##################### ElasticSearch Configuration Example #####################
# This file contains an overview of various configuration settings, # targeted at operations staff. Application developers should # consult the guide at <http://elasticsearch.org/guide>. # # The installation procedure is covered at # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup.html>. # # ElasticSearch comes with reasonable defaults for most settings, # so you can try it out without bothering with configuration. # # Most of the time, these defaults are just fine for running a production # cluster. If you're fine-tuning your cluster, or wondering about the # effect of certain configuration option, please _do ask_ on the # mailing list or IRC channel [http://elasticsearch.org/community]. # Any element in the configuration can be replaced with environment variables # by placing them in ${...} notation. For example: # # node.rack: ${RACK_ENV_VAR} # For information on supported formats and syntax for the config file, see # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup-configuration.html> ################################### Cluster ################################### # Cluster name identifies your cluster for auto-discovery. If you're running # multiple clusters on the same network, make sure you're using unique names. # cluster.name: graylog #################################### Node ##################################### # Node names are generated dynamically on startup, so you're relieved # from configuring them manually. You can tie this node to a specific name: # # node.name: "Franz Kafka" # Every node can be configured to allow or deny being eligible as the master, # and to allow or deny to store the data. # # Allow this node to be eligible as a master node (enabled by default): # # node.master: true # # Allow this node to store data (enabled by default): # # node.data: true # You can exploit these settings to design advanced cluster topologies. # # 1. You want this node to never become a master node, only to hold data. # This will be the "workhorse" of your cluster. # # node.master: false # node.data: true # # 2. You want this node to only serve as a master: to not store any data and # to have free resources. This will be the "coordinator" of your cluster. # # node.master: true # node.data: false # # 3. You want this node to be neither master nor data node, but # to act as a "search load balancer" (fetching data from nodes, # aggregating results, etc.) # # node.master: false # node.data: false # Use the Cluster Health API [http://localhost:9200/_cluster/health], the # Node Info API [http://localhost:9200/_cluster/nodes] or GUI tools # such as <http://github.com/lukas-vlcek/bigdesk> and # <http://mobz.github.com/elasticsearch-head> to inspect the cluster state. # A node can have generic attributes associated with it, which can later be used # for customized shard allocation filtering, or allocation awareness. An attribute # is a simple key value pair, similar to node.key: value, here is an example: # # node.rack: rack314 # By default, multiple nodes are allowed to start from the same installation location # to disable it, set the following: # node.max_local_storage_nodes: 1 #################################### Index #################################### # You can set a number of options (such as shard/replica options, mapping # or analyzer definitions, translog settings, ...) for indices globally, # in this file. # # Note, that it makes more sense to configure index settings specifically for # a certain index, either when creating it or by using the index templates API. # # See <http://elasticsearch.org/guide/en/elasticsearch/reference/current/index-modules.html> and # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/indices-create-index.html> # for more information. # Set the number of shards (splits) of an index (5 by default): # # index.number_of_shards: 5 # Set the number of replicas (additional copies) of an index (1 by default): # # index.number_of_replicas: 1 # Note, that for development on a local machine, with small indices, it usually # makes sense to "disable" the distributed features: # #index.number_of_shards: 1 #index.number_of_replicas: 0 # These settings directly affect the performance of index and search operations # in your cluster. Assuming you have enough machines to hold shards and # replicas, the rule of thumb is: # # 1. Having more *shards* enhances the _indexing_ performance and allows to # _distribute_ a big index across machines. # 2. Having more *replicas* enhances the _search_ performance and improves the # cluster _availability_. # # The "number_of_shards" is a one-time setting for an index. # # The "number_of_replicas" can be increased or decreased anytime, # by using the Index Update Settings API. # # ElasticSearch takes care about load balancing, relocating, gathering the # results from nodes, etc. Experiment with different settings to fine-tune # your setup. # Use the Index Status API (<http://localhost:9200/A/_status>) to inspect # the index status. #################################### Paths #################################### # Path to directory containing configuration (this file and logging.yml): # # path.conf: /path/to/conf # Path to directory where to store index data allocated for this node. # path.data: /var/opt/graylog/data/elasticsearch # # Can optionally include more than one location, causing data to be striped across # the locations (a la RAID 0) on a file level, favouring locations with most free # space on creation. For example: # # path.data: /path/to/data1,/path/to/data2 # Path to temporary files: # # path.work: /path/to/work # Path to log files: # path.logs: /var/log/graylog/elasticsearch/ # Path to where plugins are installed: # # path.plugins: /path/to/plugins #################################### Plugin ################################### # If a plugin listed here is not installed for current node, the node will not start. # # plugin.mandatory: mapper-attachments,lang-groovy ################################### Memory #################################### # ElasticSearch performs poorly when JVM starts swapping: you should ensure that # it _never_ swaps. # # Set this property to true to lock the memory: # # bootstrap.mlockall: true # Make sure that the ES_MIN_MEM and ES_MAX_MEM environment variables are set # to the same value, and that the machine has enough memory to allocate # for ElasticSearch, leaving enough memory for the operating system itself. # # You should also make sure that the ElasticSearch process is allowed to lock # the memory, eg. by using `ulimit -l unlimited`. ############################## Network And HTTP ############################### # ElasticSearch, by default, binds itself to the 0.0.0.0 address, and listens # on port [9200-9300] for HTTP traffic and on port [9300-9400] for node-to-node # communication. (the range means that if the port is busy, it will automatically # try the next port). # Set the bind address specifically (IPv4 or IPv6): # # network.bind_host: 192.168.0.1 # Set the address other nodes will use to communicate with this node. If not # set, it is automatically derived. It must point to an actual IP address. # # network.publish_host: 192.168.0.1 # Set both 'bind_host' and 'publish_host': # network.host: 172.31.62.98 # Set a custom port for the node to node communication (9300 by default): # # transport.tcp.port: 9300 # Enable compression for all communication between nodes (disabled by default): # # transport.tcp.compress: true # Set a custom port to listen for HTTP traffic: # # http.port: 9200 # Set a custom allowed content length: # # http.max_content_length: 100mb # Disable HTTP completely: # # http.enabled: false ################################### Gateway ################################### # The gateway allows for persisting the cluster state between full cluster # restarts. Every change to the state (such as adding an index) will be stored # in the gateway, and when the cluster starts up for the first time, # it will read its state from the gateway. # There are several types of gateway implementations. For more information, see # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-gateway.html>. # The default gateway type is the "local" gateway (recommended): # # gateway.type: local # Settings below control how and when to start the initial recovery process on # a full cluster restart (to reuse as much local data as possible when using shared # gateway). # Allow recovery process after N nodes in a cluster are up: # # gateway.recover_after_nodes: 1 # Set the timeout to initiate the recovery process, once the N nodes # from previous setting are up (accepts time value): # # gateway.recover_after_time: 5m # Set how many nodes are expected in this cluster. Once these N nodes # are up (and recover_after_nodes is met), begin recovery process immediately # (without waiting for recover_after_time to expire): # # gateway.expected_nodes: 2 ############################# Recovery Throttling ############################# # These settings allow to control the process of shards allocation between # nodes during initial recovery, replica allocation, rebalancing, # or when adding and removing nodes. # Set the number of concurrent recoveries happening on a node: # # 1. During the initial recovery # # cluster.routing.allocation.node_initial_primaries_recoveries: 4 # # 2. During adding/removing nodes, rebalancing, etc # # cluster.routing.allocation.node_concurrent_recoveries: 2 # Set to throttle throughput when recovering (eg. 100mb, by default 20mb): # # indices.recovery.max_bytes_per_sec: 20mb # Set to limit the number of open concurrent streams when # recovering a shard from a peer: # # indices.recovery.concurrent_streams: 