http://wiki.apache.org/cassandra/Operations
+# for more details.
+#
+# If blank, Cassandra will request a token bisecting the range of
+# the heaviest-loaded existing node.  If there is no load information
+# available, such as is the case with a new cluster, it will pick
+# a random token, which will lead to hot spots.
+initial_token:
+
+# See http://wiki.apache.org/cassandra/HintedHandoff
+hinted_handoff_enabled: true
+# this defines the maximum amount of time a dead host will have hints
+# generated.  After it has been dead this long, hints will be dropped.
+max_hint_window_in_ms: 3600000 # one hour
+# Sleep this long after delivering each hint
+hinted_handoff_throttle_delay_in_ms: 1
+
+# The following setting populates the page cache on memtable flush and compaction
+# WARNING: Enable this setting only when the whole node's data fits in memory.
+# Defaults to: false
+# populate_io_cache_on_flush: false
+
+# authentication backend, implementing IAuthenticator; used to identify users
+authenticator: org.apache.cassandra.auth.AllowAllAuthenticator
+
+# authorization backend, implementing IAuthority; used to limit access/provide permissions
+authority: org.apache.cassandra.auth.AllowAllAuthority
+
+# The partitioner is responsible for distributing rows (by key) across
+# nodes in the cluster.  Any IPartitioner may be used, including your
+# own as long as it is on the classpath.  Out of the box, Cassandra
+# provides org.apache.cassandra.dht.RandomPartitioner
+# org.apache.cassandra.dht.ByteOrderedPartitioner,
+# org.apache.cassandra.dht.OrderPreservingPartitioner (deprecated),
+# and org.apache.cassandra.dht.CollatingOrderPreservingPartitioner
+# (deprecated).
+# 
+# - RandomPartitioner distributes rows across the cluster evenly by md5.
+#   When in doubt, this is the best option.
+# - ByteOrderedPartitioner orders rows lexically by key bytes.  BOP allows
+#   scanning rows in key order, but the ordering can generate hot spots
+#   for sequential insertion workloads.
+# - OrderPreservingPartitioner is an obsolete form of BOP, that stores
+# - keys in a less-efficient format and only works with keys that are
+#   UTF8-encoded Strings.
+# - CollatingOPP colates according to EN,US rules rather than lexical byte
+#   ordering.  Use this as an example if you need custom collation.
+#
+# See http://wiki.apache.org/cassandra/Operations for more on
+# partitioners and token selection.
+partitioner: org.apache.cassandra.dht.RandomPartitioner
+
+# directories where Cassandra should store data on disk.
+data_file_directories:
+    - <%= File.join(node.cassandra.data_root_dir, 'data') %>
+
+# commit log
+commitlog_directory: <%= File.join(node.cassandra.data_root_dir, 'commitlog') %>
+
+# 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 store the whole values of
+# its rows, 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
+# safe the keys cache. Caches are saved to saved_caches_directory as
+# specified in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 14400 or 4 hours.
+key_cache_save_period: 14400
+
+# Number of keys from the key cache to save
+# Disabled by default, meaning all keys are going to be saved
+# key_cache_keys_to_save: 100
+
+# Maximum size of the row cache in memory.
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is 0, to disable row caching.
+row_cache_size_in_mb: 0
+
+# Duration in seconds after which Cassandra should
+# safe the row cache. Caches are saved to saved_caches_directory as specified
+# in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 0 to disable saving the row cache.
+row_cache_save_period: 0
+
+# Number of keys from the row cache to save
+# Disabled by default, meaning all keys are going to be saved
+# row_cache_keys_to_save: 100
+
+# The provider for the row cache to use.
+#
+# Supported values are: ConcurrentLinkedHashCacheProvider, SerializingCacheProvider
+#
+# SerializingCacheProvider serialises the contents of the row and stores
+# it in native memory, i.e., off the JVM Heap. Serialized rows take
+# significantly less memory than "live" rows in the JVM, so you can cache
+# more rows in a given memory footprint.  And storing the cache off-heap
+# means you can use smaller heap sizes, reducing the impact of GC pauses.
+#
+# It is also valid to specify the fully-qualified class name to a class
+# that implements org.apache.cassandra.cache.IRowCacheProvider.
