add basic docs

This commit is contained in:
Simon Willnauer 2017-01-05 16:10:34 +01:00
parent 0183b0c5a8
commit dca54734ac
6 changed files with 122 additions and 4 deletions

View File

@ -86,7 +86,7 @@ public final class RemoteClusterService extends AbstractComponent implements Clo
/**
* The name of a node attribute to filter out nodes that should not be connected to in the remote cluster.
* For instance a node can be configured with <tt>node.node_attr.gateway: true</tt> in order to be eligable as a gateway node between
* For instance a node can be configured with <tt>node.node_attr.gateway: true</tt> in order to be eligible as a gateway node between
* clusters. In that case <tt>search.remote.node_attribute: gateway</tt> can be used to filter out other nodes in the remote cluster
*/
public static final Setting<String> REMOTE_NODE_ATTRIBUTE = Setting.simpleString("search.remote.node_attribute",
@ -157,7 +157,7 @@ public final class RemoteClusterService extends AbstractComponent implements Clo
return remoteClusters.isEmpty() == false;
}
public String[] filterIndices(Map<String, List<String>> perClusterIndices, String... requestIndices) {
public String[] filterIndices(Map<String, List<String>> perClusterIndices, String[] requestIndices) {
List<String> localIndicesList = new ArrayList<>();
for (String index : requestIndices) {
int i = index.indexOf(REMOTE_CLUSTER_INDEX_SEPARATOR);

View File

@ -124,7 +124,7 @@ public class TransportSearchAction extends HandledTransportAction<SearchRequest,
final Map<String, List<String>> remoteIndicesByCluster;
if (remoteClusterService.isCrossClusterSearchEnabled()) {
remoteIndicesByCluster = new HashMap<>();
localIndices = remoteClusterService.filterIndices(remoteIndicesByCluster);
localIndices = remoteClusterService.filterIndices(remoteIndicesByCluster, searchRequest.indices());
} else {
remoteIndicesByCluster = Collections.emptyMap();
localIndices = searchRequest.indices();

View File

@ -257,7 +257,7 @@ public final class ClusterSettings extends AbstractScopedSettings {
RemoteClusterService.REMOTE_CLUSTERS_SEEDS,
RemoteClusterService.REMOTE_CONNECTIONS_PER_CLUSTER,
RemoteClusterService.REMOTE_INITIAL_CONNECTION_TIMEOUT_SETTING,
RemoteClusterServic.REMOTE_NODE_ATTRIBUTE
RemoteClusterService.REMOTE_NODE_ATTRIBUTE,
TransportService.TRACE_LOG_EXCLUDE_SETTING,
TransportService.TRACE_LOG_INCLUDE_SETTING,
TransportCloseIndexAction.CLUSTER_INDICES_CLOSE_ENABLE_SETTING,

View File

@ -145,6 +145,7 @@ buildRestTests.expectedUnconvertedCandidates = [
'reference/modules/scripting/security.asciidoc',
'reference/modules/scripting/using.asciidoc',
'reference/modules/transport.asciidoc',
'reference/modules/cross-cluster-search.asciidoc', // this is hart to test since we need 2 clusters -- maybe we can trick it into referencing itself...
'reference/query-dsl/exists-query.asciidoc',
'reference/query-dsl/function-score-query.asciidoc',
'reference/query-dsl/geo-shape-query.asciidoc',

View File

@ -77,6 +77,11 @@ The modules in this section are:
A tribe node joins one or more clusters and acts as a federated
client across them.
<<modules-cross-cluster-search, Cross cluster Search>>::
Cross cluster search allows to execute search requests across more than one cluster without joining them and acts
as a federated client across them.
--

View File

@ -0,0 +1,112 @@
[[modules-cross-cluster-search]]
== Cross cluster search
The _cross cluster search_ feature allows any node to act as a federated client across
multiple clusters. In contrast to the _tribe_ feature, a _cross cluster search_ node won't
join the remote cluster, instead it connects to a remote cluster in a light fashion in order to executed
federated search requests.
The _cross cluster search_ feature works by configuring a remote cluster in the cluster state and connects only to a
limited number of nodes in the remote cluster. Each remote cluster is referenced by a name and a list of seed nodes.
Those seed nodes are used to discover other nodes eligible as so-called _gateway nodes_. Each node in a cluster that
has remote cluster configured connects to one or more _gateway nodes_ and uses them to federate search requests to
the remote cluster.
Remote clusters can either be configured as part of the `elasticsearch.yml` file or be dynamically updated via
the <<cluster settings API, cluster-update-settings>>. If a remote cluster is configured via `elasticsearch.yml` only
the nodes with the configuration set will be connecting to the remote cluster. Remote clusters set via the
<<cluster settings API, cluster-update-settings>> will be available on every node in the cluster.
The `elasticsearch.yml` config file for a _cross cluster search_ node just needs to list the
remote clusters that should be connected to, for instance:
[source,yaml]
--------------------------------
search:
remote:
seeds:
cluster_one: 127.0.0.1:9300 <1>
cluster_two: 127.0.0.1:9301 <1>
--------------------------------
<1> `cluster_one` and `cluster_two` are arbitrary names representing the connection to each cluster. These names are subsequently used to distinguish between local and remote indices.
[float]
=== Using cross cluster search
To search the `twitter` index on remote cluster `cluster_1` the index name must be prefixed with the cluster name
separated by a `|` character:
[source,js]
--------------------------------------------------
POST /cluster_1|twitter/tweet/_search
{
"match_all": {}
}
--------------------------------------------------
In contrast to the `tribe` feature cross cluster search can also search indices with the same name on different clusters:
[source,js]
--------------------------------------------------
POST /cluster_1|twitter,twitter/tweet/_search
{
"match_all": {}
}
--------------------------------------------------
Search results are disambiguated the same way as the indices are disambiguated in the request. Even if index names are
identical these indices will be treated as different indices when results are merged. All results retrieved from a remote index
will be prefixed with it's remote clusters name:
[source,js]
--------------------------------------------------
{
"took" : 89,
"timed_out" : false,
"_shards" : {
"total" : 10,
"successful" : 10,
"failed" : 0
},
"hits" : {
"total" : 2,
"max_score" : 1.0,
"hits" : [
{
"_index" : "cluster_1|twitter",
"_type" : "tweet",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"user" : "kimchy",
"postDate" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
}
},
{
"_index" : "cluster_1|twitter",
"_type" : "tweet",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"user" : "kimchy",
"postDate" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
}
}
]
}
}
--------------------------------------------------
[float]
=== Cross cluster search settings
* `search.remote.connections_per_cluster` - the number of nodes to connect to per remote cluster. The default is `3`
* `search.remote.initial_connect_timeout` - the time to wait for remote connections to be established when the node starts. The default is `30s`.
* `search.remote.node_attribute` - a node attribute to filter out nodes that are eligible as a gateway node in the remote cluster.
For instance a node can have a node attribute `node.attr.gateway: true` such that only nodes with this attribute
will be connected to if `search.remote.node_attribute` is set to `gateway`