5 ################################## Discovery ################################## # Discovery infrastructure ensures nodes can be found within a cluster # and master node is elected. Multicast discovery is the default. # Set to ensure a node sees N other master eligible nodes to be considered # operational within the cluster. Its recommended to set it to a higher value # than 1 when running more than 2 nodes in the cluster. # # discovery.zen.minimum_master_nodes: 1 # Set the time to wait for ping responses from other nodes when discovering. # Set this option to a higher value on a slow or congested network # to minimize discovery failures: # discovery.zen.ping.timeout: 10s # For more information, see # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-zen.html> # Unicast discovery allows to explicitly control which nodes will be used # to discover the cluster. It can be used when multicast is not present, # or to restrict the cluster communication-wise. # # 1. Disable multicast discovery (enabled by default): # discovery.zen.ping.multicast.enabled: false # # 2. Configure an initial list of master nodes in the cluster # to perform discovery when new nodes (master or data) are started: # discovery.zen.ping.unicast.hosts: ["172.31.62.98:9300"] # EC2 discovery allows to use AWS EC2 API in order to perform discovery. # # You have to install the cloud-aws plugin for enabling the EC2 discovery. # # For more information, see # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-ec2.html> # # See <http://elasticsearch.org/tutorials/elasticsearch-on-ec2/> # for a step-by-step tutorial. ################################## Slow Log ################################## # Shard level query and fetch threshold logging. #index.search.slowlog.threshold.query.warn: 10s #index.search.slowlog.threshold.query.info: 5s #index.search.slowlog.threshold.query.debug: 2s #index.search.slowlog.threshold.query.trace: 500ms #index.search.slowlog.threshold.fetch.warn: 1s #index.search.slowlog.threshold.fetch.info: 800ms #index.search.slowlog.threshold.fetch.debug: 500ms #index.search.slowlog.threshold.fetch.trace: 200ms #index.indexing.slowlog.threshold.index.warn: 10s #index.indexing.slowlog.threshold.index.info: 5s #index.indexing.slowlog.threshold.index.debug: 2s #index.indexing.slowlog.threshold.index.trace: 500ms ################################## GC Logging ################################ #monitor.jvm.gc.young.warn: 1000ms #monitor.jvm.gc.young.info: 700ms #monitor.jvm.gc.young.debug: 400ms #monitor.jvm.gc.old.warn: 10s #monitor.jvm.gc.old.info: 5s #monitor.jvm.gc.old.debug: 2s *GRAY LOG CONFIGURATION* # If you are running more than one instances of graylog-server you have to select one of these # instances as master. The master will perform some periodical tasks that non-masters won't perform. is_master = true # The auto-generated node ID will be stored in this file and read after restarts. It is a good idea # to use an absolute file path here if you are starting graylog-server from init scripts or similar. node_id_file = /var/opt/graylog/graylog-server-node-id # You MUST set a secret to secure/pepper the stored user passwords here. Use at least 64 characters. # Generate one by using for example: pwgen -N 1 -s 96 password_secret = omg # the default root user is named 'admin' root_username = lucky # You MUST specify a hash password for the root user (which you only need to initially set up the # system and in case you lose connectivity to your authentication backend) # This password cannot be changed using the API or via the web interface. If you need to change it, # modify it in this file. # Create one by using for example: echo -n yourpassword | shasum -a 256 # and put the resulting hash value into the following line root_password_sha2 = 8c6976e5b5410415bde908bd4dee15dfb167a9c87 # The email address of the root user. # Default is empty #root_email = "" # The time zone setting of the root user. # Default is UTC root_timezone = Etc/UTC # Set plugin directory here (relative or absolute) plugin_dir = /opt/graylog/plugin # REST API listen URI. Must be reachable by other graylog-server nodes if you run a cluster. rest_listen_uri = http://0.0.0.0:12900/ # Web interface listen URI web_listen_uri = http://0.0.0.0:9000/ # REST API transport address. Defaults to the value of rest_listen_uri. Exception: If rest_listen_uri # is set to a wildcard IP address (0.0.0.0) the first non-loopback IPv4 system address is used. # If set, his will be promoted in the cluster discovery APIs, so other nodes may try to connect on # this address and it is used to generate URLs addressing entities in the REST API. (see rest_listen_uri) # You will need to define this, if your Graylog server is running behind a HTTP proxy that is rewriting # the scheme, host name or URI. # Enable CORS headers for REST api. This is necessary for JS-clients