+#
+# Defaults to SerializingCacheProvider
+row_cache_provider: SerializingCacheProvider
+
+# saved caches
+saved_caches_directory: <%= File.join(node.cassandra.data_root_dir, 'saved_caches') %>
+
+# commitlog_sync may be either "periodic" or "batch." 
+# When in batch mode, Cassandra won't ack writes until the commit log
+# has been fsynced to disk.  It will wait up to
+# commitlog_sync_batch_window_in_ms milliseconds for other writes, before
+# performing the sync.
+#
+# commitlog_sync: batch
+# commitlog_sync_batch_window_in_ms: 50
+#
+# the other option is "periodic" where writes may be acked immediately
+# and the CommitLog is simply synced every commitlog_sync_period_in_ms
+# milliseconds.
+commitlog_sync: periodic
+commitlog_sync_period_in_ms: 10000
+
+# The size of the individual commitlog file segments.  A commitlog
+# segment may be archived, deleted, or recycled once all the data
+# in it (potentally from each columnfamily in the system) has been 
+# flushed to sstables.  
+#
+# The default size is 32, which is almost always fine, but if you are
+# archiving commitlog segments (see commitlog_archiving.properties),
+# then you probably want a finer granularity of archiving; 8 or 16 MB
+# is reasonable.
+commitlog_segment_size_in_mb: 32
+
+# any class that implements the SeedProvider interface and has a
+# constructor that takes a Map<String, String> of parameters will do.
+seed_provider:
+    # Addresses of hosts that are deemed contact points. 
+    # Cassandra nodes use this list of hosts to find each other and learn
+    # the topology of the ring.  You must change this if you are running
+    # multiple nodes!
+    - class_name: org.apache.cassandra.locator.SimpleSeedProvider
+      parameters:
+          # seeds is actually a comma-delimited list of addresses.
+          # Ex: "<ip1>,<ip2>,<ip3>"
+          - seeds: "127.0.0.1"
+
+# emergency pressure valve: each time heap usage after a full (CMS)
+# garbage collection is above this fraction of the max, Cassandra will
+# flush the largest memtables.  
+#
+# Set to 1.0 to disable.  Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+#
+# RELYING ON THIS AS YOUR PRIMARY TUNING MECHANISM WILL WORK POORLY:
+# it is most effective under light to moderate load, or read-heavy
+# workloads; under truly massive write load, it will often be too
+# little, too late.
+flush_largest_memtables_at: 0.75
+
+# emergency pressure valve #2: the first time heap usage after a full
+# (CMS) garbage collection is above this fraction of the max,
+# Cassandra will reduce cache maximum _capacity_ to the given fraction
+# of the current _size_.  Should usually be set substantially above
+# flush_largest_memtables_at, since that will have less long-term
+# impact on the system.  
+# 
+# Set to 1.0 to disable.  Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+reduce_cache_sizes_at: 0.85
+reduce_cache_capacity_to: 0.6
+
+# For workloads with more data than can fit in memory, Cassandra's
+# bottleneck will be reads that need to fetch data from
+# disk. "concurrent_reads" should be set to (16 * number_of_drives) in
+# order to allow the operations to enqueue low enough in the stack
+# that the OS and drives can reorder them.
+#
+# On the other hand, since writes are almost never IO bound, the ideal
+# number of "concurrent_writes" is dependent on the number of cores in
+# your system; (8 * number_of_cores) is a good rule of thumb.
+concurrent_reads: 32
+concurrent_writes: 32
+
+# Total memory to use for memtables.  Cassandra will flush the largest
+# memtable when this much memory is used.
+# If omitted, Cassandra will set it to 1/3 of the heap.
+# memtable_total_space_in_mb: 2048
+
+# Total space to use for commitlogs.  Since commitlog segments are
+# mmapped, and hence use up address space, the default size is 32
+# on 32-bit JVMs, and 1024 on 64-bit JVMs.
+#
+# If space gets above this value (it will round up to the next nearest
+# segment multiple), Cassandra will flush every dirty CF in the oldest
+# segment and remove it.  So a small total commitlog space will tend
+# to cause more flush activity on less-active columnfamilies.
