Add support for field level segment stats in opensearch stats api #19747
      
        
          +756
        
        
          −55
        
        
          
        
      
    
  
  Add this suggestion to a batch that can be applied as a single commit.
  This suggestion is invalid because no changes were made to the code.
  Suggestions cannot be applied while the pull request is closed.
  Suggestions cannot be applied while viewing a subset of changes.
  Only one suggestion per line can be applied in a batch.
  Add this suggestion to a batch that can be applied as a single commit.
  Applying suggestions on deleted lines is not supported.
  You must change the existing code in this line in order to create a valid suggestion.
  Outdated suggestions cannot be applied.
  This suggestion has been applied or marked resolved.
  Suggestions cannot be applied from pending reviews.
  Suggestions cannot be applied on multi-line comments.
  Suggestions cannot be applied while the pull request is queued to merge.
  Suggestion cannot be applied right now. Please check back later.
  
    
  
    
Summary
This PR adds field-level disk consumption statistics to the
_statsAPI, allowing users to understand how much disk space each field consumes in their Lucene segment files. This feature helps identify which fields are taking up the most space and enables better index optimization decisions.Related Issue
Resolves #12113
Motivation
Users currently have segment-level file size statistics but lack visibility into which fields contribute to disk usage. This makes it difficult to:
Implementation Details
Approach
The implementation uses proportional attribution to calculate field-level statistics:
FieldInfosto determine which fields use which file types.tim,.dvd,.doc, etc.)Testing
Stats API Call
curl -X GET "http://localhost:9200/my-index/_stats/segments?include_field_level_segment_file_sizes=true"Output
{ "_shards": { "total": 6, "successful": 3, "failed": 0 }, "_all": { "primaries": { "segments": { "count": 3, "memory_in_bytes": 0, "terms_memory_in_bytes": 0, "stored_fields_memory_in_bytes": 0, "term_vectors_memory_in_bytes": 0, "norms_memory_in_bytes": 0, "points_memory_in_bytes": 0, "doc_values_memory_in_bytes": 0, "index_writer_memory_in_bytes": 0, "version_map_memory_in_bytes": 0, "fixed_bit_set_memory_in_bytes": 0, "max_unsafe_auto_id_timestamp": -1, "remote_store": { "upload": { "total_upload_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "refresh_size_lag": { "total_bytes": 0, "max_bytes": 0 }, "max_refresh_time_lag_in_millis": 0, "total_time_spent_in_millis": 0, "pressure": { "total_rejections": 0 } }, "download": { "total_download_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "total_time_spent_in_millis": 0 } }, "segment_replication": { "max_bytes_behind": 0, "total_bytes_behind": 0, "max_replication_lag": 0 }, "file_sizes": {}, "field_level_file_sizes": { "_seq_no": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "author": { "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "dvm": { "size_in_bytes": 358 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 } }, "_source": { "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "fdx": { "size_in_bytes": 18 } }, "_id": { "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "title": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } }, "publish_date": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "_version": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "_primary_term": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "views": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "content": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } } } } }, "total": { "segments": { "count": 3, "memory_in_bytes": 0, "terms_memory_in_bytes": 0, "stored_fields_memory_in_bytes": 0, "term_vectors_memory_in_bytes": 0, "norms_memory_in_bytes": 0, "points_memory_in_bytes": 0, "doc_values_memory_in_bytes": 0, "index_writer_memory_in_bytes": 0, "version_map_memory_in_bytes": 0, "fixed_bit_set_memory_in_bytes": 0, "max_unsafe_auto_id_timestamp": -1, "remote_store": { "upload": { "total_upload_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "refresh_size_lag": { "total_bytes": 0, "max_bytes": 0 }, "max_refresh_time_lag_in_millis": 0, "total_time_spent_in_millis": 0, "pressure": { "total_rejections": 0 } }, "download": { "total_download_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "total_time_spent_in_millis": 0 } }, "segment_replication": { "max_bytes_behind": 0, "total_bytes_behind": 0, "max_replication_lag": 0 }, "file_sizes": {}, "field_level_file_sizes": { "_seq_no": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "author": { "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "dvm": { "size_in_bytes": 