Get response very slowly when using ngram

we using ngram for partial match, and set value 1,1 for min_gram, max_gram. But get response very slowly when using query phrase as follows:
POST trimps2/tb/_search
"query": {
"multi_match": {
"query": "138141",
"type": "phrase",
"slop": 0,
"fields": ["_all"],
"analyzer": "charSplit",
"max_expansions": 1
"profile": true,
"from": 100
charSplit is self-defined analyzer.
Total data size is about 165G, and number of docs is about 501,667,114.
Any idea to model data with other way which can get response quickly. Thank you very much.

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.