[receiver:elasticsearchreceiver]: Add additional node level metric fo…

…r cache count (open-telemetry#14028)

Add additional Elasticsearchreceiver node level metric:

- This new metric tracks the query cache counts for hit & miss

receiver/elasticsearchreceiver/documentation.md

@@ -26,6 +26,7 @@ These are the metrics available for this scraper.
 | **elasticsearch.indexing_pressure.memory.total.primary_rejections** | Cumulative number of indexing requests rejected in the primary stage. | 1 | Sum(Int) | <ul> </ul> |
 | **elasticsearch.indexing_pressure.memory.total.replica_rejections** | Number of indexing requests rejected in the replica stage. | 1 | Sum(Int) | <ul> </ul> |
 | **elasticsearch.memory.indexing_pressure** | Memory consumed, in bytes, by indexing requests in the specified stage. | By | Sum(Int) | <ul> <li>indexing_pressure_stage</li> </ul> |
+| **elasticsearch.node.cache.count** | Total count of query cache misses across all shards assigned to selected nodes. | {count} | Sum(Int) | <ul> <li>query_cache_count_type</li> </ul> |
 | **elasticsearch.node.cache.evictions** | The number of evictions from the cache. | {evictions} | Sum(Int) | <ul> <li>cache_name</li> </ul> |
 | **elasticsearch.node.cache.memory.usage** | The size in bytes of the cache. | By | Sum(Int) | <ul> <li>cache_name</li> </ul> |
 | **elasticsearch.node.cluster.connections** | The number of open tcp connections for internal cluster communication. | {connections} | Sum(Int) | <ul> </ul> |
@@ -114,6 +115,7 @@ metrics:
 | memory_pool_name (name) | The name of the JVM memory pool. | |
 | memory_state (state) | State of the memory | free, used |
 | operation (operation) | The type of operation. | index, delete, get, query, fetch, scroll, suggest, merge, refresh, flush, warmer |
+| query_cache_count_type (type) | Type of query cache count | hit, miss |
 | shard_state (state) | The state of the shard. | active, relocating, initializing, unassigned |
 | task_state (state) | The state of the task. | rejected, completed |
 | thread_pool_name | The name of the thread pool. | |

receiver/elasticsearchreceiver/metadata.yaml

@@ -131,6 +131,12 @@ attributes:
  ingest_pipeline_name:
  value: name
  description: Name of the ingest pipeline.
+ query_cache_count_type:
+ value: type
+ description: Type of query cache count
+ enum:
+ - hit
+ - miss
 metrics:
  # these metrics are from /_nodes/stats, and are node level metrics
  elasticsearch.breaker.memory.estimated:
@@ -176,6 +182,15 @@ metrics:
  value_type: int
  attributes: [cache_name]
  enabled: true
+ elasticsearch.node.cache.count:
+ description: Total count of query cache misses across all shards assigned to selected nodes.
+ unit: "{count}"
+ sum:
+ monotonic: false
+ aggregation: cumulative
+ value_type: int
+ attributes: [ query_cache_count_type ]
+ enabled: true
  elasticsearch.node.fs.disk.available:
  description: The amount of disk space available to the JVM across all file stores for this node. Depending on OS or process level restrictions, this might appear less than free. This is the actual amount of free disk space the Elasticsearch node can utilise.
  unit: By

receiver/elasticsearchreceiver/scraper.go

@@ -120,6 +120,9 @@ func (r *elasticsearchScraper) scrapeNodeMetrics(ctx context.Context, now pcommo
  r.mb.RecordElasticsearchNodeCacheEvictionsDataPoint(now, info.Indices.FieldDataCache.Evictions, metadata.AttributeCacheNameFielddata)
  r.mb.RecordElasticsearchNodeCacheEvictionsDataPoint(now, info.Indices.QueryCache.Evictions, metadata.AttributeCacheNameQuery)
 
+ r.mb.RecordElasticsearchNodeCacheCountDataPoint(now, info.Indices.QueryCache.HitCount, metadata.AttributeQueryCacheCountTypeHit)
+ r.mb.RecordElasticsearchNodeCacheCountDataPoint(now, info.Indices.QueryCache.MissCount, metadata.AttributeQueryCacheCountTypeMiss)
+
  r.mb.RecordElasticsearchNodeFsDiskAvailableDataPoint(now, info.FS.Total.AvailableBytes)
  r.mb.RecordElasticsearchNodeFsDiskFreeDataPoint(now, info.FS.Total.FreeBytes)
  r.mb.RecordElasticsearchNodeFsDiskTotalDataPoint(now, info.FS.Total.TotalBytes)

receiver/elasticsearchreceiver/testdata/expected_metrics/clusterSkip.json

@@ -793,6 +793,42 @@
  },
  "unit": "By"
  },
+ {
+ "description": "Total count of query cache misses across all shards assigned to selected nodes.",
+ "name": "elasticsearch.node.cache.count",
+ "sum": {
+ "aggregationTemporality": "AGGREGATION_TEMPORALITY_CUMULATIVE",
+ "dataPoints": [
+ {
+ "asInt": "333",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "hit"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952760849369000",
+ "timeUnixNano": "1662952760851518000"
+ },
+ {
+ "asInt": "5324",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "miss"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952760849369000",
+ "timeUnixNano": "1662952760851518000"
+ }
+ ]
+ },
+ "unit": "{count}"
+ },
  {
  "description": "The number of evictions from the cache.",
  "name": "elasticsearch.node.cache.evictions",

receiver/elasticsearchreceiver/testdata/expected_metrics/full.json

@@ -793,6 +793,42 @@
  },
  "unit": "By"
  },
+ {
+ "description": "Total count of query cache misses across all shards assigned to selected nodes.",
+ "name": "elasticsearch.node.cache.count",
+ "sum": {
+ "aggregationTemporality": "AGGREGATION_TEMPORALITY_CUMULATIVE",
+ "dataPoints": [
+ {
+ "asInt": "333",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "hit"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952599630580000",
+ "timeUnixNano": "1662952599632385000"
+ },
+ {
+ "asInt": "5324",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "miss"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952599630580000",
+ "timeUnixNano": "1662952599632385000"
+ }
+ ]
+ },
+ "unit": "{count}"
+ },
  {
  "description": "The number of evictions from the cache.",
  "name": "elasticsearch.node.cache.evictions",

receiver/elasticsearchreceiver/testdata/expected_metrics/fullWithoutDirection.json

@@ -793,6 +793,42 @@
  },
  "unit": "By"
  },
+ {
+ "description": "Total count of query cache misses across all shards assigned to selected nodes.",
+ "name": "elasticsearch.node.cache.count",
+ "sum": {
+ "aggregationTemporality": "AGGREGATION_TEMPORALITY_CUMULATIVE",
+ "dataPoints": [
+ {
+ "asInt": "333",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "hit"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952651341631000",
+ "timeUnixNano": "1662952651343244000"
+ },
+ {
+ "asInt": "5324",
+ "attributes": [
+ {
+ "key": "type",
+ "value": {
+ "stringValue": "miss"
+ }
+ }
+ ],
+ "startTimeUnixNano": "1662952651341631000",
+ "timeUnixNano": "1662952651343244000"
+ }
+ ]
+ },
+ "unit": "{count}"
+ },
  {
  "description": "The number of evictions from the cache.",
  "name": "elasticsearch.node.cache.evictions",

unreleased/add-additional-es-node-metric-cache-count.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: elasticsearchreceiver
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add additional node metric for cache count
+
+# One or more tracking issues related to the change
+issues: [14027]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: