Add superdataset replicas number config (#5424)

* distinct the number of metrics or common record index with super dataset index.

docs/en/setup/backend/backend-storage.md

@@ -53,15 +53,16 @@ storage:
     protocol: ${SW_STORAGE_ES_HTTP_PROTOCOL:"http"}
     trustStorePath: ${SW_STORAGE_ES_SSL_JKS_PATH:""}
     trustStorePass: ${SW_STORAGE_ES_SSL_JKS_PASS:""}
-    dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
-    superDatasetDayStep: ${SW_SUPERDATASET_STORAGE_DAY_STEP:-1} # Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value lt 0
     user: ${SW_ES_USER:""}
     password: ${SW_ES_PASSWORD:""}
     secretsManagementFile: ${SW_ES_SECRETS_MANAGEMENT_FILE:""} # Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool.
+    dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
     indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:1} # Shard number of new indexes
-    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} # Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
-    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:0}
-    # Batch process setting, refer to https://www.elastic.co/guide/en/elasticsearch/client/java-api/5.5/java-docs-bulk-processor.html
+    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:1} # Replicas number of new indexes
+    # Super data set has been defined in the codes, such as trace segments.The following 3 config would be improve es performance when storage super size data in es.
+    superDatasetDayStep: ${SW_SUPERDATASET_STORAGE_DAY_STEP:-1} # Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0
+    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} #  This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
+    superDatasetIndexReplicasNumber: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_REPLICAS_NUMBER:0} # Represent the replicas number in the super size dataset record index, the default value is 0.
     bulkActions: ${SW_STORAGE_ES_BULK_ACTIONS:1000} # Execute the bulk every 1000 requests
     flushInterval: ${SW_STORAGE_ES_FLUSH_INTERVAL:10} # flush the bulk every 10 seconds whatever the number of requests
     concurrentRequests: ${SW_STORAGE_ES_CONCURRENT_REQUESTS:2} # the number of concurrent requests

docs/en/setup/backend/configuration-vocabulary.md

@@ -74,12 +74,13 @@ core|default|role|Option values, `Mixed/Receiver/Aggregator`. **Receiver** mode
 | - | - | password | Password of ElasticSearch cluster | SW_ES_PASSWORD | - |
 | - | - | trustStorePath | Trust JKS file path. Only work when user name and password opened | SW_STORAGE_ES_SSL_JKS_PATH | - |
 | - | - | trustStorePass | Trust JKS file password. Only work when user name and password opened | SW_STORAGE_ES_SSL_JKS_PASS | - |
-| - | - | indexShardsNumber | Shard number of new indexes | SW_STORAGE_ES_INDEX_SHARDS_NUMBER | 1 |
 | - | - | secretsManagementFile| Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool. Provide the capability to update them in the runtime.|SW_ES_SECRETS_MANAGEMENT_FILE | - |
 | - | - | dayStep| Represent the number of days in the one minute/hour/day index.| SW_STORAGE_DAY_STEP | 1|
 | - | - | indexShardsNumber | Shard number of new indexes | SW_STORAGE_ES_INDEX_SHARDS_NUMBER | 1 |
-| - | - | superDatasetIndexShardsFactor | Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.|SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR|5 |
 | - | - | indexReplicasNumber | Replicas number of new indexes | SW_STORAGE_ES_INDEX_REPLICAS_NUMBER | 0 |
+| - | - | superDatasetDayStep | Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0.|SW_SUPERDATASET_STORAGE_DAY_STEP|-1 |
+| - | - | superDatasetIndexShardsFactor | Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.|SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR|5 |
+| - | - | superDatasetIndexReplicasNumber | Represent the replicas number in the super size dataset record index.|SW_STORAGE_ES_SUPER_DATASET_INDEX_REPLICAS_NUMBER|0 |
 | - | - | bulkActions| Bulk size of the batch execution. | SW_STORAGE_ES_BULK_ACTIONS| 1000|
 | - | - | flushInterval| Period of flush, no matter `bulkActions` reached or not. Unit is second.| SW_STORAGE_ES_FLUSH_INTERVAL | 10|
 | - | - | concurrentRequests| The number of concurrent requests allowed to be executed. | SW_STORAGE_ES_CONCURRENT_REQUESTS| 2 |
@@ -99,11 +100,13 @@ core|default|role|Option values, `Mixed/Receiver/Aggregator`. **Receiver** mode
 | - | - | secretsManagementFile| Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool. Provide the capability to update them in the runtime.|SW_ES_SECRETS_MANAGEMENT_FILE | - |
 | - | - | dayStep| Represent the number of days in the one minute/hour/day index.| SW_STORAGE_DAY_STEP | 1|
 | - | - | indexShardsNumber | Shard number of new indexes | SW_STORAGE_ES_INDEX_SHARDS_NUMBER | 1 |
-| - | - | superDatasetIndexShardsFactor | Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.|SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR|5 |
 | - | - | indexReplicasNumber | Replicas number of new indexes | SW_STORAGE_ES_INDEX_REPLICAS_NUMBER | 0 |
+| - | - | superDatasetDayStep | Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0.|SW_SUPERDATASET_STORAGE_DAY_STEP|-1 |
+| - | - | superDatasetIndexShardsFactor | Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.|SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR|5 |
+| - | - | superDatasetIndexReplicasNumber | Represent the replicas number in the super size dataset record index.|SW_STORAGE_ES_SUPER_DATASET_INDEX_REPLICAS_NUMBER|0 |
 | - | - | bulkActions| Bulk size of the batch execution. | SW_STORAGE_ES_BULK_ACTIONS| 1000|
 | - | - | flushInterval| Period of flush, no matter `bulkActions` reached or not. Unit is second.| SW_STORAGE_ES_FLUSH_INTERVAL | 10|
-| - | - | concurrentRequests| The number of concurrent requests allowed to be executed. |SW_STORAGE_ES_CONCURRENT_REQUESTS| 2 |
+| - | - | concurrentRequests| The number of concurrent requests allowed to be executed. | SW_STORAGE_ES_CONCURRENT_REQUESTS| 2 |
 | - | - | resultWindowMaxSize | The max size of dataset when OAP loading cache, such as network alias. | SW_STORAGE_ES_QUERY_MAX_WINDOW_SIZE | 10000|
 | - | - | metadataQueryMaxSize | The max size of metadata per query. | SW_STORAGE_ES_QUERY_MAX_SIZE | 5000 |
 | - | - | segmentQueryMaxSize | The max size of trace segments per query. | SW_STORAGE_ES_QUERY_SEGMENT_SIZE | 200|