+# commitlog_total_space_in_mb: 4096
+
+# This sets the amount of memtable flush writer threads.  These will
+# be blocked by disk io, and each one will hold a memtable in memory
+# while blocked. If you have a large heap and many data directories,
+# you can increase this value for better flush performance.
+# By default this will be set to the amount of data directories defined.
+#memtable_flush_writers: 1
+
+# the number of full memtables to allow pending flush, that is,
+# waiting for a writer thread.  At a minimum, this should be set to
+# the maximum number of secondary indexes created on a single CF.
+memtable_flush_queue_size: 4
+
+# 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 SSD:s; not
+# necessarily on platters.
+trickle_fsync: false
+trickle_fsync_interval_in_kb: 10240
+
+# TCP port, for commands and data
+storage_port: 7000
+
+# SSL port, for encrypted communication.  Unused unless enabled in
+# encryption_options
+ssl_storage_port: 7001
+
+# Address to bind to and tell other Cassandra nodes to connect to. You
+# _must_ change this if you want multiple nodes to be able to
+# communicate!
+# 
+# Leaving it blank leaves it up to InetAddress.getLocalHost(). This
+# will always do the Right Thing *if* the node is properly configured
+# (hostname, name resolution, etc), and the Right Thing is to use the
+# address associated with the hostname (it might not be).
+#
+# Setting this to 0.0.0.0 is always wrong.
+listen_address: localhost
+
+# Address to broadcast to other Cassandra nodes
+# Leaving this blank will set it to the same value as listen_address
+# broadcast_address: 1.2.3.4
+
+# The address to bind the Thrift RPC service to -- clients connect
+# here. Unlike ListenAddress above, you *can* specify 0.0.0.0 here if
+# you want Thrift to listen on all interfaces.
+# 
+# Leaving this blank has the same effect it does for ListenAddress,
+# (i.e. it will be based on the configured hostname of the node).
+rpc_address: localhost
+# port for Thrift to listen for clients on
+rpc_port: 9160
+
+# enable or disable keepalive on rpc connections
+rpc_keepalive: true
+
+# Cassandra provides three options for the RPC Server:
+#
+# sync  -> One connection per thread in the rpc pool (see below).
+#          For a very large number of clients, memory will be your limiting
+#          factor; on a 64 bit JVM, 128KB is the minimum stack size per thread.
+#          Connection pooling is very, very strongly recommended.
+#
+# async -> Nonblocking server implementation with one thread to serve 
+#          rpc connections.  This is not recommended for high throughput use
+#          cases. Async has been tested to be about 50% slower than sync
+#          or hsha and is deprecated: it will be removed in the next major release.
+#
+# hsha  -> Stands for "half synchronous, half asynchronous." The rpc thread pool 
+#          (see below) is used to manage requests, but the threads are multiplexed
+#          across the different clients.
+#
+# 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.
+rpc_server_type: sync
+
+# Uncomment rpc_min|max|thread to set request pool size.
+# You would primarily set max for the sync server to safeguard against
+# misbehaved clients; if you do hit the max, Cassandra will block until one
+# disconnects before accepting more.  The defaults for sync are min of 16 and max
+# unlimited.
+# 
+# For the Hsha server, the min and max both default to quadruple the number of
+# CPU cores.
+#
+# This configuration is ignored by the async server.
+#
+# 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:
+
+# Frame size for thrift (maximum field length).
+# 0 disables TFramedTransport in favor of TSocket. This option
+# is deprecated; we strongly recommend using Framed mode.
+thrift_framed_transport_size_in_mb: 15
+
+# The max length of a thrift message, including all fields and
+# internal thrift overhead.
+thrift_max_message_length_in_mb: 16
+
+# Set to true to have Cassandra create a hard link to each sstable
+# flushed or streamed locally in a backups/ subdirectory of the
+# Keyspace data.  Removing these links is the operator's
+# responsibility.
+incremental_backups: false
+
+# Whether or not to take a snapshot before each compaction.  Be
+# careful using this option, since Cassandra won't clean up the
+# snapshots for you.  Mostly useful if you're paranoid when there
+# is a data format change.
+snapshot_before_compaction: false
+
+# Whether or not a snapshot is taken of the data before keyspace truncation
+# or dropping of column families. The STRONGLY advised default of true 
+# should be used to provide data safety. If you set this flag to false, you will
+# lose data on truncation or drop.
