diff --git a/.gitignore b/.gitignore
index 97982775a..3ad01e985 100644
--- a/.gitignore
+++ b/.gitignore
@@ -72,3 +72,4 @@ build
 config.mk
 xgboost
 *.data
+build_plugin
diff --git a/Makefile b/Makefile
index 0243ff553..3528104f4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,3 +1,8 @@
+# flags by plugin
+PLUGIN_OBJS=
+PLUGIN_LDFLAGS=
+PLUGIN_CFLAGS=
+
 ifndef config
 ifneq ("$(wildcard ./config.mk)","")
 	config = config.mk
@@ -36,8 +41,8 @@ ifeq ($(OS), Windows_NT)
 	export CC = gcc -m64
 endif
 
-export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS)
-export CFLAGS=  -std=c++0x -Wall -O3 -msse2  -Wno-unknown-pragmas -funroll-loops -fPIC -Iinclude $(ADD_CFLAGS)
+export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS) $(PLUGIN_LDFLAGS)
+export CFLAGS=  -std=c++0x -Wall -O3 -msse2  -Wno-unknown-pragmas -funroll-loops -fPIC -Iinclude $(ADD_CFLAGS) $(PLUGIN_CFLAGS)
 CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include
 #java include path
 export JAVAINCFLAGS = -I${JAVA_HOME}/include -I./java
@@ -76,7 +81,7 @@ $(RABIT)/lib/$(LIB_RABIT):
 java: java/libxgboost4j.so
 
 SRC = $(wildcard src/*.cc src/*/*.cc)
-ALL_OBJ = $(patsubst src/%.cc, build/%.o, $(SRC))
+ALL_OBJ = $(patsubst src/%.cc, build/%.o, $(SRC)) $(PLUGIN_OBJS)
 AMALGA_OBJ = amalgamation/xgboost-all0.o
 LIB_DEP = $(DMLC_CORE)/libdmlc.a $(RABIT)/lib/$(LIB_RABIT)
 ALL_DEP = $(filter-out build/cli_main.o, $(ALL_OBJ)) $(LIB_DEP)
@@ -87,6 +92,11 @@ build/%.o: src/%.cc
 	$(CXX) $(CFLAGS) -MM -MT build/$*.o $< >build/$*.d
 	$(CXX) -c $(CFLAGS) -c $< -o $@
 
+build_plugin/%.o: plugin/%.cc
+	@mkdir -p $(@D)
+	$(CXX) $(CFLAGS) -MM -MT build_plugin/$*.o $< >build_plugin/$*.d
+	$(CXX) -c $(CFLAGS) -c $< -o $@
+
 # The should be equivalent to $(ALL_OBJ)  except for build/cli_main.o
 amalgamation/xgboost-all0.o: amalgamation/xgboost-all0.cc
 	$(CXX) -c $(CFLAGS) -c $< -o $@
@@ -104,20 +114,20 @@ lib/libxgboost.so: $(ALL_DEP)
 	@mkdir -p $(@D)
 	$(CXX) $(CFLAGS) -shared -o $@ $(filter %.o %.a, $^) $(LDFLAGS)
 
-java/libxgboost4j.so: java/xgboost4j_wrapper.cpp lib/libxgboost.a $(LIB_DEP)
+java/libxgboost4j.so: java/xgboost4j_wrapper.cpp $(ALL_DEP)
 	$(CXX) $(CFLAGS) $(JAVAINCFLAGS) -shared -o $@ $(filter %.cpp %.o %.a, $^) $(LDFLAGS)
 
-xgboost: $(CLI_OBJ) lib/libxgboost.a $(LIB_DEP)
+xgboost: $(CLI_OBJ) $(ALL_DEP)
 	$(CXX) $(CFLAGS) -o $@  $(filter %.o %.a, $^)  $(LDFLAGS)
 
 rcpplint:
 	python2 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} R-package/src
 
 lint: rcpplint
-	python2 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} include src
+	python2 dmlc-core/scripts/lint.py xgboost ${LINT_LANG} include src plugin
 
 clean:
-	$(RM) -rf build lib bin *~ */*~ */*/*~ */*/*/*~ amalgamation/*.o xgboost
+	$(RM) -rf build build_plugin lib bin *~ */*~ */*/*~ */*/*/*~ amalgamation/*.o xgboost
 
 clean_all: clean
 	cd $(DMLC_CORE); make clean; cd -
@@ -157,3 +167,4 @@ Rcheck:
 
 -include build/*.d
 -include build/*/*.d
+-include build_plugin/*/*.d
diff --git a/make/config.mk b/make/config.mk
index 1bf0d7738..d0954fce4 100644
--- a/make/config.mk
+++ b/make/config.mk
@@ -46,3 +46,9 @@ LIB_RABIT = librabit.a
 
 # path to libjvm.so
 LIBJVM=$(JAVA_HOME)/jre/lib/amd64/server
+
+# List of additional plugins, checkout plugin folder.
+# uncomment the following lines to include these plugins
+# you can also add your own plugin like this
+
+# include plugin/example/plugin.mk
diff --git a/plugin/README.md b/plugin/README.md
new file mode 100644
index 000000000..445b60f8e
--- /dev/null
+++ b/plugin/README.md
@@ -0,0 +1,32 @@
+XGBoost Plugins Modules
+=======================
+This folder contains plugin modules to xgboost that can be optionally installed.
+The plugin system helps us to extend xgboost with additional features,
+and add experimental features that may not yet ready to be included in main project.
+
+To include a certain plugin, say ```plugin_a```, you only need to add the following line to the config.mk.
+
+```makefile
+# Add plugin by include the plugin in config
+include plugin/plugin_a/plugin.mk
+```
+
+Then rebuild libxgboost by typing make, you can get a new library with the plugin enabled.
+
+Link Static XGBoost Library with Plugins
+----------------------------------------
+This problem only happens when you link ```libxgboost.a```.
+If you only use ```libxgboost.so```(this include python and other bindings),
+you can ignore this section.
+
+When you want to link ```libxgboost.a``` with additional plugins included,
+you will need to enabled whole archeive via The following option.
+```bash
+--whole-archive libxgboost.a --no-whole-archive
+```
+
+Write Your Own Plugin
+---------------------
+You can plugin your own modules to xgboost by adding code to this folder,
+without modification to the main code repo.
+The [example](example) folder provides an example to write a plugin.
diff --git a/plugin/example/README.md b/plugin/example/README.md
new file mode 100644
index 000000000..7a3eb6685
--- /dev/null
+++ b/plugin/example/README.md
@@ -0,0 +1,21 @@
+XGBoost Plugin Example
+======================
+This folder provides an example of xgboost plugin.
+
+There are three steps you need to to do to add plugin to xgboost
+- Create your source .cc file, implement a new extension
+  - In this example [custom_obj.cc](custom_obj.cc)
+- Register this extension to xgboost via registration macr
+  - In this example ```XGBOOST_REGISTER_OBJECTIVE``` in [this line](custom_obj.cc#L75)
+- Create a [plugin.mk](plugin.mk) on this folder
+
+To add this plugin, add the following line to ```config.mk```(template in make/config.mk).
+```makefile
+# Add plugin by include the plugin in config
+include plugin/example/plugin.mk
+```
+
+Then you can test this plugin by using ```objective=mylogistic``` parameter.
+
+
+
diff --git a/plugin/example/custom_obj.cc b/plugin/example/custom_obj.cc
new file mode 100644
index 000000000..95384f21d
--- /dev/null
+++ b/plugin/example/custom_obj.cc
@@ -0,0 +1,80 @@
+/*!
+ * Copyright 2015 by Contributors
+ * \file custom_metric.cc
+ * \brief This is an example to define plugin of xgboost.
+ *  This plugin defines the additional metric function.
+ */
+#include <xgboost/base.h>
+#include <dmlc/parameter.h>
+#include <xgboost/objective.h>
+
+namespace xgboost {
+namespace obj {
+
+// This is a helpful data structure to define parameters
+// You do not have to use it.
+// see http://dmlc-core.readthedocs.org/en/latest/parameter.html
+// for introduction of this module.
+struct MyLogisticParam : public dmlc::Parameter<MyLogisticParam> {
+  float scale_neg_weight;
+  // declare parameters
+  DMLC_DECLARE_PARAMETER(MyLogisticParam) {
+    DMLC_DECLARE_FIELD(scale_neg_weight).set_default(1.0f).set_lower_bound(0.0f)
+        .describe("Scale the weight of negative examples by this factor");
+  }
+};
+
+DMLC_REGISTER_PARAMETER(MyLogisticParam);
+
+// Define a customized logistic regression objective in C++.
+// Implement the interface.
+class MyLogistic : public ObjFunction {
+ public:
+  void Configure(const std::vector<std::pair<std::string, std::string> >& args) override {
+    param_.InitAllowUnknown(args);
+  }
+  void GetGradient(const std::vector<float> &preds,
+                   const MetaInfo &info,
+                   int iter,
+                   std::vector<bst_gpair> *out_gpair) override {
+    out_gpair->resize(preds.size());
+    for (size_t i = 0; i < preds.size(); ++i) {
+      float w = info.GetWeight(i);
+      // scale the negative examples!
+      if (info.labels[i] == 0.0f) w *= param_.scale_neg_weight;
+      // logistic transoformation
+      float p = 1.0f / (1.0f + expf(-preds[i]));
+      // this is the gradient
+      float grad = (p - info.labels[i]) * w;
+      // this is the second order gradient
+      float hess = p * (1.0f - p) * w;
+      out_gpair->at(i) = bst_gpair(grad, hess);
+    }
+  }
+  const char* DefaultEvalMetric() const override {
+    return "error";
+  }
+  void PredTransform(std::vector<float> *io_preds) override {
+    // transform margin value to probability.
+    std::vector<float> &preds = *io_preds;
+    for (size_t i = 0; i < preds.size(); ++i) {
+      preds[i] = 1.0f / (1.0f + expf(-preds[i]));
+    }
+  }
+  float ProbToMargin(float base_score) const override {
+    // transform probability to margin value
+    return -std::log(1.0f / base_score - 1.0f);
+  }
+
+ private:
+  MyLogisticParam param_;
+};
+
+// Finally register the objective function.
+// After it succeeds you can try use xgboost with objective=mylogistic
+XGBOOST_REGISTER_OBJECTIVE(MyLogistic, "mylogistic")
+.describe("User defined logistic regression plugin")
+.set_body([]() { return new MyLogistic(); });
+
+}  // namespace obj
+}  // namespace xgboost
diff --git a/plugin/example/plugin.mk b/plugin/example/plugin.mk
new file mode 100644
index 000000000..8ebd26d61
--- /dev/null
+++ b/plugin/example/plugin.mk
@@ -0,0 +1,4 @@
+# Add the object files you like to include in this plugin.
+PLUGIN_OBJS += build_plugin/example/custom_obj.o
+# Add additional dependent libraries this plugin might have
+PLUGIN_LDFLAGS +=
\ No newline at end of file
diff --git a/plugin/lz4/plugin.mk b/plugin/lz4/plugin.mk
new file mode 100644
index 000000000..7a69027c7
--- /dev/null
+++ b/plugin/lz4/plugin.mk
@@ -0,0 +1,2 @@
+PLUGIN_OBJS += build_plugin/lz4/sparse_page_lz4_format.o
+PLUGIN_LDFLAGS += -llz4
diff --git a/plugin/lz4/sparse_page_lz4_format.cc b/plugin/lz4/sparse_page_lz4_format.cc
new file mode 100644
index 000000000..11d80defe
--- /dev/null
+++ b/plugin/lz4/sparse_page_lz4_format.cc
@@ -0,0 +1,281 @@
+/*!
+ * Copyright (c) 2015 by Contributors
+ * \file sparse_page_lz4_format.cc
+ *  XGBoost Plugin to enable LZ4 compressed format on the external memory pages.
+ */
+#include <xgboost/data.h>
+#include <xgboost/logging.h>
+#include <dmlc/registry.h>
+#include <lz4.h>
+#include <lz4hc.h>
+#include "../../src/data/sparse_batch_page.h"
+
+namespace xgboost {
+namespace data {
+
+DMLC_REGISTRY_FILE_TAG(sparse_page_lz4_format);
+
+// array to help compression of decompression.
+template<typename DType>
+class CompressArray {
+ public:
+  // the data content.
+  std::vector<DType> data;
+  // Decompression helper
+  // number of chunks
+  inline int num_chunk() const {
+    CHECK_GT(raw_chunks_.size(), 1);
+    return static_cast<int>(raw_chunks_.size() - 1);
+  }
+  // raw bytes
+  inline size_t RawBytes() const {
+    return raw_chunks_.back() * sizeof(DType);
+  }
+  // encoded bytes
+  inline size_t EncodedBytes() const {
+    return encoded_chunks_.back() +
+        (encoded_chunks_.size() + raw_chunks_.size()) * sizeof(bst_uint);
+  }
+  // load the array from file.
+  inline void Read(dmlc::SeekStream* fi);
+  // run decode on chunk_id
+  inline void Decompress(int chunk_id);
+  // Compression helper
+  // initialize the compression chunks
+  inline void InitCompressChunks(const std::vector<bst_uint>& chunk_ptr);
+  // initialize the compression chunks
+  inline void InitCompressChunks(size_t chunk_size, size_t max_nchunk);
+  // run decode on chunk_id
+  inline void Compress(int chunk_id);
+  // save the output buffer into file.
+  inline void Write(dmlc::Stream* fo);
+
+ private:
+  // the chunk split of the data, by number of elements
+  std::vector<bst_uint> raw_chunks_;
+  // the encoded chunk, by number of bytes
+  std::vector<bst_uint> encoded_chunks_;
+  // output buffer of compression.
+  std::vector<std::string> out_buffer_;
+  // input buffer of data.
+  std::string in_buffer_;
+};
+
+template<typename DType>
+inline void CompressArray<DType>::Read(dmlc::SeekStream* fi) {
+  CHECK(fi->Read(&raw_chunks_));
+  CHECK(fi->Read(&encoded_chunks_));
+  size_t buffer_size = encoded_chunks_.back();
+  in_buffer_.resize(buffer_size);
+  CHECK_EQ(fi->Read(dmlc::BeginPtr(in_buffer_), buffer_size), buffer_size);
+  data.resize(raw_chunks_.back());
+}
+
+template<typename DType>
+inline void CompressArray<DType>::Decompress(int chunk_id) {
+  int chunk_size = static_cast<int>(
+      raw_chunks_[chunk_id + 1] - raw_chunks_[chunk_id]) * sizeof(DType);
+  int encoded_size = static_cast<int>(
+      encoded_chunks_[chunk_id + 1] - encoded_chunks_[chunk_id]);
+  // decompress data
+  int src_size = LZ4_decompress_fast(
+      dmlc::BeginPtr(in_buffer_) + encoded_chunks_[chunk_id],
+      reinterpret_cast<char*>(dmlc::BeginPtr(data) + raw_chunks_[chunk_id]),
+      chunk_size);
+  CHECK_EQ(encoded_size, src_size);
+}
+
+template<typename DType>
+inline void CompressArray<DType>::InitCompressChunks(
+    const std::vector<bst_uint>& chunk_ptr) {
+  raw_chunks_ = chunk_ptr;
+  CHECK_GE(raw_chunks_.size(), 2);
+  out_buffer_.resize(raw_chunks_.size() - 1);
+  for (size_t i = 0; i < out_buffer_.size(); ++i) {
+    out_buffer_[i].resize(raw_chunks_[i + 1] - raw_chunks_[i]);
+  }
+}
+
+template<typename DType>
+inline void CompressArray<DType>::InitCompressChunks(size_t chunk_size, size_t max_nchunk) {
+  raw_chunks_.clear();
+  raw_chunks_.push_back(0);
+  size_t min_chunk_size = data.size() / max_nchunk;
+  chunk_size = std::max(min_chunk_size, chunk_size);
+  size_t nstep = data.size() / chunk_size;
+  for (size_t i = 0; i < nstep; ++i) {
+    raw_chunks_.push_back(raw_chunks_.back() + chunk_size * i);
+  }
+  if (nstep == 0) raw_chunks_.push_back(0);
+  raw_chunks_.back() = data.size();
+  CHECK_GE(raw_chunks_.size(), 2);
+  out_buffer_.resize(raw_chunks_.size() - 1);
+  for (size_t i = 0; i < out_buffer_.size(); ++i) {