oap-server/server-bootstrap/src/main/resources/application.yml

@@ -101,16 +101,18 @@ storage:
     nameSpace: ${SW_NAMESPACE:""}
     clusterNodes: ${SW_STORAGE_ES_CLUSTER_NODES:localhost:9200}
     protocol: ${SW_STORAGE_ES_HTTP_PROTOCOL:"http"}
-    trustStorePath: ${SW_STORAGE_ES_SSL_JKS_PATH:""}
-    trustStorePass: ${SW_STORAGE_ES_SSL_JKS_PASS:""}
     user: ${SW_ES_USER:""}
     password: ${SW_ES_PASSWORD:""}
+    trustStorePath: ${SW_STORAGE_ES_SSL_JKS_PATH:""}
+    trustStorePass: ${SW_STORAGE_ES_SSL_JKS_PASS:""}
     secretsManagementFile: ${SW_ES_SECRETS_MANAGEMENT_FILE:""} # Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool.
     dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
-    superDatasetDayStep: ${SW_SUPERDATASET_STORAGE_DAY_STEP:-1} # Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0
     indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:1} # Shard number of new indexes
-    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} # Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
-    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:0}
+    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:1} # Replicas number of new indexes
+    # Super data set has been defined in the codes, such as trace segments.The following 3 config would be improve es performance when storage super size data in es.
+    superDatasetDayStep: ${SW_SUPERDATASET_STORAGE_DAY_STEP:-1} # Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0
+    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} #  This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
+    superDatasetIndexReplicasNumber: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_REPLICAS_NUMBER:0} # Represent the replicas number in the super size dataset record index, the default value is 0.
     bulkActions: ${SW_STORAGE_ES_BULK_ACTIONS:1000} # Execute the bulk every 1000 requests
     flushInterval: ${SW_STORAGE_ES_FLUSH_INTERVAL:10} # flush the bulk every 10 seconds whatever the number of requests
     concurrentRequests: ${SW_STORAGE_ES_CONCURRENT_REQUESTS:2} # the number of concurrent requests
@@ -126,13 +128,15 @@ storage:
     trustStorePath: ${SW_STORAGE_ES_SSL_JKS_PATH:""}
     trustStorePass: ${SW_STORAGE_ES_SSL_JKS_PASS:""}
     dayStep: ${SW_STORAGE_DAY_STEP:1} # Represent the number of days in the one minute/hour/day index.
+    indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:1} # Shard number of new indexes
+    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:1} # Replicas number of new indexes
+    # Super data set has been defined in the codes, such as trace segments.The following 3 config would be improve es performance when storage super size data in es.
     superDatasetDayStep: ${SW_SUPERDATASET_STORAGE_DAY_STEP:-1} # Represent the number of days in the super size dataset record index, the default value is the same as dayStep when the value is less than 0
+    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} #  This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
+    superDatasetIndexReplicasNumber: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_REPLICAS_NUMBER:0} # Represent the replicas number in the super size dataset record index, the default value is 0.
     user: ${SW_ES_USER:""}
     password: ${SW_ES_PASSWORD:""}
     secretsManagementFile: ${SW_ES_SECRETS_MANAGEMENT_FILE:""} # Secrets management file in the properties format includes the username, password, which are managed by 3rd party tool.
-    indexShardsNumber: ${SW_STORAGE_ES_INDEX_SHARDS_NUMBER:1} # Shard number of new indexes
-    superDatasetIndexShardsFactor: ${SW_STORAGE_ES_SUPER_DATASET_INDEX_SHARDS_FACTOR:5} # Super data set has been defined in the codes, such as trace segments. This factor provides more shards for the super data set, shards number = indexShardsNumber * superDatasetIndexShardsFactor. Also, this factor effects Zipkin and Jaeger traces.
-    indexReplicasNumber: ${SW_STORAGE_ES_INDEX_REPLICAS_NUMBER:0}
     bulkActions: ${SW_STORAGE_ES_BULK_ACTIONS:1000} # Execute the bulk every 1000 requests
     flushInterval: ${SW_STORAGE_ES_FLUSH_INTERVAL:10} # flush the bulk every 10 seconds whatever the number of requests
     concurrentRequests: ${SW_STORAGE_ES_CONCURRENT_REQUESTS:2} # the number of concurrent requests

