1 ##################### Elasticsearch Configuration Example #####################
  2 
  3 # This file contains an overview of various configuration settings,
  4 # targeted at operations staff. Application developers should
  5 # consult the guide at <http://elasticsearch.org/guide>.
  6 #
  7 # The installation procedure is covered at
  8 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup.html>.
  9 #
 10 # Elasticsearch comes with reasonable defaults for most settings,
 11 # so you can try it out without bothering with configuration.
 12 #
 13 # Most of the time, these defaults are just fine for running a production
 14 # cluster. If you're fine-tuning your cluster, or wondering about the
 15 # effect of certain configuration option, please _do ask_ on the
 16 # mailing list or IRC channel [http://elasticsearch.org/community].
 17 
 18 # Any element in the configuration can be replaced with environment variables
 19 # by placing them in ${...} notation. For example:
 20 #所有的配置都可以使用环境变量，例如
 21 #node.rack: ${RACK_ENV_VAR}
 22 
 23 # For information on supported formats and syntax for the config file, see
 24 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/setup-configuration.html>
 25 
 26 
 27 ################################### Cluster ###################################
 28 
 29 # Cluster name identifies your cluster for auto-discovery. If you're running
 30 # multiple clusters on the same network, make sure you're using unique names.
 31 # 集群名称，默认为elasticsearch
 32 #cluster.name: elasticsearch
 33 
 34 
 35 #################################### Node #####################################
 36 
 37 # Node names are generated dynamically on startup, so you're relieved
 38 # from configuring them manually. You can tie this node to a specific name:
 39 #节点名称，es启动时会自动创建节点名称，但你也可进行配置
 40 #这些名称默认是在es的lib目录下的elasticsearch-1.4.4.jar文件中的config目录下的names.txt文件中
 41 #node.name: "Franz Kafka"
 42 
 43 # Every node can be configured to allow or deny being eligible as the master,
 44 # and to allow or deny to store the data.
 45 #
 46 # Allow this node to be eligible as a master node (enabled by default):
 47 #(是否具备成为主节点的资格)是否作为主节点，每个节点都可以被配置成为主节点，默认值为true：
 48 #node.master: true
 49 #
 50 # Allow this node to store data (enabled by default):
 51 #是否存储数据，即存储索引片段，默认值为true
 52 #node.data: true
 53 
 54 # You can exploit these settings to design advanced cluster topologies.
 55 #当master为false，而data为true时，会对该节点产生严重负荷；
 56 # 1. You want this node to never become a master node, only to hold data.
 57 #    This will be the "workhorse" of your cluster.
 58 #
 59 #node.master: false
 60 #node.data: true
 61 #当master为true，而data为false时，该节点作为一个协调者；
 62 # 2. You want this node to only serve as a master: to not store any data and
 63 #    to have free resources. This will be the "coordinator" of your cluster.
 64 #
 65 #node.master: true
 66 #node.data: false
 67 #当master为false，data也为false时，该节点就变成了一个负载均衡器。
 68 # 3. You want this node to be neither master nor data node, but
 69 #    to act as a "search load balancer" (fetching data from nodes,
 70 #    aggregating results, etc.)
 71 #
 72 #node.master: false
 73 #node.data: false
 74 
 75 # Use the Cluster Health API [http://localhost:9200/_cluster/health], the
 76 # Node Info API [http://localhost:9200/_nodes] or GUI tools
 77 # such as <http://www.elasticsearch.org/overview/marvel/>,
 78 # <http://github.com/karmi/elasticsearch-paramedic>,
 79 # <http://github.com/lukas-vlcek/bigdesk> and
 80 # <http://mobz.github.com/elasticsearch-head> to inspect the cluster state.
 81 
 82 # A node can have generic attributes associated with it, which can later be used
 83 # for customized shard allocation filtering, or allocation awareness. An attribute
 84 # is a simple key value pair, similar to node.key: value, here is an example:
 85 #每个节点都可以定义一些与之关联的通用属性，用于后期集群进行分片分配时的过滤：
 86 #node.rack: rack314
 87 
 88 # By default, multiple nodes are allowed to start from the same installation location
 89 # to disable it, set the following:
 90 #默认情况下，多个节点可以在同一个安装路径启动，如果你想让你的es只启动一个节点，可以进行如下设置：
 91 #node.max_local_storage_nodes: 1
 92 
 93 
 94 #################################### Index ####################################
 95 
 96 # You can set a number of options (such as shard/replica options, mapping
 97 # or analyzer definitions, translog settings, ...) for indices globally,
 98 # in this file.
