Merge branch 'main' into es-9.0-bump

.ci/scripts/resolve-dra-manifest.sh

@@ -23,7 +23,14 @@ LATEST_VERSION=$(strip_version $LATEST_BUILD)
 if [ "$LATEST_VERSION" != "$ES_VERSION" ]; then
   echo "Latest build for '$ARTIFACT' is version $LATEST_VERSION but expected version $ES_VERSION." 1>&2
   NEW_BRANCH=$(echo $ES_VERSION | sed -E "s/([0-9]+\.[0-9]+)\.[0-9]/\1/g")
+
+  # Temporary
+  if [[ "$ES_VERSION" == "8.16.0" ]]; then
+    NEW_BRANCH="8.x"
+  fi
+
   echo "Using branch $NEW_BRANCH instead of $BRANCH." 1>&2
+  echo "https://artifacts-$WORKFLOW.elastic.co/$ARTIFACT/latest/$NEW_BRANCH.json"
   LATEST_BUILD=$(fetch_build $WORKFLOW $ARTIFACT $NEW_BRANCH)
 fi
 

docs/reference/cluster/stats.asciidoc

@@ -1307,6 +1307,142 @@ Each repository type may also include other statistics about the repositories of
 
 ====
 
+`ccs`::
+(object) Contains information relating to <<modules-cross-cluster-search, {ccs}>> settings and activity in the cluster.
++
+.Properties of `ccs`
+[%collapsible%open]
+=====
+
+
+`_search`:::
+(object) Contains the telemetry information about the <<modules-cross-cluster-search, {ccs}>> usage in the cluster.
++
+.Properties of `_search`
+[%collapsible%open]
+======
+`total`:::
+(integer) The total number of {ccs} requests that have been executed by the cluster.
+
+`success`:::
+(integer) The total number of {ccs} requests that have been successfully executed by the cluster.
+
+`skipped`:::
+(integer) The total number of {ccs} requests (successful or failed) that had at least one remote cluster skipped.
+
+`took`:::
+(object) Contains statistics about the time taken to execute {ccs} requests.
++
+.Properties of `took`
+[%collapsible%open]
+=======
+`max`:::
+(integer) The maximum time taken to execute a {ccs} request, in milliseconds.
+
+`avg`:::
+(integer) The median time taken to execute a {ccs} request, in milliseconds.
+
+`p90`:::
+(integer) The 90th percentile of the time taken to execute {ccs} requests, in milliseconds.
+=======
+
+`took_mrt_true`::
+(object) Contains statistics about the time taken to execute {ccs} requests for which the
+<<ccs-minimize-roundtrips,`ccs_minimize_roundtrips`>> setting was set to `true`.
++
+.Properties of `took_mrt_true`
+[%collapsible%open]
+=======
+`max`:::
+(integer) The maximum time taken to execute a {ccs} request, in milliseconds.
+
+`avg`:::
+(integer) The median time taken to execute a {ccs} request, in milliseconds.
+
+`p90`:::
+(integer) The 90th percentile of the time taken to execute {ccs} requests, in milliseconds.
+=======
+
+`took_mrt_false`::
+(object) Contains statistics about the time taken to execute {ccs} requests for which the
+<<ccs-minimize-roundtrips,`ccs_minimize_roundtrips`>> setting was set to `false`.
++
+.Properties of `took_mrt_false`
+[%collapsible%open]
+=======
+`max`:::
+(integer) The maximum time taken to execute a {ccs} request, in milliseconds.
+
+`avg`:::
+(integer) The median time taken to execute a {ccs} request, in milliseconds.
+
+`p90`:::
+(integer) The 90th percentile of the time taken to execute {ccs} requests, in milliseconds.
+=======
+
+`remotes_per_search_max`::
+(integer) The maximum number of remote clusters that were queried in a single {ccs} request.
+
+`remotes_per_search_avg`::
+(float) The average number of remote clusters that were queried in a single {ccs} request.
+
+`failure_reasons`::
+(object) Contains statistics about the reasons for {ccs} request failures.
+The keys are the failure reason names and the values are the number of requests that failed for that reason.
+
+`features`::
+(object) Contains statistics about the features used in {ccs} requests. The keys are the names of the search feature,
+and the values are the number of requests that used that feature. Single request can use more than one feature
+(e.g. both `async` and `wildcard`). Known features are:
+
+* `async` - <<async-search, Async search>>
+
+* `mrt` - <<ccs-minimize-roundtrips,`ccs_minimize_roundtrips`>> setting was set to `true`.
+
+* `wildcard` - <<api-multi-index,Multi-target syntax>> for indices with wildcards was used in the search request.
+
+`clients`::
+(object) Contains statistics about the clients that executed {ccs} requests.
+The keys are the names of the clients, and the values are the number of requests that were executed by that client.
+Only known clients (such as `kibana` or `elasticsearch`) are counted.
+
+`clusters`::
+(object) Contains statistics about the clusters that were queried in {ccs} requests.
+The keys are cluster names, and the values are per-cluster telemetry data.
+This also includes the local cluster itself, which uses the name `(local)`.
++
+.Properties of per-cluster data:
+[%collapsible%open]
+=======
+`total`:::
+(integer) The total number of successful (not skipped) {ccs} requests that were executed against this cluster.
+This may include requests where partial results were returned, but not requests in which the cluster has been skipped entirely.
+
+`skipped`:::
+(integer) The total number of {ccs} requests for which this cluster was skipped.
+
+`took`:::
+(object) Contains statistics about the time taken to execute requests against this cluster.
++
+.Properties of `took`
+[%collapsible%open]
+========
+`max`:::
+(integer) The maximum time taken to execute a {ccs} request, in milliseconds.
+
+`avg`:::
+(integer) The median time taken to execute a {ccs} request, in milliseconds.
+
+`p90`:::
+(integer) The 90th percentile of the time taken to execute {ccs} requests, in milliseconds.
+========
+
+=======
+
+======
+
+=====
+
 [[cluster-stats-api-example]]
 ==== {api-examples-title}
 