+    out_buffer_[i].resize(raw_chunks_[i + 1] - raw_chunks_[i]);
+  }
+}
+
+template<typename DType>
+inline void CompressArray<DType>::Compress(int chunk_id) {
+  CHECK_LT(static_cast<size_t>(chunk_id + 1), raw_chunks_.size());
+  std::string& buf = out_buffer_[chunk_id];
+  size_t raw_chunk_size = (raw_chunks_[chunk_id + 1] - raw_chunks_[chunk_id]) * sizeof(DType);
+  int bound = LZ4_compressBound(raw_chunk_size);
+  CHECK_NE(bound, 0);
+  buf.resize(bound);
+  int encoded_size = LZ4_compress_HC(
+      reinterpret_cast<char*>(dmlc::BeginPtr(data) + raw_chunks_[chunk_id]),
+      dmlc::BeginPtr(buf), raw_chunk_size, buf.length(), 9);
+  CHECK_NE(encoded_size, 0);
+  CHECK_LE(static_cast<size_t>(encoded_size), buf.length());
+  buf.resize(encoded_size);
+}
+
+template<typename DType>
+inline void CompressArray<DType>::Write(dmlc::Stream* fo) {
+  encoded_chunks_.clear();
+  encoded_chunks_.push_back(0);
+  for (size_t i = 0; i < out_buffer_.size(); ++i) {
+    encoded_chunks_.push_back(encoded_chunks_.back() + out_buffer_[i].length());
+  }
+  fo->Write(raw_chunks_);
+  fo->Write(encoded_chunks_);
+  for (const std::string& buf : out_buffer_) {
+    fo->Write(dmlc::BeginPtr(buf), buf.length());
+  }
+}
+
+class SparsePageLZ4Format : public SparsePage::Format {
+ public:
+  SparsePageLZ4Format()
+      : raw_bytes_(0), encoded_bytes_(0) {
+    nthread_ = 4;
+    raw_bytes_ = encoded_bytes_ = 0;
+  }
+  ~SparsePageLZ4Format() {
+    if (raw_bytes_ != 0) {
+      LOG(CONSOLE) << "raw_bytes=" << raw_bytes_
+                   << ", encoded_bytes=" << encoded_bytes_
+                   << ", ratio=" << double(encoded_bytes_) / raw_bytes_;
+    }
+  }
+
+  bool Read(SparsePage* page, dmlc::SeekStream* fi) override {
+    if (!fi->Read(&(page->offset))) return false;
+    CHECK_NE(page->offset.size(), 0) << "Invalid SparsePage file";
+    this->LoadIndexValue(fi);
+
+    page->data.resize(page->offset.back());
+    CHECK_EQ(index_.data.size(), value_.data.size());
+    CHECK_EQ(index_.data.size(), page->data.size());
+    for (size_t i = 0; i < page->data.size(); ++i) {
+      page->data[i] = SparseBatch::Entry(index_.data[i], value_.data[i]);
+    }
+    return true;
+  }
+
+  bool Read(SparsePage* page,
+            dmlc::SeekStream* fi,
+            const std::vector<bst_uint>& sorted_index_set) override {
+    if (!fi->Read(&disk_offset_)) return false;
+    this->LoadIndexValue(fi);
+
+    page->offset.clear();
+    page->offset.push_back(0);
+    for (bst_uint cid : sorted_index_set) {
+      page->offset.push_back(
+          page->offset.back() + disk_offset_[cid + 1] - disk_offset_[cid]);
+    }
+    page->data.resize(page->offset.back());
+    CHECK_EQ(index_.data.size(), value_.data.size());
+    CHECK_EQ(index_.data.size(), disk_offset_.back());
+
+    for (size_t i = 0; i < sorted_index_set.size(); ++i) {
+      bst_uint cid = sorted_index_set[i];
+      size_t dst_begin = page->offset[i];
+      size_t src_begin = disk_offset_[cid];
+      size_t num = disk_offset_[cid + 1] - disk_offset_[cid];
+      for (size_t j = 0; j < num; ++j) {
+        page->data[dst_begin + j] = SparseBatch::Entry(
+            index_.data[src_begin + j], value_.data[src_begin + j]);
+      }
+    }
+    return true;
+  }
+
+  void Write(const SparsePage& page, dmlc::Stream* fo) override {
+    CHECK(page.offset.size() != 0 && page.offset[0] == 0);
+    CHECK_EQ(page.offset.back(), page.data.size());
+    fo->Write(page.offset);
+    index_.data.resize(page.data.size());
