diff --git a/data/common/cassandra.yaml b/data/common/cassandra.yaml --- a/data/common/cassandra.yaml +++ b/data/common/cassandra.yaml @@ -1,1182 +1,78 @@ -cassandra::release: 311x -cassandra::cluster: azure +cassandra::base_data_directory: /srv/cassandra +cassandra::base_config_directory: /etc/cassandra +cassandra::base_log_directory: /var/log/cassandra -cassandra::exporter::version: "0.9.10" -cassandra::exporter::listen_network: "%{lookup('internal_network')}" -cassandra::exporter::listen_port: 9500 +cassandra::version: 4.0.5 cassandra::listen_network: "%{lookup('internal_network')}" -cassandra::baseline_settings: - # NOTE: - # See http://wiki.apache.org/cassandra/StorageConfiguration for - # full explanations of configuration directives - # /NOTE - - # 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 - - # 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 - - # 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 - - # 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 - - # commitlog_sync may be either "periodic" or "batch." - # - # When in batch mode, Cassandra won't ack writes until the commit log - # has been fsynced to disk. It will wait - # commitlog_sync_batch_window_in_ms milliseconds between fsyncs. - # This window should be kept short because the writer threads will - # be unable to do extra work while waiting. (You may need to increase - # concurrent_writes for the same reason.) - # - # commitlog_sync: batch - # commitlog_sync_batch_window_in_ms: 2 - # - # the other option is "periodic" where writes may be acked immediately - # and the CommitLog is simply synced every commitlog_sync_period_in_ms - # milliseconds. - commitlog_sync: periodic - commitlog_sync_period_in_ms: 10000 - - # The size of the individual commitlog file segments. A commitlog - # segment may be archived, deleted, or recycled once all the data - # in it (potentially from each columnfamily in the system) has been - # flushed to sstables. - # - # The default size is 32, which is almost always fine, but if you are - # archiving commitlog segments (see commitlog_archiving.properties), - # then you probably want a finer granularity of archiving; 8 or 16 MB - # is reasonable. - # Max mutation size is also configurable via max_mutation_size_in_kb setting in - # cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. - # This should be positive and less than 2048. - # - # NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must - # be set to at least twice the size of max_mutation_size_in_kb / 1024 - # - commitlog_segment_size_in_mb: 32 - - # Compression to apply to the commit log. If omitted, the commit log - # will be written uncompressed. LZ4, Snappy, and Deflate compressors - # are supported. - # commitlog_compression: - # - class_name: LZ4Compressor - # parameters: - # - - - # 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: 64 - concurrent_writes: 96 - concurrent_counter_writes: 64 - - # 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: true - 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 - - # Set listen_address OR listen_interface, not both. Interfaces must correspond - # to a single address, IP aliasing is not supported. - # listen_interface: eth0 - - # If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address - # you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 - # address will be used. If true the first ipv6 address will be used. Defaults to false preferring - # ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. - # listen_interface_prefer_ipv6: false - - # Address to broadcast to other Cassandra nodes - # Leaving this blank will set it to the same value as listen_address - # broadcast_address: 1.2.3.4 - - # When using multiple physical network interfaces, set this - # to true to listen on broadcast_address in addition to - # the listen_address, allowing nodes to communicate in both - # interfaces. - # Ignore this property if the network configuration automatically - # routes between the public and private networks such as EC2. - # listen_on_broadcast_address: false - - # Internode authentication backend, implementing IInternodeAuthenticator; - # used to allow/disallow connections from peer nodes. - # internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator - - # Whether to start the native transport server. - # Please note that the address on which the native transport is bound is the - # same as the rpc_address. The port however is different and specified below. - start_native_transport: true - # port for the CQL native transport to listen for clients on - # For security reasons, you should not expose this port to the internet. Firewall it if needed. +cassandra::nodes: + cassandra01.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + cassandra02.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + cassandra03.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + cassandra04.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + cassandra05.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + cassandra06.internal.softwareheritage.org: + instances: + instance1: + cluster_name: archive_production + +cassandra::clusters: + archive_production: + seed_provider: + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + - seeds: "cassandra01.internal.softwareheritage.org:7000" + +cassandra::default_instance_configuration: + cluster_name: "%{lookup('cassandra::default_cluster_name')}" + datacenter: "%{::subnet}" + # rack: "%{::hostname}" + rack: rack1 native_transport_port: 9042 - # Enabling native transport encryption in client_encryption_options allows you to either use - # encryption for the standard port or to use a dedicated, additional port along with the unencrypted - # standard native_transport_port. - # Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption - # for native_transport_port. Setting native_transport_port_ssl to a different value - # from native_transport_port will use encryption for native_transport_port_ssl while - # keeping native_transport_port unencrypted. - # native_transport_port_ssl: 9142 - # The maximum threads for handling requests when the native transport is used. - # This is similar to rpc_max_threads though the default differs slightly (and - # there is no native_transport_min_threads, idle threads will always be stopped - # after 30 seconds). - # native_transport_max_threads: 128 - # - # The maximum size of allowed frame. Frame (requests) larger than this will - # be rejected as invalid. The