+auto_snapshot: true
+
+# Add column indexes to a row after its contents reach this size.
+# Increase if your column values are large, or if you have a very large
+# number of columns.  The competing causes are, Cassandra has to
+# deserialize this much of the row to read a single column, so you want
+# it to be small - at least if you do many partial-row reads - but all
+# the index data is read for each access, so you don't want to generate
+# that wastefully either.
+column_index_size_in_kb: 64
+
+# Size limit for rows being compacted in memory.  Larger rows will spill
+# over to disk and use a slower two-pass compaction process.  A message
+# will be logged specifying the row key.
+in_memory_compaction_limit_in_mb: 64
+
+# Number of simultaneous compactions to allow, NOT including
+# validation "compactions" for anti-entropy repair.  Simultaneous
+# compactions can help preserve read performance in a mixed read/write
+# workload, by mitigating the tendency of small sstables to accumulate
+# during a single long running compactions. The default is usually
+# fine and if you experience problems with compaction running too
+# slowly or too fast, you should look at
+# compaction_throughput_mb_per_sec first.
+#
+# This setting has no effect on LeveledCompactionStrategy.
+#
+# concurrent_compactors defaults to the number of cores.
+# Uncomment to make compaction mono-threaded, the pre-0.8 default.
+#concurrent_compactors: 1
+
+# Multi-threaded compaction. When enabled, each compaction will use
+# up to one thread per core, plus one thread per sstable being merged.
+# This is usually only useful for SSD-based hardware: otherwise, 
+# your concern is usually to get compaction to do LESS i/o (see:
+# compaction_throughput_mb_per_sec), not more.
+multithreaded_compaction: false
+
+# 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
+
+# Track cached row keys during compaction, and re-cache their new
+# positions in the compacted sstable.  Disable if you use really large
+# key caches.
+compaction_preheat_key_cache: true
+
+# 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 400 Mbps or 50 MB/s.
+# stream_throughput_outbound_megabits_per_sec: 400
+
+# Time to wait for a reply from other nodes before failing the command 
+rpc_timeout_in_ms: 10000
+
+# Enable socket timeout for streaming operation.
+# When a timeout occurs during streaming, streaming is retried from the start
+# of the current file. This *can* involve re-streaming an important amount of
+# data, so you should avoid setting the value too low.
+# Default value is 0, which never timeout streams.
+# streaming_socket_timeout_in_ms: 0
+
+# phi value that must be reached for a host to be marked down.
+# most users should never need to adjust this.
+# phi_convict_threshold: 8
+
+# endpoint_snitch -- Set this to a class that implements
+# IEndpointSnitch.  The snitch has two functions:
+# - it teaches Cassandra enough about your network topology to route
+#   requests efficiently
+# - it allows Cassandra to spread replicas around your cluster to avoid
+#   correlated failures. It does this by grouping machines into
+#   "datacenters" and "racks."  Cassandra will do its best not to have
+#   more than one replica on the same "rack" (which may not actually
+#   be a physical location)
+#
+# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
+# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
+# ARE PLACED.
+#
+# Out of the box, Cassandra provides
+#  - SimpleSnitch:
+#    Treats Strategy order as proximity. This improves cache locality
+#    when disabling read repair, which can further improve throughput.
+#    Only appropriate for single-datacenter deployments.
+#  - PropertyFileSnitch:
+#    Proximity is determined by rack and data center, which are
+#    explicitly configured in cassandra-topology.properties.
+#  - GossipingPropertyFileSnitch
+#    The rack and datacenter for the local node are defined in
+#    cassandra-rackdc.properties and propagated to other nodes via gossip.  If
+#    cassandra-topology.properties exists, it is used as a fallback, allowing
+#    migration from the PropertyFileSnitch.
+#  - RackInferringSnitch:
+#    Proximity is determined by rack and data center, which are
+#    assumed to correspond to the 3rd and 2nd octet of each node's
+#    IP address, respectively.  Unless this happens to match your
+#    deployment conventions (as it did Facebook's), this is best used
+#    as an example of writing a custom Snitch class.
+#  - Ec2Snitch:
+#    Appropriate for EC2 deployments in a single Region.  Loads Region
+#    and Availability Zone information from the EC2 API. The Region is
+#    treated as the Datacenter, and the Availability Zone as the rack.