+    value_.data.resize(page.data.size());
+
+    for (size_t i = 0; i < page.data.size(); ++i) {
+      index_.data[i] = page.data[i].index;
+      value_.data[i] = page.data[i].fvalue;
+    }
+
+    index_.InitCompressChunks(kChunkSize, kMaxChunk);
+    value_.InitCompressChunks(kChunkSize, kMaxChunk);
+
+    int nindex = index_.num_chunk();
+    int nvalue = value_.num_chunk();
+    int ntotal = nindex + nvalue;
+    #pragma omp parallel for schedule(dynamic, 1) num_threads(nthread_)
+    for (int i = 0; i < ntotal; ++i) {
+      if (i < nindex) {
+        index_.Compress(i);
+      } else {
+        value_.Compress(i - nindex);
+      }
+    }
+    index_.Write(fo);
+    value_.Write(fo);
+    raw_bytes_ += index_.RawBytes() + value_.RawBytes() + page.offset.size() * sizeof(size_t);
+    encoded_bytes_ += index_.EncodedBytes() +
+        value_.EncodedBytes() + page.offset.size() * sizeof(size_t);
+  }
+
+  inline void LoadIndexValue(dmlc::SeekStream* fi) {
+    index_.Read(fi);
+    value_.Read(fi);
+
+    int nindex = index_.num_chunk();
+    int nvalue = value_.num_chunk();
+    int ntotal = nindex + nvalue;
+    #pragma omp parallel for schedule(dynamic, 1) num_threads(nthread_)
+    for (int i = 0; i < ntotal; ++i) {
+      if (i < nindex) {
+        index_.Decompress(i);
+      } else {
+        value_.Decompress(i - nindex);
+      }
+    }
+  }
+
+ private:
+  // default chunk size.
+  static const size_t kChunkSize = 64 << 10UL;
+  // maximum chunk size.
+  static const size_t kMaxChunk = 64;
+  // number of threads
+  int nthread_;
+  // raw bytes
+  size_t raw_bytes_;
+  // encoded bytes
+  size_t encoded_bytes_;
+  /*! \brief external memory column offset */
+  std::vector<size_t> disk_offset_;
+  // internal index
+  CompressArray<bst_uint> index_;
+  // value set.
+  CompressArray<bst_float> value_;
+};
+
+XGBOOST_REGISTER_SPARSE_PAGE_FORMAT(lz4)
+.describe("Apply LZ4 binary data compression for ext memory.")
+.set_body([]() {
+    return new SparsePageLZ4Format();
+  });
+}  // namespace data
+}  // namespace xgboost
diff --git a/src/data/data.cc b/src/data/data.cc
index 30da58e8e..d3c530c32 100644
--- a/src/data/data.cc
+++ b/src/data/data.cc
@@ -255,5 +255,8 @@ std::string SparsePage::Format::DecideFormat(const std::string& cache_prefix) {
     return "raw";
   }
 }
+
+// List of files that will be force linked in static links.
+DMLC_REGISTRY_LINK_TAG(sparse_page_raw_format);
 }  // namespace data
 }  // namespace xgboost
diff --git a/src/data/sparse_batch_page.h b/src/data/sparse_batch_page.h
index 78534bfd6..680b255c2 100644
--- a/src/data/sparse_batch_page.h
+++ b/src/data/sparse_batch_page.h
@@ -155,7 +155,7 @@ class SparsePage::Format {
    * \brief save the data to fo, when a page was written.
    * \param fo output stream
    */
-  virtual void Write(const SparsePage& page, dmlc::Stream* fo) const = 0;
+  virtual void Write(const SparsePage& page, dmlc::Stream* fo) = 0;
   /*!
    * \brief Create sparse page of format.
    * \return The created format functors.
diff --git a/src/data/sparse_page_dmatrix.h b/src/data/sparse_page_dmatrix.h
index 9d0a2e344..e4aebee9c 100644
--- a/src/data/sparse_page_dmatrix.h
+++ b/src/data/sparse_page_dmatrix.h
@@ -71,7 +71,7 @@ class SparsePageDMatrix : public DMatrix {
   /*! \brief page size 256 MB */
   static const size_t kPageSize = 256UL << 20UL;
   /*! \brief Maximum number of rows per batch. */
-  static const size_t kMaxRowPerBatch = 32UL << 10UL;
+  static const size_t kMaxRowPerBatch = 64UL << 10UL;
 