default is 256MB. If you're changing this parameter, - # you may want to adjust max_value_size_in_mb accordingly. This should be positive and less than 2048. - # native_transport_max_frame_size_in_mb: 256 - - # The maximum number of concurrent client connections. - # The default is -1, which means unlimited. - # native_transport_max_concurrent_connections: -1 - - # The maximum number of concurrent client connections per source ip. - # The default is -1, which means unlimited. - # native_transport_max_concurrent_connections_per_ip: -1 - - # Whether to start the thrift rpc server. - start_rpc: false - - # Set rpc_address OR rpc_interface, not both. Interfaces must correspond - # to a single address, IP aliasing is not supported. - # rpc_interface: eth1 - - # If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address - # you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 - # address will be used. If true the first ipv6 address will be used. Defaults to false preferring - # ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. - # rpc_interface_prefer_ipv6: false - - # port for Thrift to listen for clients on - rpc_port: 9160 - - # RPC address to broadcast to drivers and other Cassandra nodes. This cannot - # be set to 0.0.0.0. If left blank, this will be set to the value of - # rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must - # be set. - # broadcast_rpc_address: 1.2.3.4 - - # enable or disable keepalive on rpc/native connections - rpc_keepalive: true - - # Cassandra provides two out-of-the-box options for the RPC Server: - # - # sync - # One thread per thrift connection. For a very large number of clients, memory - # will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size - # per thread, and that will correspond to your use of virtual memory (but physical memory - # may be limited depending on use of stack space). - # - # hsha - # Stands for "half synchronous, half asynchronous." All thrift clients are handled - # asynchronously using a small number of threads that does not vary with the amount - # of thrift clients (and thus scales well to many clients). The rpc requests are still - # synchronous (one thread per active request). If hsha is selected then it is essential - # that rpc_max_threads is changed from the default value of unlimited. - # - # The default is sync because on Windows hsha is about 30% slower. On Linux, - # sync/hsha performance is about the same, with hsha of course using less memory. - # - # Alternatively, can provide your own RPC server by providing the fully-qualified class name - # of an o.a.c.t.TServerFactory that can create an instance of it. - rpc_server_type: sync - - # Uncomment rpc_min|max_thread to set request pool size limits. - # - # Regardless of your choice of RPC server (see above), the number of maximum requests in the - # RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync - # RPC server, it also dictates the number of clients that can be connected at all). - # - # The default is unlimited and thus provides no protection against clients overwhelming the server. You are - # encouraged to set a maximum that makes sense for you in production, but do keep in mind that - # rpc_max_threads represents the maximum number of client requests this server may execute concurrently. - # - # rpc_min_threads: 16 - # rpc_max_threads: 2048 - - # uncomment to set socket buffer sizes on rpc connections - # rpc_send_buff_size_in_bytes: - # rpc_recv_buff_size_in_bytes: - - # Uncomment to set socket buffer size for internode communication - # Note that when setting this, the buffer size is limited by net.core.wmem_max - # and when not setting it it is defined by net.ipv4.tcp_wmem - # See also: - # /proc/sys/net/core/wmem_max - # /proc/sys/net/core/rmem_max - # /proc/sys/net/ipv4/tcp_wmem - # /proc/sys/net/ipv4/tcp_wmem - # and 'man tcp' - # internode_send_buff_size_in_bytes: - - # Uncomment to set socket buffer size for internode communication - # Note that when setting this, the buffer size is limited by net.core.wmem_max - # and when not setting it it is defined by net.ipv4.tcp_wmem - # internode_recv_buff_size_in_bytes: - - # Frame size for thrift (maximum message length). - thrift_framed_transport_size_in_mb: 15 - - # Set to true to have Cassandra create a hard link to each sstable - # flushed or streamed locally in a backups/ subdirectory of the - # keyspace data. Removing these links is the operator's - # responsibility. - incremental_backups: false - - # Whether or not to take a snapshot before each compaction. Be - # careful using this option, since Cassandra won't clean up the - # snapshots for you. Mostly useful if you're paranoid when there - # is a data format change. - snapshot_before_compaction: false - - # Whether or not a snapshot is taken of the data before keyspace truncation - # or dropping of column families. The STRONGLY advised default of true - # should be used to provide data safety. If you set this flag to false, you will - # lose data on truncation or drop. - auto_snapshot: true - - # Granularity of the collation index of rows within a partition. - # Increase if your rows are large, or if you have a very large - # number of rows per partition. The competing goals are these: - # - # - a smaller granularity means more index entries are generated - # and looking up rows withing the partition by collation column - # is faster - # - but, Cassandra will keep the collation index in memory for hot - # rows (as part of the key cache), so a larger granularity means - # you can cache more hot rows - column_index_size_in_kb: 64 - - # Per sstable indexed key cache entries (the collation index in memory - # mentioned above) exceeding this size will not be held on heap. - # This means that only partition information is held on heap and the - # index entries are read from disk. - # - # Note that this size refers to the size of the - # serialized index information and not the size of the partition. - column_index_cache_size_in_kb: 2 - - # Number of simultaneous compactions to allow, NOT including - # validation "compactions" for anti-entropy repair. Simultaneous - # compactions can help preserve read performance in a mixed read/write - # workload, by mitigating the tendency of small sstables to accumulate - # during a single long running compactions. The default is usually - # fine and if you experience problems with compaction running too - # slowly or too fast, you should look at - # compaction_throughput_mb_per_sec