Begin by installing the ClickHouse client on your local machine or server where ClickHouse is running. Ensure you have access to the ClickHouse server and that you can run SQL queries. This step is crucial for exporting data from ClickHouse into a format that you can then import into Elasticsearch.

Use SQL queries in the ClickHouse client to export the required data. You can use the `SELECT INTO OUTFILE` command to export data into a CSV or JSON format. For example, you can run:
```sql
SELECT * FROM your_table INTO OUTFILE '/path/to/your_data.csv' FORMAT CSV;
```
This command exports the data into a CSV file, which is a straightforward format to work with for subsequent processing.

Once your data is exported, you may need to transform it into a format compatible with Elasticsearch's bulk API (e.g., JSON format with a specific structure). Write a script in Python or another language to read the CSV file and output a JSON file where each line is a JSON object. Ensure the data is structured according to Elasticsearch's document structure, including index metadata.

Set up an Elasticsearch instance if you haven't already. Define an index and any necessary mappings that match the structure of the data you plan to import. You can do this by using the Elasticsearch API to create an index with the desired mappings:
```json
PUT /your_index
{
"mappings": {
"properties": {
"field1": { "type": "text" },
"field2": { "type": "keyword" },
...
}
}
}
```

Use the Elasticsearch bulk API to import the prepared JSON data. This can be done using a simple script that reads the JSON file and sends HTTP requests to the Elasticsearch endpoint. Here's a basic example using Python's `requests` library:
```python
import json
import requests
with open('/path/to/your_data.json') as f:
data = f.read()
response = requests.post('http://localhost:9200/your_index/_bulk', data=data, headers={"Content-Type": "application/x-ndjson"})
print(response.status_code)
print(response.text)
```
Make sure to handle any errors and check the response for successful import.

After loading the data, verify the import by querying Elasticsearch to ensure that the data is present and correctly indexed. You can use the Elasticsearch query DSL to perform searches and check the document count:
```json
GET /your_index/_search
{
"query": {
"match_all": {}
}
}
```

Review performance and optimize where necessary. Elasticsearch offers various tools and settings to optimize indexing and search performance. Monitor the Elasticsearch cluster's health and performance using its built-in monitoring tools, like Kibana, to ensure everything is working efficiently. Adjust settings as needed to handle the data volume and query load.
By following these steps, you can successfully transfer data from ClickHouse to Elasticsearch without relying on third-party connectors or integrations.