accessing the server directly. # If these are disabled, modern browsers will not be able to retrieve resources from the server. # This is disabled by default. Uncomment the next line to enable it. rest_enable_cors = true # Enable GZIP support for REST api. This compresses API responses and therefore helps to reduce # overall round trip times. This is disabled by default. Uncomment the next line to enable it. #rest_enable_gzip = true # Enable HTTPS support for the REST API. This secures the communication with the REST API with # TLS to prevent request forgery and eavesdropping. This is disabled by default. Uncomment the # next line to enable it. #rest_enable_tls = true # The X.509 certificate file to use for securing the REST API. #rest_tls_cert_file = /path/to/graylog2.crt # The private key to use for securing the REST API. #rest_tls_key_file = /path/to/graylog2.key # The password to unlock the private key used for securing the REST API. #rest_tls_key_password = secret # The maximum size of a single HTTP chunk in bytes. #rest_max_chunk_size = 8192 # The maximum size of the HTTP request headers in bytes. #rest_max_header_size = 8192 # The maximal length of the initial HTTP/1.1 line in bytes. #rest_max_initial_line_length = 4096 # The size of the thread pool used exclusively for serving the REST API. #rest_thread_pool_size = 16 # The size of the worker thread pool used exclusively for serving the REST API. #rest_worker_threads_max_pool_size = 16 # Embedded Elasticsearch configuration file # pay attention to the working directory of the server, maybe use an absolute path here #elasticsearch_config_file = /etc/graylog-elasticsearch.yml # Disable checking the version of Elasticsearch for being compatible with this Graylog release. # WARNING: Using Graylog with unsupported and untested versions of Elasticsearch may lead to data loss! #elasticsearch_disable_version_check = true # Disable message retention on this node, i. e. disable Elasticsearch index rotation. #no_retention = false # How many Elasticsearch shards and replicas should be used per index? Note that this only applies to newly created indices. elasticsearch_shards = 1 elasticsearch_replicas = 0 # Prefix for all Elasticsearch indices and index aliases managed by Graylog. elasticsearch_index_prefix = graylog # Do you want to allow searches with leading wildcards? This can be extremely resource hungry and should only # be enabled with care. See also: http://graylog2.org/resources/documentation/general/queries allow_leading_wildcard_searches = true # Do you want to allow searches to be highlighted? Depending on the size of your messages this can be memory hungry and # should only be enabled after making sure your Elasticsearch cluster has enough memory. allow_highlighting = false # settings to be passed to elasticsearch's client (overriding those in the provided elasticsearch_config_file) # all these # this must be the same as for your Elasticsearch cluster elasticsearch_cluster_name = graylog # we don't want the graylog server to store any data, or be master node #elasticsearch_node_master = false #elasticsearch_node_data = false # use a different port if you run multiple Elasticsearch nodes on one machine #elasticsearch_transport_tcp_port = 9350 # we don't need to run the embedded HTTP server here elasticsearch_http_enabled = false #elasticsearch_discovery_zen_ping_multicast_enabled = false elasticsearch_discovery_zen_ping_unicast_hosts = 172.31.62.98:9300 # Change the following setting if you are running into problems with timeouts during Elasticsearch cluster discovery. # The setting is specified in milliseconds, the default is 5000ms (5 seconds). elasticsearch_cluster_discovery_timeout = 5000 # the following settings allow to change the bind addresses for the Elasticsearch client in graylog # these settings are empty by default, letting Elasticsearch choose automatically, # override them here or in the 'elasticsearch_config_file' if you need to bind to a special address # refer to http://www.elasticsearch.org/guide/en/elasticsearch/reference/1.3/modules-network.html # for special values here elasticsearch_network_host = 0.0.0.0 # elasticsearch_network_bind_host = # elasticsearch_network_publish_host = # The total amount of time discovery will look for other Elasticsearch nodes in the cluster # before giving up and declaring the current node master. elasticsearch_discovery_initial_state_timeout = 3s # Analyzer (tokenizer) to use for message and full_message field. The "standard" filter usually is a good idea. # All supported analyzers are: standard, simple, whitespace, stop, keyword, pattern, language, snowball, custom # Elasticsearch documentation: http://www.elasticsearch.org/guide/reference/index-modules/analysis/ # Note that this setting only takes effect on newly created indices. elasticsearch_analyzer = standard # Global request