From 867b5772f63795d220ad0f9fa8986c68e8042146 Mon Sep 17 00:00:00 2001
From: xuchuanyin <xuchuanyin@apache.org>
Date: Tue, 14 Dec 2021 22:32:24 +0800
Subject: [PATCH] clear memory of sample data right after BinMapper is
 constructed to save memory

Sample data is useless after BinMapper is constructed, but the corresponding memory is still there before feature extraction is finished.
---
 src/io/dataset_loader.cpp | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/io/dataset_loader.cpp b/src/io/dataset_loader.cpp
index 1beff696f904..5ab6572b14b9 100644
--- a/src/io/dataset_loader.cpp
+++ b/src/io/dataset_loader.cpp
@@ -234,8 +234,9 @@ Dataset* DatasetLoader::LoadFromFile(const char* filename, int rank, int num_mac
       auto sample_data = SampleTextDataFromMemory(text_data);
       CheckSampleSize(sample_data.size(),
                       static_cast<size_t>(dataset->num_data_));
-      // construct feature bin mappers
+      // construct feature bin mappers & clear sample data
       ConstructBinMappersFromTextData(rank, num_machines, sample_data, parser.get(), dataset.get());
+      std::vector<std::string>().swap(sample_data);
       if (dataset->has_raw()) {
         dataset->ResizeRaw(dataset->num_data_);
       }
@@ -254,8 +255,9 @@ Dataset* DatasetLoader::LoadFromFile(const char* filename, int rank, int num_mac
       }
       CheckSampleSize(sample_data.size(),
                       static_cast<size_t>(dataset->num_data_));
-      // construct feature bin mappers
+      // construct feature bin mappers & clear sample data
       ConstructBinMappersFromTextData(rank, num_machines, sample_data, parser.get(), dataset.get());
+      std::vector<std::string>().swap(sample_data);
       if (dataset->has_raw()) {
         dataset->ResizeRaw(dataset->num_data_);
       }