Elasticsearch配置

##################### 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.
#
##配置es的集群名称，默认是elasticsearch，es会自动发现在同一网段下的es，如果在同一网段下有多个集群，就可以用这个属性来区分不同的集群。
# cluster.name: elasticsearch




#################################### 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:
#
##节点名，默认随机指定一个name列表中的名字，该列表在es的jar包中的config文件夹里name.txt，其中有很多作者添加的有趣的名字
# 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):
#
##指定该节点是否有资格被选举为node，默认时true。es是默认集群中的第一台机器为master，如果这台机器挂了就会重新选举master
# node.master: true
#
# Allow this node to store data (enabled by default):
#
##指定该节点是否存储索引数据，默认true
# 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/_nodes] or GUI tools
# such as <http://www.elasticsearch.org/overview/marvel/>,
# <http://github.com/karmi/elasticsearch-paramedic>,
# <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):
#
##设置默认索引副本个数，默认为1个副本
# 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):
#
##设置默认文件的存储路径，默认是es根目录下的config文件夹
# path.conf: /path/to/conf


# Path to directory where to store index data allocated for this node.
#
##设置索引数据的存储路径，默认是es根目录下的data文件夹，可是设置多个存储路径，用逗号隔开
# path.data: /path/to/data
#
# 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:
#
##设置临时文件的存储路径，默认是es跟目录下的work文件夹
# path.work: /path/to/work


# Path to log files:
#
##设置日志文件的存储路径，默认时es根目录下的logs文件夹
# path.logs: /path/to/logs


# Path to where plugins are installed:
#
##设置插件的存储路径，默认时es根目录下的plugins文件夹
# 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:
#
##设置为true来锁住内存，因为当JVM开始swapping时es的效率会降低，所以要保证它不swap，可以把ES_MIN_MEM和ES_MAX_MEM两个环境变量设置成同一个值，并且保证机器有足够的内存分配给es，同时也要允许es的进程可以锁住内存，linux下可以通过ulimit -l unlimited命令
# 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):
#
##设置绑定的ip地址，可以时IPV4或者IPV6的，默认为0.0.0.0
# 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.
#
##设置其他节点和该节点交互的IP地址，如果不设置他会自动判断，其值必须是个真实的IP地址
# network.publish_host: 192.168.0.1


# Set both 'bind_host' and 'publish_host':
#
##同时设置bind——host和publish——host两个参数
# network.host: 192.168.0.1


# Set a custom port for the node to node communication (9300 by default):
#
##设置节点间交互的tcp端口，默认9300
# transport.tcp.port: 9300


# Enable compression for all communication between nodes (disabled by default):
#
##设置是否压缩tcp传输时的数据，默认为false，不压缩
# transport.tcp.compress: true


# Set a custom port to listen for HTTP traffic:
#
##设置对外服务的http端口，默认9200
# http.port: 9200


# Set a custom allowed content length:
#
##设置内容的最大容量，默认100mb
# http.max_content_length: 100mb


# Disable HTTP completely:
#
##是否使用http协议对外提供服务，默认为true，开启
# 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的类型，默认为local即本地文件系统，可以设置为本地文件系统，分布式文件系统，hadoop和HDFS和amazon的S3服务器，其他文件系统的设置。。
# 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:
#
##设置集群中N个节点启动时进行数据恢复，默认1
# 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):
#
##设置初始化数据恢复进程的超时时间，默认5分钟
# 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):
#
##设置集群中节点的数量，默认2，一旦N个节点启动，就会立即进行数据恢复
# 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:
#
##设置集群中自动发现其他节点时ping链接超时时间，默认3s
# discovery.zen.ping.timeout: 3s


# 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):
#
##设置是否多播发现节点，默认true
# 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:
#
##设置集群中master节点的初始列表，可以通过这些节点来自动发现新加入集群的节点
# discovery.zen.ping.unicast.hosts: ["host1", "host2:port"]


# 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.


# GCE discovery allows to use Google Compute Engine API in order to perform discovery.
#
# You have to install the cloud-gce plugin for enabling the GCE discovery.
#
# For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-gce>.


# Azure discovery allows to use Azure API in order to perform discovery.
#
# You have to install the cloud-azure plugin for enabling the Azure discovery.
#
# For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-azure>.


################################## 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