timeout for Elasticsearch requests (e. g. during search, index creation, or index time-range # calculations) based on a best-effort to restrict the runtime of Elasticsearch operations. # Default: 1m #elasticsearch_request_timeout = 1m # Batch size for the Elasticsearch output. This is the maximum (!) number of messages the Elasticsearch output # module will get at once and write to Elasticsearch in a batch call. If the configured batch size has not been # reached within output_flush_interval seconds, everything that is available will be flushed at once. Remember # that every outputbuffer processor manages its own batch and performs its own batch write calls. # ("outputbuffer_processors" variable) output_batch_size = 500 # Flush interval (in seconds) for the Elasticsearch output. This is the maximum amount of time between two # batches of messages written to Elasticsearch. It is only effective at all if your minimum number of messages # for this time period is less than output_batch_size * outputbuffer_processors. output_flush_interval = 1 # As stream outputs are loaded only on demand, an output which is failing to initialize will be tried over and # over again. To prevent this, the following configuration options define after how many faults an output will # not be tried again for an also configurable amount of seconds. output_fault_count_threshold = 5 output_fault_penalty_seconds = 30 # The number of parallel running processors. # Raise this number if your buffers are filling up. processbuffer_processors = 5 outputbuffer_processors = 3 #outputbuffer_processor_keep_alive_time = 5000 #outputbuffer_processor_threads_core_pool_size = 3 #outputbuffer_processor_threads_max_pool_size = 30 # UDP receive buffer size for all message inputs (e. g. SyslogUDPInput). #udp_recvbuffer_sizes = 1048576 # Wait strategy describing how buffer processors wait on a cursor sequence. (default: sleeping) # Possible types: # - yielding # Compromise between performance and CPU usage. # - sleeping # Compromise between performance and CPU usage. Latency spikes can occur after quiet periods. # - blocking # High throughput, low latency, higher CPU usage. # - busy_spinning # Avoids syscalls which could introduce latency jitter. Best when threads can be bound to specific CPU cores. processor_wait_strategy = blocking # Size of internal ring buffers. Raise this if raising outputbuffer_processors does not help anymore. # For optimum performance your LogMessage objects in the ring buffer should fit in your CPU L3 cache. # Start server with --statistics flag to see buffer utilization. # Must be a power of 2. (512, 1024, 2048, ...) ring_size = 65536 inputbuffer_ring_size = 65536 inputbuffer_processors = 2 inputbuffer_wait_strategy = blocking # Enable the disk based message journal. message_journal_enabled = true # The directory which will be used to store the message journal. The directory must me exclusively used by Graylog and # must not contain any other files than the ones created by Graylog itself. message_journal_dir = /var/opt/graylog/data/journal # Journal hold messages before they could be written to Elasticsearch. # For a maximum of 12 hours or 5 GB whichever happens first. # During normal operation the journal will be smaller. #message_journal_max_age = 12h message_journal_max_size = 1gb #message_journal_flush_age = 1m #message_journal_flush_interval = 1000000 #message_journal_segment_age = 1h #message_journal_segment_size = 100mb # Number of threads used exclusively for dispatching internal events. Default is 2. async_eventbus_processors = 2 # How many seconds to wait between marking node as DEAD for possible load balancers and starting the actual # shutdown process. Set to 0 if you have no status checking load balancers in front. lb_recognition_period_seconds = 3 # Every message is matched against the configured streams and it can happen that a stream contains rules which # take an unusual amount of time to run, for example if its using regular expressions that perform excessive backtracking. # This will impact the processing of the entire server. To keep such misbehaving stream rules from impacting other # streams, Graylog limits the execution time for each stream. # The default values are noted below, the timeout is in milliseconds. # If the stream matching for one stream took longer than the timeout value, and this happened more than "max_faults" times # that stream is disabled and a notification is shown in the web interface. # stream_processing_timeout = 2000 # stream_processing_max_faults = 3 # Length of the interval in seconds in which the alert conditions for all streams should be checked # and alarms are being sent. alert_check_interval = 60 # Since 0.21 the graylog server supports pluggable output modules. This means a single message can be written to multiple # outputs. The next setting defines the timeout for a