 99 #
100 # Note, that it makes more sense to configure index settings specifically for
101 # a certain index, either when creating it or by using the index templates API.
102 #
103 # See <http://elasticsearch.org/guide/en/elasticsearch/reference/current/index-modules.html> and
104 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/indices-create-index.html>
105 # for more information.
106 
107 # Set the number of shards (splits) of an index (5 by default):
108 #设置一个索引库的分片数量，默认值为5：
109 #index.number_of_shards: 5
110 
111 # Set the number of replicas (additional copies) of an index (1 by default):
112 #设置一个索引库可被复制的数量，默认值为1：
113 #index.number_of_replicas: 1
114 
115 # Note, that for development on a local machine, with small indices, it usually
116 # makes sense to "disable" the distributed features:
117 #当你想要禁用分布式时，你可以进行如下设置：
118 #index.number_of_shards: 1
119 #index.number_of_replicas: 0
120 
121 # These settings directly affect the performance of index and search operations
122 # in your cluster. Assuming you have enough machines to hold shards and
123 # replicas, the rule of thumb is:
124 # 这两个属性的设置直接影响集群中索引和搜索操作的执行。假设你有足够的机器来持有分片和复制品，
125 #    那么可以按如下规则设置这两个值：
126 # 1. Having more *shards* enhances the _indexing_ performance and allows to
127 #    _distribute_ a big index across machines.
128 #拥有更多的分片可以提升索引执行能力，并允许通过机器分发一个大型的索引；
129 # 2. Having more *replicas* enhances the _search_ performance and improves the
130 #    cluster _availability_.
131 #拥有更多的复制器能够提升搜索执行能力以及集群能力。
132 # The "number_of_shards" is a one-time setting for an index.
133 #对于一个索引来说，number_of_shards只能设置一次
134 # The "number_of_replicas" can be increased or decreased anytime,
135 # by using the Index Update Settings API.
136 #而number_of_replicas可以使用索引更新设置API在任何时候被增加或者减少
137 #
138 # Elasticsearch takes care about load balancing, relocating, gathering the
139 # results from nodes, etc. Experiment with different settings to fine-tune
140 # your setup.
141 # ElasticSearch关注负载均衡、迁移、从节点聚集结果等等。可以尝试多种设计来完成这些功能。
142 # Use the Index Status API (<http://localhost:9200/A/_status>) to inspect
143 # the index status.
144 #可以连接http://localhost:9200/A/_status来检测索引的状态。
145 
146 
147 #################################### Paths ####################################
148 
149 # Path to directory containing configuration (this file and logging.yml):
150 #配置文件所在的位置，即elasticsearch.yml和logging.yml所在的位置：
151 #path.conf: /path/to/conf
152 
153 # Path to directory where to store index data allocated for this node.
154 #分配给当前节点的索引数据所在的位置：
155 #path.data: /path/to/data
156 #
157 # Can optionally include more than one location, causing data to be striped across
158 # the locations (a la RAID 0) on a file level, favouring locations with most free
159 # space on creation. For example:
160 #可以可选择的包含一个以上的位置，使得数据在文件级别跨越位置，这样在创建时就有更多的自由路径，如：
161 #path.data: /path/to/data1,/path/to/data2
162 
163 # Path to temporary files:
164 # 临时文件位置：
165 #path.work: /path/to/work
166 
167 # Path to log files:
168 #日志文件所在位置：
169 #path.logs: /path/to/logs
170 
171 # Path to where plugins are installed:
172 # 插件安装位置：
173 #path.plugins: /path/to/plugins
174 
175 
176 #################################### Plugin ###################################
177 
178 # If a plugin listed here is not installed for current node, the node will not start.
179 #若列表中的某一个插件未安装，则节点无法启动：
180 #plugin.mandatory: mapper-attachments,lang-groovy
181 
182 
183 ################################### Memory ####################################
184 
185 # Elasticsearch performs poorly when JVM starts swapping: you should ensure that
186 # it _never_ swaps.
187 #
188 # Set this property to true to lock the memory:
189 #JVM开始交换时，ElasticSearch表现并不好：你需要保障JVM不进行交换，可以将bootstrap.mlockall设置为true禁止交换
190 #bootstrap.mlockall: true
191 
192 # Make sure that the ES_MIN_MEM and ES_MAX_MEM environment variables are set
193 # to the same value, and that the machine has enough memory to allocate
194 # for Elasticsearch, leaving enough memory for the operating system itself.