358 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 } }, "_source": { "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "fdx": { "size_in_bytes": 18 } }, "_id": { "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "title": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } }, "publish_date": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "_version": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "_primary_term": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "views": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "content": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } } } } } }, "indices": { "my-index": { "uuid": "QjqlEhehSRS8pI4xr6_gbg", "primaries": { "segments": { "count": 3, "memory_in_bytes": 0, "terms_memory_in_bytes": 0, "stored_fields_memory_in_bytes": 0, "term_vectors_memory_in_bytes": 0, "norms_memory_in_bytes": 0, "points_memory_in_bytes": 0, "doc_values_memory_in_bytes": 0, "index_writer_memory_in_bytes": 0, "version_map_memory_in_bytes": 0, "fixed_bit_set_memory_in_bytes": 0, "max_unsafe_auto_id_timestamp": -1, "remote_store": { "upload": { "total_upload_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "refresh_size_lag": { "total_bytes": 0, "max_bytes": 0 }, "max_refresh_time_lag_in_millis": 0, "total_time_spent_in_millis": 0, "pressure": { "total_rejections": 0 } }, "download": { "total_download_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "total_time_spent_in_millis": 0 } }, "segment_replication": { "max_bytes_behind": 0, "total_bytes_behind": 0, "max_replication_lag": 0 }, "file_sizes": {}, "field_level_file_sizes": { "_seq_no": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "author": { "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "dvm": { "size_in_bytes": 358 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 } }, "_source": { "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "fdx": { "size_in_bytes": 18 } }, "_id": { "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "title": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } }, "publish_date": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "_version": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "_primary_term": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "views": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "content": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } } } } }, "total": { "segments": { "count": 3, "memory_in_bytes": 0, "terms_memory_in_bytes": 0, "stored_fields_memory_in_bytes": 0, "term_vectors_memory_in_bytes": 0, "norms_memory_in_bytes": 0, "points_memory_in_bytes": 0, "doc_values_memory_in_bytes": 0, "index_writer_memory_in_bytes": 0, "version_map_memory_in_bytes": 0, "fixed_bit_set_memory_in_bytes": 0, "max_unsafe_auto_id_timestamp": -1, "remote_store": { "upload": { "total_upload_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "refresh_size_lag": { "total_bytes": 0, "max_bytes": 0 }, "max_refresh_time_lag_in_millis": 0, "total_time_spent_in_millis": 0, "pressure": { "total_rejections": 0 } }, "download": { "total_download_size": { "started_bytes": 0, "succeeded_bytes": 0, "failed_bytes": 0 }, "total_time_spent_in_millis": 0 } }, "segment_replication": { "max_bytes_behind": 0, "total_bytes_behind": 0, "max_replication_lag": 0 }, "file_sizes": {}, "field_level_file_sizes": { "_seq_no": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "author": { "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "dvm": { "size_in_bytes": 358 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 } }, "_source": { "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 }, "fdx": { "size_in_bytes": 18 } }, "_id": { "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "title": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } }, "publish_date": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "_version": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "_primary_term": { "dvm": { "size_in_bytes": 358 }, "dvd": { "size_in_bytes": 48 }, "fdx": { "size_in_bytes": 18 }, "fnm": { "size_in_bytes": 315 }, "fdt": { "size_in_bytes": 202 } }, "views": { "kdi": { "size_in_bytes": 69 }, "dvd": { "size_in_bytes": 48 }, "fnm": { "size_in_bytes": 315 }, "kdm": { "size_in_bytes": 249 }, "fdt": { "size_in_bytes": 202 }, "kdd": { "size_in_bytes": 129 }, "dvm": { "size_in_bytes": 358 }, "fdx": { "size_in_bytes": 18 } }, "content": { "nvm": { "size_in_bytes": 207 }, "fnm": { "size_in_bytes": 315 }, "pos": { "size_in_bytes": 177 }, "fdt": { "size_in_bytes": 202 }, "doc": { "size_in_bytes": 66 }, "tim": { "size_in_bytes": 340 }, "tip": { "size_in_bytes": 84 }, "fdx": { "size_in_bytes": 18 }, "nvd": { "size_in_bytes": 94 } } } } } } } }Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.