first. - # - # concurrent_compactors defaults to the smaller of (number of disks, - # number of cores), with a minimum of 2 and a maximum of 8. - # - # If your data directories are backed by SSD, you should increase this - # to the number of cores. - #concurrent_compactors: 1 - - # Throttles compaction to the given total throughput across the entire - # system. The faster you insert data, the faster you need to compact in - # order to keep the sstable count down, but in general, setting this to - # 16 to 32 times the rate you are inserting data is more than sufficient. - # Setting this to 0 disables throttling. Note that this account for all types - # of compaction, including validation compaction. - compaction_throughput_mb_per_sec: 16 - - # When compacting, the replacement sstable(s) can be opened before they - # are completely written, and used in place of the prior sstables for - # any range that has been written. This helps to smoothly transfer reads - # between the sstables, reducing page cache churn and keeping hot rows hot - sstable_preemptive_open_interval_in_mb: 50 - - # Throttles all outbound streaming file transfers on this node to the - # given total throughput in Mbps. This is necessary because Cassandra does - # mostly sequential IO when streaming data during bootstrap or repair, which - # can lead to saturating the network connection and degrading rpc performance. - # When unset, the default is 200 Mbps or 25 MB/s. - # stream_throughput_outbound_megabits_per_sec: 200 - - # Throttles all streaming file transfer between the datacenters, - # this setting allows users to throttle inter dc stream throughput in addition - # to throttling all network stream traffic as configured with - # stream_throughput_outbound_megabits_per_sec - # When unset, the default is 200 Mbps or 25 MB/s - # inter_dc_stream_throughput_outbound_megabits_per_sec: 200 - - # How long the coordinator should wait for read operations to complete + storage_port: 7000 + jmx_port: 7199 + jmx_exporter_port: 7070 + +# Reflect the base of the cassandra.yaml content +# These list is completed and/or overridden in cassandra::instance +cassandra::base_instance_configuration: + num_tokens: 16 + allocate_tokens_for_local_replication_factor: 3 + disk_optimization_strategy: ssd + concurrent_compactors: 4 # should be min(nb core, nb disks) + internode_compression: dc # default dc possible all|dc|none + concurrent_reads: 64 # 16 x number of drives + concurrent_writes: 128 # 8 x number of cores + concurrent_counter_writes: 48 + commitlog_sync: periodic # default periodic + commitlog_sync_period_in_ms: 10000 # default 10000 + commitlog_total_space_in_mb: 16384 # default 8192 + commitlog_segment_size_in_mb: 256 # default 32 (due to oversize mutation on revision table) + partitioner: org.apache.cassandra.dht.Murmur3Partitioner + endpoint_snitch: GossipingPropertyFileSnitch + enable_user_defined_functions: true # needed by swh-storage + compaction_throughput_mb_per_sec: 160 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: true - - # Enables scripted UDFs (JavaScript UDFs). - # Java UDFs are always enabled, if enable_user_defined_functions is true. - # Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. - # This option has no effect, if enable_user_defined_functions is false. - enable_scripted_user_defined_functions: false - - # Enables materialized view creation on this node. - # Materialized views are considered experimental and are not recommended for production use. - enable_materialized_views: true - - # The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation. - # Lowering this value on Windows can provide much tighter latency and better throughput, however - # some virtualized environments may see a negative performance impact from changing this setting - # below their system default. The sysinternals 'clockres' tool can confirm your system's default - # setting. - windows_timer_interval: 1 - - - # Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from - # a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by - # the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys - # can still (and should!) be in the keystore and will be used on decrypt operations - # (to handle the case of key rotation). - # - # It is strongly recommended to download and install Java Cryptography Extension (JCE) - # Unlimited Strength Jurisdiction Policy Files for your version of the JDK. - # (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html) - # - # Currently, only the following file types are supported for transparent data encryption, although - # more are coming in future cassandra releases: commitlog, hints - transparent_data_encryption_options: - enabled: false - chunk_length_kb: 64 - cipher: AES/CBC/PKCS5Padding - key_alias: testing:1 - # CBC IV length for AES needs to be 16 bytes (which is also the default size) - # iv_length: 16 - key_provider: - - class_name: org.apache.cassandra.security.JKSKeyProvider - parameters: - - keystore: conf/.keystore - keystore_password: cassandra - store_type: JCEKS - key_password: cassandra - - - ##################### - # SAFETY THRESHOLDS # - ##################### - - # When executing a scan, within or across a partition, we need to keep the - # tombstones seen in memory so we can return them to the coordinator, which - # will use them to make sure other replicas also know about the deleted rows. - # With workloads that generate a lot of tombstones, this can cause performance - # problems and even exaust the server heap. - # (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) - # Adjust the thresholds here if you understand the dangers and want to - # scan more tombstones anyway. These thresholds may also be adjusted at runtime - # using the StorageService mbean. - tombstone_warn_threshold: 1000 - tombstone_failure_threshold: 100000 - - # Log WARN on any multiple-partition batch size exceeding this value. 