[improvement][mongodb cdc]optimize startup performance (#519)

use 'collection.estimatedDocumentCount();' replace 'collection.countDocuments();'
apache · Nov 26, 2024 · ba0f97a · ba0f97a
1 parent 3ac63f2
commit ba0f97a
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/...connector/src/main/java/org/apache/doris/flink/tools/cdc/mongodb/MongoDBDatabaseSync.java b/...connector/src/main/java/org/apache/doris/flink/tools/cdc/mongodb/MongoDBDatabaseSync.java
@@ -114,7 +114,7 @@ public List<SourceSchema> getSchemaList() throws Exception {
                     throw new IllegalStateException("No documents in collection to infer schema");
                 }
 
-                long totalDocuments = collection.countDocuments();
+                long totalDocuments = collection.estimatedDocumentCount();
                 long sampleSize = (long) Math.ceil(totalDocuments * samplePercent);
                 ArrayList<Document> documents = sampleData(collection, sampleSize);
                 MongoDBSchema mongoDBSchema =