Slow aggregations query

Hi,
I have a problem with queries with aggregations on a big index.
My aggregations are basically facets for students list, so I have high cardinality fields (education, skills, titles etc).
My environment:

CPU Count 4
System Memory 16Gb
EC2 Instance Type m4.xlarge

Count of documents 50M
Document has several nested objects, here is example
https://gist.github.com/aburakovskiy/a5088b87b79130d6be91ee9f981323c3

"education": [
{
"school": "Gemological Institute of America",
"degree": "Graduate jewller, Metal and Jewelry Arts, A",
"startDate": "2001-01-01T00:00:00+0000",
"endDate": "2002-01-01T00:00:00+0000"
},
{
"school": "University of Mumbai",
"degree": "Bachelors , Business/Commerce, General, A",
"startDate": "1998-01-01T00:00:00+0000",
"endDate": "2001-01-01T00:00:00+0000"
}
]

Here is example of query:
https://gist.github.com/aburakovskiy/b6ea9d7170e500ff9b66d6c6dff3dda7

And it took over 3s.

I've tried to enable "eager_global_ordinals", but it didn't increase performance.

Is it possible to improve queries performance (decrease query time to less then 0.5s)?

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