  private:
   // declare the column batch iter.
diff --git a/src/data/sparse_page_raw_format.cc b/src/data/sparse_page_raw_format.cc
index 867ffad1c..d0019fde6 100644
--- a/src/data/sparse_page_raw_format.cc
+++ b/src/data/sparse_page_raw_format.cc
@@ -4,11 +4,14 @@
  *  Raw binary format of sparse page.
  */
 #include <xgboost/data.h>
+#include <dmlc/registry.h>
 #include "./sparse_batch_page.h"
 
 namespace xgboost {
 namespace data {
 
+DMLC_REGISTRY_FILE_TAG(sparse_page_raw_format);
+
 class SparsePageRawFormat : public SparsePage::Format {
  public:
   bool Read(SparsePage* page, dmlc::SeekStream* fi) override {
@@ -73,7 +76,7 @@ class SparsePageRawFormat : public SparsePage::Format {
     return true;
   }
 
-  void Write(const SparsePage& page, dmlc::Stream* fo) const override {
+  void Write(const SparsePage& page, dmlc::Stream* fo) override {
     CHECK(page.offset.size() != 0 && page.offset[0] == 0);
     CHECK_EQ(page.offset.back(), page.data.size());
     fo->Write(page.offset);
diff --git a/src/objective/regression_obj.cc b/src/objective/regression_obj.cc
index bf2a08e1a..6eb0f0a78 100644
--- a/src/objective/regression_obj.cc
+++ b/src/objective/regression_obj.cc
@@ -108,10 +108,10 @@ class RegLossObj : public ObjFunction {
       LOG(FATAL) << Loss::LabelErrorMsg();
     }
   }
-  virtual const char* DefaultEvalMetric() const {
+  const char* DefaultEvalMetric() const override {
     return Loss::DefaultEvalMetric();
   }
-  virtual void PredTransform(std::vector<float> *io_preds) {
+  void PredTransform(std::vector<float> *io_preds) override {
     std::vector<float> &preds = *io_preds;
     const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size());
     #pragma omp parallel for schedule(static)
@@ -119,7 +119,7 @@ class RegLossObj : public ObjFunction {
       preds[j] = Loss::PredTransform(preds[j]);
     }
   }
-  virtual float ProbToMargin(float base_score) const {
+  float ProbToMargin(float base_score) const override {
     return Loss::ProbToMargin(base_score);
   }