195 #请确保ES_MIN_MEM和ES_MAX_MEM的值是一样的，并且能够为ElasticSearch分配足够的内在，并为系统操作保留足够的内存
196 # You should also make sure that the Elasticsearch process is allowed to lock
197 # the memory, eg. by using `ulimit -l unlimited`.
198 #你应该确保Elasticsearch 进程可以锁定内存。通过使用"ulimit -l unlimited"
199 
200 ############################## Network And HTTP ###############################
201 
202 # Elasticsearch, by default, binds itself to the 0.0.0.0 address, and listens
203 # on port [9200-9300] for HTTP traffic and on port [9300-9400] for node-to-node
204 # communication. (the range means that if the port is busy, it will automatically
205 # try the next port).
206 # 默认情况下，ElasticSearch使用0.0.0.0地址，并为http传输开启9200-9300端口，
207 #    为节点到节点的通信开启9300-9400端口，也可以自行设置IP地址
208 #    （如果节点被占用了，es将会自动尝试使用下一个端口）
209 # Set the bind address specifically (IPv4 or IPv6):
210 #
211 #network.bind_host: 192.168.0.1
212 
213 # Set the address other nodes will use to communicate with this node. If not
214 # set, it is automatically derived. It must point to an actual IP address.
215 # publish_host设置其他节点连接此节点的地址，如果不设置的话，则自动获取，publish_host的地址必须为真实地址
216 #network.publish_host: 192.168.0.1
217 
218 # Set both 'bind_host' and 'publish_host':
219 #bind_host和publish_host可以一起设置
220 #network.host: 192.168.0.1
221 
222 # Set a custom port for the node to node communication (9300 by default):
223 #可以定制该节点与其他节点交互的端口
224 #transport.tcp.port: 9300
225 
226 # Enable compression for all communication between nodes (disabled by default):
227 #节点间交互时，可以设置是否压缩，默认为不压缩
228 #transport.tcp.compress: true
229 
230 # Set a custom port to listen for HTTP traffic:
231 #可以为Http传输监听定制端口
232 #http.port: 9200
233 
234 # Set a custom allowed content length:
235 #设置内容的最大长度
236 #http.max_content_length: 100mb
237 
238 # Disable HTTP completely:
239 #禁止HTTP
240 #http.enabled: false
241 
242 
243 ################################### Gateway ###################################
244 
245 # The gateway allows for persisting the cluster state between full cluster
246 # restarts. Every change to the state (such as adding an index) will be stored
247 # in the gateway, and when the cluster starts up for the first time,
248 # it will read its state from the gateway.
249 # 网关允许在所有集群重启后持有集群状态，集群状态的变更都会被保存下来，
250 #    当第一次启用集群时，可以从网关中读取到状态，
251 
252 # There are several types of gateway implementations. For more information, see
253 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-gateway.html>.
254 
255 # The default gateway type is the "local" gateway (recommended):
256 #默认文件类型是本地local：
257 #gateway.type: local
258 
259 # Settings below control how and when to start the initial recovery process on
260 # a full cluster restart (to reuse as much local data as possible when using shared
261 # gateway).
262 
263 # Allow recovery process after N nodes in a cluster are up:
264 #允许在N个节点启动后恢复过程
265 #gateway.recover_after_nodes: 1
266 
267 # Set the timeout to initiate the recovery process, once the N nodes
268 # from previous setting are up (accepts time value):
269 #设置初始化恢复过程的超时时间
270 #gateway.recover_after_time: 5m
271 
272 # Set how many nodes are expected in this cluster. Once these N nodes
273 # are up (and recover_after_nodes is met), begin recovery process immediately
274 # (without waiting for recover_after_time to expire):
275 #设置该集群中可存在的节点上限
276 #gateway.expected_nodes: 2
277 
278 
279 ############################# Recovery Throttling #############################
280 
281 # These settings allow to control the process of shards allocation between
282 # nodes during initial recovery, replica allocation, rebalancing,
283 # or when adding and removing nodes.
284 
285 # Set the number of concurrent recoveries happening on a node:
286 #设置一个节点的并发数量，有两种情况，
287 #一种是在初始复苏过程中：
288 # 1. During the initial recovery
289 #
290 #cluster.routing.allocation.node_initial_primaries_recoveries: 4
291 #
292 # 2. During adding/removing nodes, rebalancing, etc
293 #另一种是在添加、删除节点及调整时：
294 #cluster.routing.allocation.node_concurrent_recoveries: 2
295 
296 # Set to throttle throughput when recovering (eg. 100mb, by default 20mb):
297 #设置复苏时的吞吐量，默认情况下是无限的
298 #indices.recovery.max_bytes_per_sec: 20mb
299 
300 # Set to limit the number of open concurrent streams when
301 # recovering a shard from a peer:
302 #设置从对等节点恢复片段时打开的流的数量上限
303 #indices.recovery.concurrent_streams: 5
304 
305 
306 ################################## Discovery ##################################
307 
308 # Discovery infrastructure ensures nodes can be found within a cluster
309 # and master node is elected. Multicast discovery is the default.