@@ -1607,7 +1743,35 @@ The API returns the following response:
    },
    "repositories": {
      ...
-   }
+   },
+   "ccs": {
+     "_search": {
+        "total": 7,
+        "success": 7,
+        "skipped": 0,
+        "took": {
+            "max": 36,
+            "avg": 20,
+            "p90": 33
+        },
+        "took_mrt_true": {
+            "max": 33,
+            "avg": 15,
+            "p90": 33
+        },
+        "took_mrt_false": {
+            "max": 36,
+            "avg": 26,
+            "p90": 36
+        },
+        "remotes_per_search_max": 3,
+        "remotes_per_search_avg": 2.0,
+        "failure_reasons": { ... },
+        "features": { ... },
+        "clients": { ... },
+        "clusters": { ... }
+     }
+  }
 }
 --------------------------------------------------
 // TESTRESPONSE[s/"plugins": \[[^\]]*\]/"plugins": $body.$_path/]
@@ -1618,10 +1782,15 @@ The API returns the following response:
 // TESTRESPONSE[s/"packaging_types": \[[^\]]*\]/"packaging_types": $body.$_path/]
 // TESTRESPONSE[s/"snapshots": \{[^\}]*\}/"snapshots": $body.$_path/]
 // TESTRESPONSE[s/"repositories": \{[^\}]*\}/"repositories": $body.$_path/]
+// TESTRESPONSE[s/"clusters": \{[^\}]*\}/"clusters": $body.$_path/]
+// TESTRESPONSE[s/"features": \{[^\}]*\}/"features": $body.$_path/]
+// TESTRESPONSE[s/"clients": \{[^\}]*\}/"clients": $body.$_path/]
+// TESTRESPONSE[s/"failure_reasons": \{[^\}]*\}/"failure_reasons": $body.$_path/]
 // TESTRESPONSE[s/"field_types": \[[^\]]*\]/"field_types": $body.$_path/]
 // TESTRESPONSE[s/"runtime_field_types": \[[^\]]*\]/"runtime_field_types": $body.$_path/]
 // TESTRESPONSE[s/"search": \{[^\}]*\}/"search": $body.$_path/]
-// TESTRESPONSE[s/: true|false/: $body.$_path/]
+// TESTRESPONSE[s/"remotes_per_search_avg": [.0-9]+/"remotes_per_search_avg": $body.$_path/]
+// TESTRESPONSE[s/: (true|false)/: $body.$_path/]
 // TESTRESPONSE[s/: (\-)?[0-9]+/: $body.$_path/]
 // TESTRESPONSE[s/: "[^"]*"/: $body.$_path/]
 // These replacements do a few things:

