spark 2.1.1 ml.LogisticRegression with large feature set cause Kryo serialization failed: Buffer overflow

I try to train a big model. I have 40 million instances and 50 million feature set, and it is sparse. I am using 40 executors with 20 GB each + driver with 40 GB. The number of data partitions is 5000, the treeAggregate depth is 4, the spark.kryoserializer.buffer.max is 2016m, the spark.driver.maxR

Spark 2.1.1 Driver OOM when use interaction for large scale Sparse Vector

I'm working on large scale logistic regression for ctr prediction, and when user interaction for feature engineer, driver OOM. For detail, I interact among userid(one-hot, 30w dimension, sparse) and base features(60 dimensions, dense), driver memory is set to 40g. So, I try to debug from remote, a