single output module, including the default output module where all # messages end up. This setting is specified in milliseconds. # Time in milliseconds to wait for all message outputs to finish writing a single message. #output_module_timeout = 10000 # Time in milliseconds after which a detected stale master node is being rechecked on startup. #stale_master_timeout = 2000 # Time in milliseconds which Graylog is waiting for all threads to stop on shutdown. # shutdown_timeout = 30000 # MongoDB Configuration mongodb_uri = mongodb://127.0.0.1:27017/graylog # Raise this according to the maximum connections your MongoDB server can handle if you encounter MongoDB connection problems. mongodb_max_connections = 100 # Number of threads allowed to be blocked by MongoDB connections multiplier. Default: 5 # If mongodb_max_connections is 100, and mongodb_threads_allowed_to_block_multiplier is 5, then 500 threads can block. More than that and an exception will be thrown. # http://api.mongodb.org/java/current/com/mongodb/MongoOptions.html#threadsAllowedToBlockForConnectionMultiplier mongodb_threads_allowed_to_block_multiplier = 5 # Drools Rule File (Use to rewrite incoming log messages) # See: http://graylog2.org/resources/documentation/general/rewriting # Email transport transport_email_enabled = false transport_email_hostname = transport_email_port = 587 transport_email_use_auth = false transport_email_use_tls = true transport_email_use_ssl = true transport_email_auth_username = transport_email_auth_password = transport_email_subject_prefix = [graylog] transport_email_from_email = # Specify and uncomment this if you want to include links to the stream in your stream alert mails. # This should define the fully qualified base url to your web interface exactly the same way as it is accessed by your users. # transport_email_web_interface_url = # The default connect timeout for outgoing HTTP connections. # Values must be a positive duration (and between 1 and 2147483647 when converted to milliseconds). # Default: 5s #http_connect_timeout = 5s # The default read timeout for outgoing HTTP connections. # Values must be a positive duration (and between 1 and 2147483647 when converted to milliseconds). # Default: 10s #http_read_timeout = 10s # The default write timeout for outgoing HTTP connections. # Values must be a positive duration (and between 1 and 2147483647 when converted to milliseconds). # Default: 10s #http_write_timeout = 10s # HTTP proxy for outgoing HTTP calls # Disable the optimization of Elasticsearch indices after index cycling. This may take some load from Elasticsearch # on heavily used systems with large indices, but it will decrease search performance. The default is to optimize # cycled indices. #disable_index_optimization = true # Optimize the index down to <= index_optimization_max_num_segments. A higher number may take some load from Elasticsearch # on heavily used systems with large indices, but it will decrease search performance. The default is 1. #index_optimization_max_num_segments = 1 # Disable the index range calculation on all open/available indices and only calculate the range for the latest # index. This may speed up index cycling on systems with large indices but it might lead to wrong search results # in regard to the time range of the messages (i. e. messages within a certain range may not be found). The default # is to calculate the time range on all open/available indices. #disable_index_range_calculation = true # The threshold of the garbage collection runs. If GC runs take longer than this threshold, a system notification # will be generated to warn the administrator about possible problems with the system. Default is 1 second. #gc_warning_threshold = 1s # Connection timeout for a configured LDAP server (e. g. ActiveDirectory) in milliseconds. #ldap_connection_timeout = 2000 # Enable collection of Graylog-related metrics into MongoDB #enable_metrics_collection = false # Disable the use of SIGAR for collecting system stats #disable_sigar = false # The default cache time for dashboard widgets. (Default: 10 seconds, minimum: 1 second) dashboard_widget_default_cache_time = 10s # Automatically load content packs in "content_packs_dir" on the first start of Graylog. content_packs_loader_enabled = true # The directory which contains content packs which should be loaded on the first start of Graylog. content_packs_dir = /opt/graylog/contentpacks # A comma-separated list of content packs (files in "content_packs_dir") which should be applied on # the first start of Graylog. content_packs_auto_load = grok-patterns.json,content_pack_appliance.json -- You received this message because you are subscribed to the Google Groups "Graylog Users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/graylog2/66209fe2-203d-4b5c-a48e-27caa223279c%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