310 
311 # Set to ensure a node sees N other master eligible nodes to be considered
312 # operational within the cluster. This should be set to a quorum/majority of 
313 # the master-eligible nodes in the cluster.
314 #设置一个集群中主节点的数量，当多于三个节点时，该值可在2-4之间
315 #discovery.zen.minimum_master_nodes: 1
316 
317 # Set the time to wait for ping responses from other nodes when discovering.
318 # Set this option to a higher value on a slow or congested network
319 # to minimize discovery failures:
320 #设置ping其他节点时的超时时间，网络比较慢时可将该值设大
321 #discovery.zen.ping.timeout: 3s
322 
323 # For more information, see
324 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-zen.html>
325 
326 # Unicast discovery allows to explicitly control which nodes will be used
327 # to discover the cluster. It can be used when multicast is not present,
328 # or to restrict the cluster communication-wise.
329 #
330 # 1. Disable multicast discovery (enabled by default):
331 # 禁止当前节点发现多个集群节点，
332 # 默认启用发现节点机制，设为false的话表示禁用自动发现机制
333 #discovery.zen.ping.multicast.enabled: false
334 #
335 # 2. Configure an initial list of master nodes in the cluster
336 #    to perform discovery when new nodes (master or data) are started:
337 #设置新节点被启动时能够发现的主节点列表
338 #discovery.zen.ping.unicast.hosts: ["host1", "host2:port"]
339 
340 # EC2 discovery allows to use AWS EC2 API in order to perform discovery.
341 #
342 # You have to install the cloud-aws plugin for enabling the EC2 discovery.
343 #
344 # For more information, see
345 # <http://elasticsearch.org/guide/en/elasticsearch/reference/current/modules-discovery-ec2.html>
346 #
347 # See <http://elasticsearch.org/tutorials/elasticsearch-on-ec2/>
348 # for a step-by-step tutorial.
349 
350 # GCE discovery allows to use Google Compute Engine API in order to perform discovery.
351 #
352 # You have to install the cloud-gce plugin for enabling the GCE discovery.
353 #
354 # For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-gce>.
355 
356 # Azure discovery allows to use Azure API in order to perform discovery.
357 #
358 # You have to install the cloud-azure plugin for enabling the Azure discovery.
359 #
360 # For more information, see <https://github.com/elasticsearch/elasticsearch-cloud-azure>.
361 
362 ################################## Slow Log ##################################
363 
364 # Shard level query and fetch threshold logging.
365 
366 #index.search.slowlog.threshold.query.warn: 10s
367 #index.search.slowlog.threshold.query.info: 5s
368 #index.search.slowlog.threshold.query.debug: 2s
369 #index.search.slowlog.threshold.query.trace: 500ms
370 
371 #index.search.slowlog.threshold.fetch.warn: 1s
372 #index.search.slowlog.threshold.fetch.info: 800ms
373 #index.search.slowlog.threshold.fetch.debug: 500ms
374 #index.search.slowlog.threshold.fetch.trace: 200ms
375 
376 #index.indexing.slowlog.threshold.index.warn: 10s
377 #index.indexing.slowlog.threshold.index.info: 5s
378 #index.indexing.slowlog.threshold.index.debug: 2s
379 #index.indexing.slowlog.threshold.index.trace: 500ms
380 
381 ################################## GC Logging ################################
382 
383 #monitor.jvm.gc.young.warn: 1000ms
384 #monitor.jvm.gc.young.info: 700ms
385 #monitor.jvm.gc.young.debug: 400ms
386 
387 #monitor.jvm.gc.old.warn: 10s
388 #monitor.jvm.gc.old.info: 5s
389 #monitor.jvm.gc.old.debug: 2s
390 
391 ################################## Security ################################
392 
393 # Uncomment if you want to enable JSONP as a valid return transport on the
394 # http server. With this enabled, it may pose a security risk, so disabling
395 # it unless you need it is recommended (it is disabled by default).
396 #如果你想要启用JSONP作为HTTP服务器的有效传输的话取消注释。
397 #启用此功能，它可能会带来风险。因此，禁用它，除非你必须需要它（默认禁用）
398 #http.jsonp.enable: true