oap-server/server-storage-plugin/storage-elasticsearch-plugin/src/main/java/org/apache/skywalking/oap/server/storage/plugin/elasticsearch/StorageModuleElasticsearchConfig.java

@@ -20,80 +20,60 @@ package org.apache.skywalking.oap.server.storage.plugin.elasticsearch;
 
 import lombok.Getter;
 import lombok.Setter;
-
+import org.apache.skywalking.oap.server.core.storage.annotation.SuperDataset;
 import org.apache.skywalking.oap.server.library.module.ModuleConfig;
 
 @Getter
+@Setter
 public class StorageModuleElasticsearchConfig extends ModuleConfig {
-    @Setter
     private String nameSpace;
-    @Setter
     private String clusterNodes;
-    @Getter
-    @Setter
     String protocol = "http";
-    @Setter
+    /**
+     * Since 6.4.0, the index of metrics and traces data in minute/hour/month precision are organized in days. ES
+     * storage creates new indexes in every day.
+     *
+     * @since 7.0.0 dayStep represents how many days a single one index represents. Default is 1, meaning no difference
+     * with previous versions. But if there isn't much traffic for single one day, user could set the step larger to
+     * reduce the number of indexes, and keep the TTL longer.
+     */
+    private int dayStep = 1;
+    private int indexReplicasNumber = 0;
     private int indexShardsNumber = 1;
-    @Setter
+    /**
+     * @since 8.2.0, the record day step is for super size dataset record index rolling when the value of it is greater than 0
+     */
+    private int superDatasetDayStep = -1;
+    /**
+     * @see SuperDataset
+     * @since 8.2.0, the replicas number is for super size dataset record replicas number
+     */
+    private int superDatasetIndexReplicasNumber = 0;
     private int superDatasetIndexShardsFactor = 5;
-    @Setter
-    private int indexReplicasNumber = 0;
-    @Setter
     private int indexRefreshInterval = 2;
-    @Setter
     private int bulkActions = 2000;
-    @Setter
     private int flushInterval = 10;
-    @Setter
     private int concurrentRequests = 2;
     /**
      * @since 7.0.0 This could be managed inside {@link #secretsManagementFile}
      */
-    @Setter
     private String user;
     /**
      * @since 7.0.0 This could be managed inside {@link #secretsManagementFile}
      */
-    @Setter
     private String password;
     /**
      * Secrets management file includes the username, password, which are managed by 3rd party tool.
      */
-    @Getter
     private String secretsManagementFile;
-    @Getter
-    @Setter
     private String trustStorePath;
     /**
      * @since 7.0.0 This could be managed inside {@link #secretsManagementFile}
      */
-    @Getter
-    @Setter
     private String trustStorePass;
-    /**
-     * Since 6.4.0, the index of metrics and traces data in minute/hour/month precision are organized in days. ES
-     * storage creates new indexes in every day.
-     *
-     * @since 7.0.0 dayStep represents how many days a single one index represents. Default is 1, meaning no difference
-     * with previous versions. But if there isn't much traffic for single one day, user could set the step larger to
-     * reduce the number of indexes, and keep the TTL longer.
-     */
-    @Getter
-    private int dayStep = 1;
-    /**
-     * @since 8.2.0, the record day step is for super size dataset record index rolling when the value of it is greater than 0
-     */
-    @Getter
-    private int superDatasetDayStep = -1;
-    @Setter
     private int resultWindowMaxSize = 10000;
-    @Setter
     private int metadataQueryMaxSize = 5000;
-    @Setter
     private int segmentQueryMaxSize = 200;
-    @Setter
     private int profileTaskQueryMaxSize = 200;
-    @Setter
     private String advanced;
-
 }

oap-server/server-storage-plugin/storage-elasticsearch-plugin/src/main/java/org/apache/skywalking/oap/server/storage/plugin/elasticsearch/base/StorageEsInstaller.java

@@ -104,7 +104,9 @@ public class StorageEsInstaller extends ModelInstaller {
     protected Map<String, Object> createSetting(Model model) {
         Map<String, Object> setting = new HashMap<>();
 
-        setting.put("index.number_of_replicas", config.getIndexReplicasNumber());
+        setting.put("index.number_of_replicas", model.isSuperDataset()
+            ? config.getSuperDatasetIndexReplicasNumber()
+            : config.getIndexReplicasNumber());
         setting.put("index.number_of_shards", model.isSuperDataset()
             ? config.getIndexShardsNumber() * config.getSuperDatasetIndexShardsFactor()
             : config.getIndexShardsNumber());