5kb per batch by default. - # Caution should be taken on increasing the size of this threshold as it can lead to node instability. - batch_size_warn_threshold_in_kb: 5 - - # Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. - batch_size_fail_threshold_in_kb: 50 - - # Log WARN on any batches not of type LOGGED than span across more partitions than this limit - unlogged_batch_across_partitions_warn_threshold: 10 - - # Log a warning when compacting partitions larger than this value - compaction_large_partition_warning_threshold_mb: 100 - - # GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level - # Adjust the threshold based on your application throughput requirement - # By default, Cassandra logs GC Pauses greater than 200 ms at INFO level - gc_warn_threshold_in_ms: 1000 - - # Maximum size of any value in SSTables. Safety measure to detect SSTable corruption - # early. Any value size larger than this threshold will result into marking an SSTable - # as corrupted. This should be positive and less than 2048. - # max_value_size_in_mb: 256 - - # Back-pressure settings # - # If enabled, the coordinator will apply the back-pressure strategy specified below to each mutation - # sent to replicas, with the aim of reducing pressure on overloaded replicas. - back_pressure_enabled: false - # The back-pressure strategy applied. - # The default implementation, RateBasedBackPressure, takes three arguments: - # high ratio, factor, and flow type, and uses the ratio between incoming mutation responses and outgoing mutation requests. - # If below high ratio, outgoing mutations are rate limited according to the incoming rate decreased by the given factor; - # if above high ratio, the rate limiting is increased by the given factor; - # such factor is usually best configured between 1 and 10, use larger values for a faster recovery - # at the expense of potentially more dropped mutations; - # the rate limiting is applied according to the flow type: if FAST, it's rate limited at the speed of the fastest replica, - # if SLOW at the speed of the slowest one. - # New strategies can be added. Implementors need to implement org.apache.cassandra.net.BackpressureStrategy and - # provide a public constructor accepting a Map. - back_pressure_strategy: - - class_name: org.apache.cassandra.net.RateBasedBackPressure - parameters: - - high_ratio: 0.90 - factor: 5 - flow: FAST - - # Coalescing Strategies # - # Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). - # On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in - # virtualized environments, the point at which an application can be bound by network packet processing can be - # surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal - # doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process - # is sufficient for many applications such that no load starvation is experienced even without coalescing. - # There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages - # per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one - # trip to read from a socket, and all the task submission work can be done at the same time reducing context switching - # and increasing cache friendliness of network message processing. - # See CASSANDRA-8692 for details. - - # Strategy to use for coalescing messages in OutboundTcpConnection. - # Can be fixed, movingaverage, timehorizon, disabled (default). - # You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. - # otc_coalescing_strategy: DISABLED - - # How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first - # message is received before it will be sent with any accompanying messages. For moving average this is the - # maximum amount of time that will be waited as well as the interval at which messages must arrive on average - # for coalescing to be enabled. - # otc_coalescing_window_us: 200 - - # Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. - # otc_coalescing_enough_coalesced_messages: 8 - - # How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. - # Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory - # taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value - # will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU - # time and queue contention while iterating the backlog of messages. - # An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. - # - # otc_backlog_expiration_interval_ms: 200 - -cassandra::clusters: - azure: - cluster_name: SWH on Azure - seed_provider: - - class_name: org.apache.cassandra.locator.SimpleSeedProvider - parameters: - - seeds: 192.168.200.27 # cassandra01.euwest.azure.internal.softwareheritage.org + slow_query_log_timeout_in_ms: 1000 diff --git a/data/deployments/production/common.yaml b/data/deployments/production/common.yaml --- a/data/deployments/production/common.yaml +++ b/data/deployments/production/common.yaml @@ -24,3 +24,5 @@ swh::deploy::worker::loader_git::concurrency: 4 memcached::server::max_memory: 1224 + +cassandra::default_cluster_name: archive_production diff --git a/data/deployments/staging/common.yaml b/data/deployments/staging/common.yaml --- a/data/deployments/staging/common.yaml +++ b/data/deployments/staging/common.yaml @@ -389,3 +389,5 @@ key: "AAAAC3NzaC1lZDI1NTE5AAAAILRVodfvLudSiOdWOPDSoN5MIwZPbyZAyClfr/SQUK4w" swh::deploy::maven_index_exporter::url: maven-exporter.internal.staging.swh.network + +cassandra::default_cluster_name: archive_staging diff --git a/site-modules/profile/files/cassandra/99-cassandra.rules b/site-modules/profile/files/cassandra/99-cassandra.rules deleted file mode 100644 --- a/site-modules/profile/files/cassandra/99-cassandra.rules +++ /dev/null @@ -1,7 +0,0 @@ -# Readahead configuration for cassandra devices. -# -# https://docs.microsoft.com/en-us/azure/architecture/best-practices/cassandra#linux-read-ahead -# -# Managed by Puppet (class profile::cassandra::node), changes will be lost. - -ACTION=="add|change", KERNEL=="sd[c-z]|md*", ATTR{queue/rotational}="0", ATTR{bdi/read_ahead_kb}="8" diff --git a/site-modules/profile/files/cassandra/jvm.options b/site-modules/profile/files/cassandra/jvm.options deleted file mode 100644 --- a/site-modules/profile/files/cassandra/jvm.options +++ /dev/null @@ -1,256 +0,0 @@ -########################################################################### -# jvm.options # -# # -# - all flags defined here will be used by cassandra to startup the JVM # -# - one flag should be specified per line # -# - lines that do not start with '-' will be ignored # -# - only static flags are accepted (no variables or parameters) # -# - dynamic flags will be appended to these on cassandra-env # -########################################################################### - -###################### -# STARTUP PARAMETERS # -###################### - -# Uncomment any of the following properties to enable specific startup parameters - -# In a multi-instance deployment, multiple Cassandra instances will independently assume that all -# CPU processors are available to it. This setting allows you to specify a smaller set of processors -# and perhaps have affinity. -#-Dcassandra.available_processors=number_of_processors - -# The directory location of the cassandra.yaml file. -#-Dcassandra.config=directory - -# Sets the initial partitioner token for a node the first time the node is started. -#-Dcassandra.initial_token=token - -# Set to false to start Cassandra on a node but not have the node join the cluster. -#-Dcassandra.join_ring=true|false - -# Set to false to clear all gossip state for the node on restart. Use when you have changed node -# information in cassandra.yaml (such as listen_address). -#-Dcassandra.load_ring_state=true|false - -# Enable pluggable metrics reporter. See Pluggable metrics reporting in Cassandra 2.0.2. -#-Dcassandra.metricsReporterConfigFile=file - -# Set the port on which the CQL native transport listens for clients. (Default: 9042) -#-Dcassandra.native_transport_port=port - -# Overrides the partitioner. (Default: org.apache.cassandra.dht.Murmur3Partitioner) -#-Dcassandra.partitioner=partitioner - -# To replace a node that has died, restart a new node in its place specifying the address of the -# dead node. The new node must not have any data in its data directory, that is, it must be in the -# same state as before bootstrapping. -#-Dcassandra.replace_address=listen_address or broadcast_address of dead node - -# Allow restoring specific tables from an archived commit log. -#-Dcassandra.replayList=table - -# Allows overriding of the default RING_DELAY (30000ms), which is the amount of time a node waits -# before joining the ring. -#-Dcassandra.ring_delay_ms=ms - -# Set the port for the Thrift RPC service, which is used for client connections. (Default: 9160) -#-Dcassandra.rpc_port=port - -# Set the SSL port for encrypted communication. (Default: 7001) -#-Dcassandra.ssl_storage_port=port - -# Enable or disable the native transport server. See start_native_transport in cassandra.yaml. -# cassandra.start_native_transport=true|false - -# Enable or disable the Thrift RPC server. (Default: true) -#-Dcassandra.start_rpc=true/false - -# Set the port for inter-node communication. (Default: 7000) -#-Dcassandra.storage_port=port - -# Set the default location for the trigger JARs. (Default: conf/triggers) -#-Dcassandra.triggers_dir=directory - -# For testing new compaction and compression strategies. It allows you to experiment with different -# strategies and benchmark write performance differences without affecting the production workload. -#-Dcassandra.write_survey=true - -# To disable configuration via JMX of auth caches (such as those for credentials, permissions and -# roles). This will mean those config options can only be set (persistently) in cassandra.yaml -# and will require a restart for new values to take effect. -#-Dcassandra.disable_auth_caches_remote_configuration=true - -# To disable dynamic calculation of the page size used when indexing an entire partition (during -# initial index build/rebuild). If set to true, the page size will be fixed to the default of -# 10000 rows per page. -#-Dcassandra.force_default_indexing_page_size=true - -######################## -# GENERAL JVM SETTINGS # -######################## - -# enable assertions. highly suggested for correct application functionality. --ea - -# enable thread priorities, primarily so we can give periodic tasks -# a lower priority to avoid interfering with client workload --XX:+UseThreadPriorities - -# allows lowering thread priority without being root on linux - probably -# not necessary on Windows but doesn't harm anything. -# see http://tech.stolsvik.com/2010/01/linux-java-thread-priorities-workar --XX:ThreadPriorityPolicy=42 - -# Enable heap-dump if there's an OOM --XX:+HeapDumpOnOutOfMemoryError - -# Per-thread stack size. --Xss256k - -# Larger interned string table, for gossip's benefit (CASSANDRA-6410) --XX:StringTableSize=1000003 - -# Make sure all memory is faulted and zeroed on startup. -# This helps prevent soft faults in containers and makes -# transparent hugepage allocation more effective. --XX:+AlwaysPreTouch - -# Disable biased locking as it does not benefit Cassandra. --XX:-UseBiasedLocking - -# Enable thread-local allocation blocks and allow the JVM to automatically -# resize them at runtime. --XX:+UseTLAB --XX:+ResizeTLAB --XX:+UseNUMA - -# http://www.evanjones.ca/jvm-mmap-pause.html --XX:+PerfDisableSharedMem - -# Prefer binding to IPv4 network intefaces (when net.ipv6.bindv6only=1). See -# http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=6342561 (short version: -# comment out this entry to enable IPv6 support). --Djava.net.preferIPv4Stack=true - -### Debug options - -# uncomment to enable flight recorder -#-XX:+UnlockCommercialFeatures -#-XX:+FlightRecorder - -# uncomment to have Cassandra JVM listen for remote debuggers/profilers on port 1414 -#-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=1414 - -# uncomment to have Cassandra JVM log internal method compilation (developers only) -#-XX:+UnlockDiagnosticVMOptions -#-XX:+LogCompilation - -################# -# HEAP SETTINGS # -################# - -# Heap size is automatically calculated by cassandra-env based on this -# formula: max(min(1/2 ram, 1024MB), min(1/4 ram, 8GB)) -# That is: -# - calculate 1/2 ram and cap to 1024MB -# - calculate 1/4 ram and cap to 8192MB -# - pick the max -# -# For production use you may wish to adjust this for your environment. -# If that's the case, uncomment the -Xmx and Xms options below to override the -# automatic calculation of JVM heap memory. -# -# It is recommended to set min (-Xms) and max (-Xmx) heap sizes to -# the same value to avoid stop-the-world GC pauses during resize, and -# so that we can lock the heap in memory on startup to prevent any -# of it from being swapped out. -#-Xms4G -#-Xmx4G - -# Young generation size is automatically calculated by cassandra-env -# based on this formula: min(100 * num_cores, 1/4 * heap size) -# -# The main trade-off for the young generation is that the larger it -# is, the longer GC pause times will be. The shorter it is, the more -# expensive GC will be (usually). -# -# It is not recommended to set the young generation size if using the -# G1 GC, since that will override the target pause-time goal. -# More info: http://www.oracle.com/technetwork/articles/java/g1gc-1984535.html -# -# The example below assumes a modern 8-core+ machine for decent -# times. If in doubt, and if you do not particularly want to tweak, go -# 100 MB per physical CPU core. -#-Xmn800M - -################################### -# EXPIRATION DATE OVERFLOW POLICY # -################################### - -# Defines how to handle INSERT requests with TTL exceeding the maximum supported expiration date: -# * REJECT: this is the default policy and will reject any requests with expiration date timestamp after 2038-01-19T03:14:06+00:00. -# * CAP: any insert with TTL expiring after 2038-01-19T03:14:06+00:00 will expire on 2038-01-19T03:14:06+00:00 and the client will receive a warning. -# * CAP_NOWARN: same as previous, except that the client warning will not be emitted. -# -#-Dcassandra.expiration_date_overflow_policy=REJECT - -################# -# GC SETTINGS # -################# - -### CMS Settings - --XX:+UseParNewGC --XX:+UseConcMarkSweepGC --XX:+CMSParallelRemarkEnabled --XX:SurvivorRatio=8 --XX:MaxTenuringThreshold=1 --XX:CMSInitiatingOccupancyFraction=75 --XX:+UseCMSInitiatingOccupancyOnly --XX:CMSWaitDuration=10000 --XX:+CMSParallelInitialMarkEnabled --XX:+CMSEdenChunksRecordAlways -# some JVMs will fill up their heap when accessed via JMX, see CASSANDRA-6541 --XX:+CMSClassUnloadingEnabled - -### G1 Settings (experimental, comment previous section and uncomment section below to enable) - -## Use the Hotspot garbage-first collector. -#-XX:+UseG1GC -# -## Have the JVM do less remembered set work during STW, instead -## preferring concurrent GC. Reduces p99.9 latency. -#-XX:G1RSetUpdatingPauseTimePercent=5 -# -## Main G1GC tunable: lowering the pause target will lower throughput and vise versa. -## 200ms is the JVM default and lowest viable setting -## 1000ms increases throughput. Keep it smaller than the timeouts in cassandra.yaml. -#-XX:MaxGCPauseMillis=500 - -## Optional G1 Settings - -# Save CPU time on large (>= 16GB) heaps by delaying region scanning -# until the heap is 70% full. The default in Hotspot 8u40 is 40%. -#-XX:InitiatingHeapOccupancyPercent=70 - -# For systems with > 8 cores, the default ParallelGCThreads is 5/8 the number of logical cores. -# Otherwise equal to the number of cores when 8 or less. -# Machines with > 10 cores should try setting these to <= full cores. -#-XX:ParallelGCThreads=16 -# By default, ConcGCThreads is 1/4 of ParallelGCThreads. -# Setting both to the same value can reduce STW durations. -#-XX:ConcGCThreads=16 - -### GC logging options -- uncomment to enable - --XX:+PrintGCDetails --XX:+PrintGCDateStamps --XX:+PrintHeapAtGC --XX:+PrintTenuringDistribution --XX:+PrintGCApplicationStoppedTime --XX:+PrintPromotionFailure -#-XX:PrintFLSStatistics=1 -#-Xloggc:/var/log/cassandra/gc.log --XX:+UseGCLogFileRotation --XX:NumberOfGCLogFiles=10 --XX:GCLogFileSize=10M diff --git a/site-modules/profile/manifests/cassandra.pp b/site-modules/profile/manifests/cassandra.pp new file mode 100644 --- /dev/null +++ b/site-modules/profile/manifests/cassandra.pp @@ -0,0 +1,132 @@ +# Install the base components of a 4.x cassandra server +# Configure all the instances declared in cassandra::instances property +# +# Look at profile::cassandra:node for more information about the +# instance(s) configuration +class profile::cassandra { + + include profile::prometheus::jmx + $jmx_exporter_version = lookup('prometheus::jmx::version') + + $cassandra_user = 'cassandra' + $cassandra_group = 'cassandra' + $cassandra_home = '/home/cassandra' + + $cassandra_version = lookup('cassandra::version') + $cassandra_archive_name = "apache-cassandra-${cassandra_version}-bin.tar.gz" + $cassandra_bin_url = "https://dlcdn.apache.org/cassandra/${cassandra_version}/${cassandra_archive_name}" + $cassandra_bin_checksum_type = 'sha512' + $cassandra_bin_checksum = '188e131392ea0e48b46f24b1be297ef6335197f4480c9421328006507e069dce659ce3ce473906398273a5926e331960cbf824362e40cb4c74670cde95458349' + + $systemd_service = 'cassandra@.service' + + $download_path = "/opt/${cassandra_archive_name}" + + $cassandra_install_directory = "/opt/cassandra-${cassandra_version}" + + $cassandra_base_data_directory = lookup('cassandra::base_data_directory') + $cassandra_config_directory = lookup('cassandra::base_config_directory') + $cassandra_log_directory = lookup('cassandra::base_log_directory') + + $cassandra_nodes = lookup('cassandra::nodes') + $node_definition = $cassandra_nodes["$::fqdn"] + $instances = $node_definition['instances'] + + $default_instance_config = lookup('cassandra::default_instance_configuration') + $clusters_config = lookup('cassandra::clusters') + + group {$cassandra_group: + system => true, + } + + user {$cassandra_user: + system => true, + gid => $cassandra_group, + shell => '/usr/sbin/nologin', + home => $cassandra_home, + } + + file { [ + $cassandra_install_directory, + $cassandra_config_directory, + ]: + ensure => directory, + owner => 'root', + group => 'root', + mode => '0755' + } + + $config_files_to_copy = [ + 'jvm11-clients.options', + 'jvm-clients.options', + 'logback-tools.xml', + ] + + $config_files_to_copy.each | $file_name | { + file { "${cassandra_config_directory}/${file_name}": + ensure => present, + owner => 'root', + group => 'root', + mode => '0644', + source => "/opt/cassandra/conf/${file_name}", + require => [File[$cassandra_config_directory]], + } + } + + file { [ + $cassandra_base_data_directory, + $cassandra_log_directory, + ]: + ensure => directory, + owner => $cassandra_user, + group => $cassandra_group, + mode => '0750' + } + + ensure_packages(['openjdk-11-jdk', 'libnetty-java']) + + archive { 'cassandra': + path => $download_path, + extract => true, + extract_command => 'tar xzf %s --strip-components=1 --no-same-owner --no-same-permissions', + source => $cassandra_bin_url, + extract_path => $cassandra_install_directory, + checksum_type => $cassandra_bin_checksum_type, + checksum => $cassandra_bin_checksum, + creates => "${cassandra_install_directory}/bin/cassandra", + cleanup => true, + user => 'root', + group => 'root', + require => File[$cassandra_install_directory], + } + -> file {'/opt/cassandra': + ensure => link, + force => true, + target => $cassandra_install_directory + } + + ::systemd::unit_file {$systemd_service: + ensure => present, + content => template('profile/cassandra/cassandra.service.erb'), + } + + file {"${cassandra_config_directory}/jmx_exporter.yml": + ensure => present, + owner => 'root', + group => 'root', + mode => '0644', + source => "https://raw.githubusercontent.com/prometheus/jmx_exporter/parent-${jmx_exporter_version}/example_configs/cassandra.yml", + } + + $instances.each | $instance_name, $instance_config | { + $merged_instance_config = $default_instance_config + $instance_config + $cluster_config = $clusters_config[$merged_instance_config["cluster_name"]] + $merged_config = $cluster_config + $merged_instance_config + + profile::cassandra::instance{$instance_name: + config => $merged_config + } + } + +} + diff --git a/site-modules/profile/manifests/cassandra/instance.pp b/site-modules/profile/manifests/cassandra/instance.pp new file mode 100644 --- /dev/null +++ b/site-modules/profile/manifests/cassandra/instance.pp @@ -0,0 +1,112 @@ +# Configure a cassandra node on a server +# Several nodes can coexist on a same server +# +# It supposes the profile::cassandra class +# was installed before this +define profile::cassandra::instance ( + $instance_name = $name, + $config = {} +) { + + $service_name = "cassandra@${instance_name}.service" + + $listen_network = lookup('internal_network') + $listen_address = ip_for_network($listen_network) + + $cassandra_base_data_dir = lookup('cassandra::base_data_directory') + $instance_base_data_dir = "${cassandra_base_data_dir}/${instance_name}" + $cassandra_config_dir = lookup('cassandra::base_config_directory') + $cassandra_log_dir = lookup('cassandra::base_log_directory') + + $base_data_dir = "${instance_base_data_dir}/data" + $commitlog_dir = "${instance_base_data_dir}/commitlog" + + $data_dir = "${base_data_dir}/data" + $hints_dir = "${data_dir}/hints" + $saved_caches_dir = "${data_dir}/saved_caches" + + $config_dir = "${cassandra_config_dir}/${instance_name}" + $log_dir = "${cassandra_log_dir}/${instance_name}" + + $jmx_exporter_path = $::profile::prometheus::jmx::jar_path + + $base_configuration = lookup('cassandra::base_instance_configuration') + $instance_configuration = { + cluster_name => $config["cluster_name"], + data_file_directories => [ $base_data_dir, ], + commitlog_directory => $commitlog_dir, + hints_directory => $hints_dir, + saved_caches_directory => $saved_caches_dir, + listen_address => $listen_address, + native_transport_port => $config['native_transport_port'], + storage_port => $config['storage_port'], + seed_provider => $config['seed_provider'] + } + + $computed_configuration = $base_configuration + $instance_configuration + + file {[ + $instance_base_data_dir, + $base_data_dir, + # $commitlog_dir, + $config_dir, + $log_dir, + ] : + ensure => directory, + owner => $::profile::cassandra::cassandra_user, + group => $::profile::cassandra::cassandra_group, + require => [ + # File[$::profile::cassandra::cassandra_base_data_directory], + # File[$::profile::cassandra::cassandra_config_directory], + # File[$::profile::cassandra::cassandra_log_directory], + ] + } + + ::systemd::dropin_file { "${service_name}.d/parameters.conf": + ensure => present, + unit => "cassandra@${instance_name}.service", + filename => 'parameters.conf', + content => template('profile/cassandra/instance-parameters.conf.erb'), + } + + service {$service_name: + enable => true, + } + + $config_files_to_copy = [ + 'jvm11-server.options', + 'jvm-server.options', + 'logback.xml', + 'cassandra-env.sh', + ] + + $config_files_to_copy.each | $file_name | { + file { "${config_dir}/${file_name}": + ensure => present, + owner => 'root', + group => 'root', + mode => '0644', + source => "/opt/cassandra/conf/${file_name}", + require => [File[$config_dir]], + } + } + + file { "${config_dir}/cassandra.yaml": + ensure => present, + owner => 'root', + group => 'root', + mode => '0644', + content => to_yaml($computed_configuration), + require => [File[$config_dir]], + } + + file { "${config_dir}/cassandra-rackdc.properties": + ensure => present, + owner => 'root', + group => 'root', + mode => '0644', + content => template('profile/cassandra/cassandra-rackdc.properties.erb'), + require => [File[$config_dir]], + } + +} diff --git a/site-modules/profile/manifests/cassandra/node.pp b/site-modules/profile/manifests/cassandra/node.pp deleted file mode 100644 --- a/site-modules/profile/manifests/cassandra/node.pp +++ /dev/null @@ -1,120 +0,0 @@ -# Definition of a cassandra node -class profile::cassandra::node { - include profile::cassandra::apt_config - - $basedir = '/srv/cassandra' - $commitlogdir = "${basedir}/commitlog" - $datadir = "${basedir}/data" - $hintsdir = "${basedir}/hints" - - file {$basedir: - ensure => 'directory', - owner => 'cassandra', - group => 'cassandra', - } - - $baseline_settings = lookup('cassandra::baseline_settings') - - $cluster = lookup('cassandra::cluster') - $cluster_settings = lookup('cassandra::clusters', Hash)[$cluster] - - $listen_network = lookup('cassandra::listen_network', Optional[String], 'first', undef) - $listen_address = lookup('cassandra::listen_address', Optional[String], 'first', undef) - $actual_listen_address = pick($listen_address, ip_for_network($listen_network)) - - $listen_settings = { - listen_address => $actual_listen_address, - rpc_address => $actual_listen_address - } - - $exporter_version = lookup('cassandra::exporter::version') - $exporter_filename = "cassandra-exporter-agent-${exporter_version}.jar" - $exporter_url = "https://github.com/instaclustr/cassandra-exporter/releases/download/v${exporter_version}/${exporter_filename}" - - $exporter_base_directory = '/opt/prometheus-cassandra-exporter' - $exporter_path = "${exporter_base_directory}/${exporter_filename}" - $exporter_config = "/etc/cassandra/cassandra-exporter.options" - - file {$exporter_base_directory: - ensure => 'directory', - mode => '0644', - owner => 'root', - group => 'root', - } - - # Use wget to work around https://tickets.puppetlabs.com/browse/PUP-6380 - exec {'download-cassandra-exporter': - command => "wget --quiet ${exporter_url} -O ${exporter_path}", - path => ['/sbin', '/usr/sbin', '/bin', '/usr/bin'], - creates => $exporter_path, - require => File[$exporter_base_directory], - } - - $exporter_network = lookup('cassandra::exporter::listen_network', Optional[String], 'first', undef) - $exporter_address = lookup('cassandra::exporter::listen_address', Optional[String], 'first', undef) - $actual_exporter_address = pick($exporter_address, ip_for_network($exporter_network)) - - $exporter_port = lookup('cassandra::exporter::listen_port') - - $exporter_target = "${actual_exporter_address}:${exporter_port}" - - file {$exporter_config: - ensure => 'present', - owner => 'root', - group => 'root', - content => template('profile/cassandra/cassandra-exporter.options.erb'), - notify => Service['cassandra'], - } - - ::systemd::unit_file {'cassandra.service': - content => template('profile/cassandra/cassandra.service.erb'), - notify => Service['cassandra'], - require => [ - Exec['download-cassandra-exporter'], - File[$exporter_config], - ], - } - - ::profile::prometheus::export_scrape_config {'cassandra': - target => $exporter_target, - labels => { - cluster => $cluster, - } - } - - package {'openjdk-8-jre-headless': - ensure => 'installed', - } - -> class {'::cassandra': - baseline_settings => $baseline_settings, - commitlog_directory => $commitlogdir, - data_file_directories => [$datadir], - hints_directory => $hintsdir, - settings => $cluster_settings + $listen_settings, - } - - file {'/etc/cassandra/jvm.options': - ensure => 'present', - owner => 'root', - group => 'root', - mode => '0644', - source => 'puppet:///modules/profile/cassandra/jvm.options', - require => Package['cassandra'], - notify => Service['cassandra'], - } - - file {'/etc/udev/rules.d/99-cassandra.rules': - ensure => 'present', - owner => 'root', - group => 'root', - mode => '0644', - source => 'puppet:///modules/profile/cassandra/99-cassandra.rules', - notify => Exec['cassandra-reload-udev-rules'], - } - - exec {'cassandra-reload-udev-rules': - command => 'udevadm control --reload-rules', - refreshonly => true, - path => ['/usr/local/sbin', '/usr/local/bin', '/usr/sbin', '/usr/bin', '/sbin', '/bin'], - } -} diff --git a/site-modules/profile/templates/cassandra/cassandra-rackdc.properties.erb b/site-modules/profile/templates/cassandra/cassandra-rackdc.properties.erb new file mode 100644 --- /dev/null +++ b/site-modules/profile/templates/cassandra/cassandra-rackdc.properties.erb @@ -0,0 +1,2 @@ +dc=<%= @config["datacenter"] %> +rack=<%= @config["rack"] %> diff --git a/site-modules/profile/templates/cassandra/cassandra.service.erb b/site-modules/profile/templates/cassandra/cassandra.service.erb --- a/site-modules/profile/templates/cassandra/cassandra.service.erb +++ b/site-modules/profile/templates/cassandra/cassandra.service.erb @@ -1,16 +1,14 @@ -# Managed by puppet (class profile::cassandra::node); Changes will be lost. +# Managed by puppet (class profile::cassandra); Changes will be lost. [Unit] Description=Cassandra After=network.target [Service] -User=cassandra -Group=cassandra -Environment=JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64 -Environment=JVM_EXTRA_OPTS=-javaagent:<%= @exporter_path %>=@<%= @exporter_config %> -EnvironmentFile=-/etc/default/cassandra -ExecStart=/usr/sbin/cassandra -f +User=<%= @cassandra_user %> +Group=<%= @cassandra_group %> + +ExecStart=/opt/cassandra/bin/cassandra -f LimitNOFILE=100000 LimitMEMLOCK=infinity LimitNPROC=32768 diff --git a/site-modules/profile/templates/cassandra/cassandra.yaml.erb b/site-modules/profile/templates/cassandra/cassandra.yaml.erb new file mode 100644 --- /dev/null +++ b/site-modules/profile/templates/cassandra/cassandra.yaml.erb @@ -0,0 +1,76 @@ +cluster_name: <%= @config["cluster_name"] %> +num_tokens: 16 +allocate_tokens_for_local_replication_factor: 3 +data_file_directories: + - <%= @base_data_dir %> + +commitlog_directory: <%= @commitlog_dir %> + +hints_directory: <%= @hints_dir %> + +saved_caches_directory: <%= @saved_caches_dir %> + +# local_system_data_file_directory: {{ cassandra_data_dir_system }} + +disk_optimization_strategy: ssd + +listen_address: <%= @listen_address %> +native_transport_port: <%= @config["native_transport_port"] %> +storage_port: <%= @config["storage_port"] %> + +concurrent_compactors: 4 # should be min(nb core, nb disks) + +internode_compression: dc # default dc possible all|dc|none + +concurrent_reads: 64 # 16 x number of drives +concurrent_writes: 128 # 8 x number of cores +concurrent_counter_writes: 48 + +commitlog_sync: periodic # default periodic +commitlog_sync_period_in_ms: 10000 # default 10000 +commitlog_total_space_in_mb: 16384 # default 8192 +commitlog_segment_size_in_mb: 256 # default 32 (due to oversize mutation on revision table) + +partitioner: org.apache.cassandra.dht.Murmur3Partitioner +endpoint_snitch: GossipingPropertyFileSnitch + +seed_provider: <%= @config["seed_provider"].to_yaml().delete_prefix("---") %> + +# needed by swh-storage +enable_user_defined_functions: true + +# TODO Test this options effects +# disk_failure_policy: +# cdc_enabled +#end + +# Trying to reduce cassandra_compaction_pendingtasks +compaction_throughput_mb_per_sec: 160 + +# https://forge.softwareheritage.org/source/cassandra-replayer-deployment/browse/master/playbooks/templates/cassandra.yaml$854 +# How long the coordinator should wait for read operations to complete. +# Lowest acceptable value is 10 ms. +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete. +# Lowest acceptable value is 10 ms. +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete. +# Lowest acceptable value is 10 ms. +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete. +# Lowest acceptable value is 10 ms. +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. +# Lowest acceptable value is 10 ms. +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.) +# Lowest acceptable value is 10 ms. +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations. +# Lowest acceptable value is 10 ms. +request_timeout_in_ms: 10000 + +slow_query_log_timeout_in_ms: 1000 diff --git a/site-modules/profile/templates/cassandra/instance-parameters.conf.erb b/site-modules/profile/templates/cassandra/instance-parameters.conf.erb new file mode 100644 --- /dev/null +++ b/site-modules/profile/templates/cassandra/instance-parameters.conf.erb @@ -0,0 +1,13 @@ +# Managed by puppet (class profile::cassandra::node); Changes will be lost. + +[Unit] +Description=Cassandra <%= @instance_name %> instance +After=network.target + +[Service] +Environment=JVM_EXTRA_OPTS="-javaagent:<%= @jmx_exporter_path %>=<%= @config["jmx_exporter_port"] %>:/etc/cassandra/jmx_exporter.yml -Dcassandra.jmx.local.port=<%= @config["jmx_port"] %> -Dcom.sun.management.jmxremote.authenticate=false" +Environment=CASSANDRA_CONF=<%= @config_dir %> +Environment=CASSANDRA_LOG_DIR=<%= @log_dir %> + +[Install] +WantedBy=multi-user.target diff --git a/site-modules/role/manifests/swh_cassandra_node.pp b/site-modules/role/manifests/swh_cassandra_node.pp --- a/site-modules/role/manifests/swh_cassandra_node.pp +++ b/site-modules/role/manifests/swh_cassandra_node.pp @@ -1,5 +1,6 @@ # Deployment of a cassandra node class role::swh_cassandra_node inherits role::swh_base { # include profile::cassandra::node + include profile::cassandra include profile::docker }