muted-tests.yml

@@ -154,9 +154,6 @@ tests:
   issue: https://github.com/elastic/elasticsearch/issues/112471
 - class: org.elasticsearch.ingest.geoip.IngestGeoIpClientYamlTestSuiteIT
   issue: https://github.com/elastic/elasticsearch/issues/111497
-- class: org.elasticsearch.smoketest.SmokeTestIngestWithAllDepsClientYamlTestSuiteIT
-  method: test {yaml=ingest/80_ingest_simulate/Test ingest simulate with reroute and mapping validation from templates}
-  issue: https://github.com/elastic/elasticsearch/issues/112575
 - class: org.elasticsearch.script.mustache.LangMustacheClientYamlTestSuiteIT
   method: test {yaml=lang_mustache/50_multi_search_template/Multi-search template with errors}
   issue: https://github.com/elastic/elasticsearch/issues/112580

qa/smoke-test-ingest-with-all-dependencies/src/yamlRestTest/resources/rest-api-spec/test/ingest/80_ingest_simulate.yml

@@ -217,7 +217,9 @@ setup:
 "Test ingest simulate with reroute and mapping validation from templates":
 
   - skip:
-      features: headers
+      features:
+        - headers
+        - allowed_warnings
 
   - requires:
       cluster_features: ["simulate.mapping.validation.templates"]
@@ -241,6 +243,8 @@ setup:
   - match: { acknowledged: true }
 
   - do:
+      allowed_warnings:
+        - "index template [first-index-template] has index patterns [first-index*] matching patterns from existing older templates [global] with patterns (global => [*]); this template [first-index-template] will take precedence during new index creation"
       indices.put_index_template:
         name: first-index-template
         body:
@@ -255,6 +259,8 @@ setup:
                   type: text
 
   - do:
+      allowed_warnings:
+        - "index template [second-index-template] has index patterns [second-index*] matching patterns from existing older templates [global] with patterns (global => [*]); this template [second-index-template] will take precedence during new index creation"
       indices.put_index_template:
         name: second-index-template
         body:

server/src/main/java/org/elasticsearch/TransportVersions.java

@@ -207,6 +207,7 @@ static TransportVersion def(int id) {
     public static final TransportVersion UNASSIGNED_PRIMARY_COUNT_ON_CLUSTER_HEALTH = def(8_737_00_0);
     public static final TransportVersion ESQL_AGGREGATE_EXEC_TRACKS_INTERMEDIATE_ATTRS = def(8_738_00_0);
 
+    public static final TransportVersion CCS_TELEMETRY_STATS = def(8_739_00_0);
     /*
      * STOP! READ THIS FIRST! No, really,
      *        ____ _____ ___  ____  _        ____  _____    _    ____    _____ _   _ ___ ____    _____ ___ ____  ____ _____ _

server/src/main/java/org/elasticsearch/action/admin/cluster/stats/CCSTelemetrySnapshot.java