+#    Only private IPs are used, so this will not work across multiple
+#    Regions.
+#  - Ec2MultiRegionSnitch:
+#    Uses public IPs as broadcast_address to allow cross-region
+#    connectivity.  (Thus, you should set seed addresses to the public
+#    IP as well.) You will need to open the storage_port or
+#    ssl_storage_port on the public IP firewall.  (For intra-Region
+#    traffic, Cassandra will switch to the private IP after
+#    establishing a connection.)
+#
+# You can use a custom Snitch by setting this to the full class name
+# of the snitch, which will be assumed to be on your classpath.
+endpoint_snitch: SimpleSnitch
+
+# controls how often to perform the more expensive part of host score
+# calculation
+dynamic_snitch_update_interval_in_ms: 100 
+# controls how often to reset all host scores, allowing a bad host to
+# possibly recover
+dynamic_snitch_reset_interval_in_ms: 600000
+# if set greater than zero and read_repair_chance is < 1.0, this will allow
+# 'pinning' of replicas to hosts in order to increase cache capacity.
+# The badness threshold will control how much worse the pinned host has to be
+# before the dynamic snitch will prefer other replicas over it.  This is
+# expressed as a double which represents a percentage.  Thus, a value of
+# 0.2 means Cassandra would continue to prefer the static snitch values
+# until the pinned host was 20% worse than the fastest.
+dynamic_snitch_badness_threshold: 0.1
+
+# request_scheduler -- Set this to a class that implements
+# RequestScheduler, which will schedule incoming client requests
+# according to the specific policy. This is useful for multi-tenancy
+# with a single Cassandra cluster.
+# NOTE: This is specifically for requests from the client and does
+# not affect inter node communication.
+# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place
+# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of
+# client requests to a node with a separate queue for each
+# request_scheduler_id. The scheduler is further customized by
+# request_scheduler_options as described below.
+request_scheduler: org.apache.cassandra.scheduler.NoScheduler
+
+# Scheduler Options vary based on the type of scheduler
+# NoScheduler - Has no options
+# RoundRobin
+#  - throttle_limit -- The throttle_limit is the number of in-flight
+#                      requests per client.  Requests beyond 
+#                      that limit are queued up until
+#                      running requests can complete.
+#                      The value of 80 here is twice the number of
+#                      concurrent_reads + concurrent_writes.
+#  - default_weight -- default_weight is optional and allows for
+#                      overriding the default which is 1.
+#  - weights -- Weights are optional and will default to 1 or the
+#               overridden default_weight. The weight translates into how
+#               many requests are handled during each turn of the
+#               RoundRobin, based on the scheduler id.
+#
+# request_scheduler_options:
+#    throttle_limit: 80
+#    default_weight: 5
+#    weights:
+#      Keyspace1: 1
+#      Keyspace2: 5
+
+# request_scheduler_id -- An identifer based on which to perform
+# the request scheduling. Currently the only valid option is keyspace.
+# request_scheduler_id: keyspace
+
+# index_interval controls the sampling of entries from the primrary
+# row index in terms of space versus time.  The larger the interval,
+# the smaller and less effective the sampling will be.  In technicial
+# terms, the interval coresponds to the number of index entries that
+# are skipped between taking each sample.  All the sampled entries
+# must fit in memory.  Generally, a value between 128 and 512 here
+# coupled with a large key cache size on CFs results in the best trade
+# offs.  This value is not often changed, however if you have many
+# very small rows (many to an OS page), then increasing this will
+# often lower memory usage without a impact on performance.
+index_interval: 128
+
+# Enable or disable inter-node encryption
+# Default settings are TLS v1, RSA 1024-bit keys (it is imperative that
+# users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher
+# suite for authentication, key exchange and encryption of the actual data transfers.
+# NOTE: No custom encryption options are enabled at the moment
+# The available internode options are : all, none, dc, rack
+#
+# If set to dc cassandra will encrypt the traffic between the DCs
+# If set to rack cassandra will encrypt the traffic between the racks
+#
+# The passwords used in these options must match the passwords used when generating
+# the keystore and truststore.  For instructions on generating these files, see:
+# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore
+#
+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]