How to fix AggregationExecutionException: Aggregation [agg_name] does not support sampling in Elasticsearch

// Example problematic query
{
  "size": 0,
  "aggs": {
    "sample_docs": {
      "sampler": {
        "shard_size": 100
      },
      "aggs": {
        "avg_price": {           // This is a METRIC aggregation - doesn't support sampling!
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}

# Use the Explain API to understand your query structure
curl -X POST "localhost:9200/your-index/_explain/your-doc-id" -H 'Content-Type: application/json' -d'
{
  "query": { ... },
  "aggs": { ... }
}
'

// BEFORE: Incorrect - sampler wraps metric aggregation
{
  "aggs": {
    "sample_docs": {
      "sampler": {
        "shard_size": 100
      },
      "aggs": {
        "avg_price": {           // METRIC - doesn't support sampling
          "avg": { "field": "price" }
        }
      }
    }
  }
}

// AFTER: Correct - sampler wraps bucket aggregation, metric is nested inside
{
  "aggs": {
    "sample_docs": {
      "sampler": {
        "shard_size": 100
      },
      "aggs": {
        "product_categories": {   // BUCKET aggregation - supports sampling
          "terms": {
            "field": "category.keyword",
            "size": 10
          },
          "aggs": {
            "avg_price": {        // METRIC - now nested inside bucket aggregation
              "avg": { "field": "price" }
            }
          }
        }
      }
    }
  }
}

// Alternative: Use diversified_sampler for more representative sampling
{
  "aggs": {
    "sample_docs": {
      "diversified_sampler": {
        "shard_size": 100,
        "field": "user_id.keyword"  // Ensure samples come from different users
      },
      "aggs": {
        "popular_products": {
          "terms": {
            "field": "product_id.keyword",
            "size": 20
          }
        }
      }
    }
  }
}

// APPROACH 1: Filter query to limit dataset before aggregation
{
  "query": {
    "function_score": {
      "query": { "match_all": {} },
      "random_score": {},  // Random sampling at query level
      "boost_mode": "replace"
    }
  },
  "size": 0,
  "aggs": {
    "avg_price": {          // Direct metric aggregation on filtered results
      "avg": { "field": "price" }
    }
  }
}

// APPROACH 2: Use bucket selector for conditional sampling
{
  "aggs": {
    "price_ranges": {
      "range": {
        "field": "price",
        "ranges": [
          { "to": 50 },
          { "from": 50, "to": 100 },
          { "from": 100 }
        ]
      },
      "aggs": {
        "sample_check": {
          "bucket_selector": {
            "buckets_path": { "count": "_count" },
            "script": "params.count > 1000"  // Only include buckets with >1000 docs
          }
        },
        "avg_rating": {
          "avg": { "field": "rating" }
        }
      }
    }
  }
}

// APPROACH 3: Use scripted metric aggregation with sampling logic
{
  "aggs": {
    "sampled_stats": {
      "scripted_metric": {
        "init_script": "state.samples = []; state.count = 0",
        "map_script": """
          if (Math.random() < 0.1) {  // 10% sampling
            state.samples.add(doc['price'].value);
            state.count++;
          }
        """,
        "combine_script": "return state",
        "reduce_script": """
          double sum = 0;
          long total = 0;
          for (state in states) {
            for (sample in state.samples) {
              sum += sample;
              total++;
            }
          }
          return ['avg': sum/total, 'count': total];
        """
      }
    }
  }
}

# Test 1: Verify which aggregations support sampling
curl -X POST "localhost:9200/test-index/_search?size=0" -H 'Content-Type: application/json' -d'
{
  "aggs": {
    "test_sampler": {
      "sampler": { "shard_size": 100 },
      "aggs": {
        "test_agg": {
          "terms": { "field": "category.keyword" }  // This should work
        }
      }
    }
  }
}
'

# Test 2: Try the diversified_sampler variant
curl -X POST "localhost:9200/test-index/_search?size=0" -H 'Content-Type: application/json' -d'
{
  "aggs": {
    "test_diversified": {
      "diversified_sampler": {
        "shard_size": 100,
        "field": "user_id.keyword"
      },
      "aggs": {
        "test_agg": {
          "date_histogram": {  // Another bucket aggregation that supports sampling
            "field": "timestamp",
            "calendar_interval": "day"
          }
        }
      }
    }
  }
}
'

# Test 3: Check aggregation documentation for compatibility
# Refer to Elasticsearch documentation for each aggregation type
# Bucket aggregations that typically support sampling:
# - terms, significant_terms
# - date_histogram, histogram
# - range, date_range, ip_range
# - filters
# - nested, reverse_nested
# - geohash_grid, geotile_grid

// OPTIMIZATION 1: Use doc_values and keyword fields
{
  "aggs": {
    "categories": {
      "terms": {
        "field": "category.keyword",  // keyword field uses doc_values
        "size": 100,
        "execution_hint": "map"       // Optimize execution
      }
    }
  }
}

// OPTIMIZATION 2: Limit aggregation scope with query filters
{
  "query": {
    "range": {
      "timestamp": {
        "gte": "now-7d/d"  // Only aggregate last 7 days
      }
    }
  },
  "aggs": {
    "daily_sales": {
      "date_histogram": {
        "field": "timestamp",
        "calendar_interval": "day",
        "min_doc_count": 1
      },
      "aggs": {
        "total_sales": {
          "sum": { "field": "amount" }
        }
      }
    }
  }
}

// OPTIMIZATION 3: Use composite aggregation for pagination
{
  "size": 0,
  "aggs": {
    "paged_results": {
      "composite": {
        "size": 1000,
        "sources": [
          {
            "category": {
              "terms": { "field": "category.keyword" }
            }
          }
        ]
      },
      "aggs": {
        "avg_price": {
          "avg": { "field": "price" }
        }
      }
    }
  }
}

// OPTIMIZATION 4: Enable request cache for repeated queries
curl -X PUT "localhost:9200/your-index/_settings" -H 'Content-Type: application/json' -d'
{
  "index.requests.cache.enable": true
}
'

# Monitor aggregation performance with Profile API
curl -X POST "localhost:9200/your-index/_search?size=0" -H 'Content-Type: application/json' -d'
{
  "profile": true,
  "aggs": {
    "test_aggregation": {
      "terms": {
        "field": "category.keyword",
        "size": 50
      }
    }
  }
}
'

# Check aggregation memory usage
curl -X GET "localhost:9200/_nodes/stats/indices/fielddata?human&fields=*" -H 'Content-Type: application/json'

# Monitor circuit breaker trips (related to aggregation memory)
curl -X GET "localhost:9200/_nodes/stats/breaker?human&pretty"

# Use the Validate API to check query syntax
curl -X GET "localhost:9200/your-index/_validate/query?explain" -H 'Content-Type: application/json' -d'
{
  "query": { ... },
  "aggs": { ... }
}
'