@@ -277,7 +277,7 @@ public int hashCode() {
      */
     public void add(CCSTelemetrySnapshot stats) {
         // This should be called in ClusterStatsResponse ctor only, so we don't need to worry about concurrency
-        if (stats.totalCount == 0) {
+        if (stats == null || stats.totalCount == 0) {
             // Just ignore the empty stats.
             // This could happen if the node is brand new or if the stats are not available, e.g. because it runs an old version.
             return;
@@ -315,7 +315,7 @@ public void add(CCSTelemetrySnapshot stats) {
      *      "p90": 2570
      * }
      */
-    public static void publishLatency(XContentBuilder builder, String name, LongMetricValue took) throws IOException {
+    private static void publishLatency(XContentBuilder builder, String name, LongMetricValue took) throws IOException {
         builder.startObject(name);
         {
             builder.field("max", took.max());

server/src/main/java/org/elasticsearch/action/admin/cluster/stats/CCSUsageTelemetry.java

@@ -175,7 +175,7 @@ public static class PerClusterCCSTelemetry {
         // The number of successful (not skipped) requests to this cluster.
         private final LongAdder count;
         private final LongAdder skippedCount;
-        // This is only over the successful requetss, skipped ones do not count here.
+        // This is only over the successful requests, skipped ones do not count here.
         private final LongMetric took;
 
         PerClusterCCSTelemetry(String clusterAlias) {

server/src/main/java/org/elasticsearch/action/admin/cluster/stats/ClusterStatsNodeResponse.java

@@ -30,6 +30,7 @@ public class ClusterStatsNodeResponse extends BaseNodeResponse {
     private final ClusterHealthStatus clusterStatus;
     private final SearchUsageStats searchUsageStats;
     private final RepositoryUsageStats repositoryUsageStats;
+    private final CCSTelemetrySnapshot ccsMetrics;
 
     public ClusterStatsNodeResponse(StreamInput in) throws IOException {
         super(in);
@@ -47,6 +48,11 @@ public ClusterStatsNodeResponse(StreamInput in) throws IOException {
         } else {
             repositoryUsageStats = RepositoryUsageStats.EMPTY;
         }
+        if (in.getTransportVersion().onOrAfter(TransportVersions.CCS_TELEMETRY_STATS)) {
+            ccsMetrics = new CCSTelemetrySnapshot(in);
+        } else {
+            ccsMetrics = new CCSTelemetrySnapshot();
+        }
     }
 
     public ClusterStatsNodeResponse(
@@ -56,7 +62,8 @@ public ClusterStatsNodeResponse(
         NodeStats nodeStats,
         ShardStats[] shardsStats,
         SearchUsageStats searchUsageStats,
-        RepositoryUsageStats repositoryUsageStats
+        RepositoryUsageStats repositoryUsageStats,
+        CCSTelemetrySnapshot ccsTelemetrySnapshot
     ) {
         super(node);
         this.nodeInfo = nodeInfo;
@@ -65,6 +72,7 @@ public ClusterStatsNodeResponse(
         this.clusterStatus = clusterStatus;
         this.searchUsageStats = Objects.requireNonNull(searchUsageStats);
         this.repositoryUsageStats = Objects.requireNonNull(repositoryUsageStats);
+        this.ccsMetrics = ccsTelemetrySnapshot;
     }
 
     public NodeInfo nodeInfo() {
@@ -95,6 +103,10 @@ public RepositoryUsageStats repositoryUsageStats() {
         return repositoryUsageStats;
     }
 
+    public CCSTelemetrySnapshot getCcsMetrics() {
+        return ccsMetrics;
+    }
+
     @Override
     public void writeTo(StreamOutput out) throws IOException {
         super.writeTo(out);
@@ -108,5 +120,9 @@ public void writeTo(StreamOutput out) throws IOException {
         if (out.getTransportVersion().onOrAfter(TransportVersions.REPOSITORIES_TELEMETRY)) {
             repositoryUsageStats.writeTo(out);
         } // else just drop these stats, ok for bwc
+        if (out.getTransportVersion().onOrAfter(TransportVersions.CCS_TELEMETRY_STATS)) {
+            ccsMetrics.writeTo(out);
+        }
     }
+
 }