Merge remote-tracking branch 'upstream/master' into colsplit-gpu-pred…

…ictor

R-package/tests/testthat/test_basic.R

@@ -85,9 +85,18 @@ test_that("dart prediction works", {
     rnorm(100)
 
   set.seed(1994)
-  booster_by_xgboost <- xgboost(data = d, label = y, max_depth = 2, booster = "dart",
-                                rate_drop = 0.5, one_drop = TRUE,
-                                eta = 1, nthread = 2, nrounds = nrounds, objective = "reg:squarederror")
+  booster_by_xgboost <- xgboost(
+    data = d,
+    label = y,
+    max_depth = 2,
+    booster = "dart",
+    rate_drop = 0.5,
+    one_drop = TRUE,
+    eta = 1,
+    nthread = 2,
+    nrounds = nrounds,
+    objective = "reg:squarederror"
+  )
   pred_by_xgboost_0 <- predict(booster_by_xgboost, newdata = d, ntreelimit = 0)
   pred_by_xgboost_1 <- predict(booster_by_xgboost, newdata = d, ntreelimit = nrounds)
   expect_true(all(matrix(pred_by_xgboost_0, byrow = TRUE) == matrix(pred_by_xgboost_1, byrow = TRUE)))
@@ -97,19 +106,19 @@ test_that("dart prediction works", {
 
   set.seed(1994)
   dtrain <- xgb.DMatrix(data = d, info = list(label = y))
-  booster_by_train <- xgb.train(params = list(
-                                    booster = "dart",
-                                    max_depth = 2,
-                                    eta = 1,
-                                    rate_drop = 0.5,
-                                    one_drop = TRUE,
-                                    nthread = 1,
-                                    tree_method = "exact",
-                                    objective = "reg:squarederror"
-                                ),
-                                data = dtrain,
-                                nrounds = nrounds
-                                )
+  booster_by_train <- xgb.train(
+    params = list(
+      booster = "dart",
+      max_depth = 2,
+      eta = 1,
+      rate_drop = 0.5,
+      one_drop = TRUE,
+      nthread = 1,
+      objective = "reg:squarederror"
+    ),
+    data = dtrain,
+    nrounds = nrounds
+  )
   pred_by_train_0 <- predict(booster_by_train, newdata = dtrain, ntreelimit = 0)
   pred_by_train_1 <- predict(booster_by_train, newdata = dtrain, ntreelimit = nrounds)
   pred_by_train_2 <- predict(booster_by_train, newdata = dtrain, training = TRUE)
@@ -399,7 +408,7 @@ test_that("colsample_bytree works", {
   xgb.importance(model = bst)
   # If colsample_bytree works properly, a variety of features should be used
   # in the 100 trees
-  expect_gte(nrow(xgb.importance(model = bst)), 30)
+  expect_gte(nrow(xgb.importance(model = bst)), 28)
 })
 
 test_that("Configuration works", {

R-package/tests/testthat/test_update.R

@@ -13,7 +13,10 @@ test_that("updating the model works", {
   watchlist <- list(train = dtrain, test = dtest)
 
   # no-subsampling
-  p1 <- list(objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2)
+  p1 <- list(
+    objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = 2,
+    updater = "grow_colmaker,prune"
+  )
   set.seed(11)
   bst1 <- xgb.train(p1, dtrain, nrounds = 10, watchlist, verbose = 0)
   tr1 <- xgb.model.dt.tree(model = bst1)

doc/c.rst

@@ -33,6 +33,8 @@ DMatrix
 .. doxygengroup:: DMatrix
    :project: xgboost
 
+.. _c_streaming:
+
 Streaming
 ---------
 

doc/tutorials/dask.rst

@@ -54,6 +54,9 @@ on a dask cluster:
         y = da.random.random(size=(num_obs, 1), chunks=(1000, 1))
 
         dtrain = xgb.dask.DaskDMatrix(client, X, y)
+        # or
+        # dtrain = xgb.dask.DaskQuantileDMatrix(client, X, y)
+        # `DaskQuantileDMatrix` is available for the `hist` and `gpu_hist` tree method.
 
         output = xgb.dask.train(
             client,

doc/tutorials/external_memory.rst

@@ -22,6 +22,15 @@ GPU-based training algorithm. We will introduce them in the following sections.
 
    The feature is still experimental as of 2.0. The performance is not well optimized.
 
+The external memory support has gone through multiple iterations and is still under heavy
+development. Like the :py:class:`~xgboost.QuantileDMatrix` with
+:py:class:`~xgboost.DataIter`, XGBoost loads data batch-by-batch using a custom iterator
+supplied by the user. However, unlike the :py:class:`~xgboost.QuantileDMatrix`, external
+memory will not concatenate the batches unless GPU is used (it uses a hybrid approach,
+more details follow). Instead, it will cache all batches on the external memory and fetch
+them on-demand.  Go to the end of the document to see a comparison between
+`QuantileDMatrix` and external memory.
+
 *************
 Data Iterator
 *************
@@ -113,10 +122,11 @@ External memory is supported by GPU algorithms (i.e. when ``tree_method`` is set
 ``gpu_hist``). However, the algorithm used for GPU is different from the one used for
 CPU. When training on a CPU, the tree method iterates through all batches from external
 memory for each step of the tree construction algorithm. On the other hand, the GPU
-algorithm concatenates all batches into one and stores it in GPU memory. To reduce overall
-memory usage, users can utilize subsampling. The good news is that the GPU hist tree
-method supports gradient-based sampling, enabling users to set a low sampling rate without
-compromising accuracy.
+algorithm uses a hybrid approach. It iterates through the data during the beginning of
+each iteration and concatenates all batches into one in GPU memory. To reduce overall
+memory usage, users can utilize subsampling. The GPU hist tree method supports
+`gradient-based sampling`, enabling users to set a low sampling rate without compromising
+accuracy.
 
 .. code-block:: python
 
@@ -134,6 +144,8 @@ see `this paper <https://arxiv.org/abs/2005.09148>`_.
    When GPU is running out of memory during iteration on external memory, user might
    recieve a segfault instead of an OOM exception.
 
+.. _ext_remarks:
+
 *******
 Remarks
 *******
@@ -142,17 +154,64 @@ When using external memory with XBGoost, data is divided into smaller chunks so
 a fraction of it needs to be stored in memory at any given time. It's important to note
 that this method only applies to the predictor data (``X``), while other data, like labels
 and internal runtime structures are concatenated. This means that memory reduction is most
-effective when dealing with wide datasets where ``X`` is larger compared to other data
-like ``y``, while it has little impact on slim datasets.
+effective when dealing with wide datasets where ``X`` is significantly larger in size
+compared to other data like ``y``, while it has little impact on slim datasets.
+
+As one might expect, fetching data on-demand puts significant pressure on the storage
+device. Today's computing device can process way more data than a storage can read in a
+single unit of time. The ratio is at order of magnitudes. An GPU is capable of processing
+hundred of Gigabytes of floating-point data in a split second. On the other hand, a
+four-lane NVMe storage connected to a PCIe-4 slot usually has about 6GB/s of data transfer
+rate. As a result, the training is likely to be severely bounded by your storage
+device. Before adopting the external memory solution, some back-of-envelop calculations
+might help you see whether it's viable. For instance, if your NVMe drive can transfer 4GB
+(a fairly practical number) of data per second and you have a 100GB of data in compressed
+XGBoost cache (which corresponds to a dense float32 numpy array with the size of 200GB,
+give or take). A tree with depth 8 needs at least 16 iterations through the data when the
+parameter is right. You need about 14 minutes to train a single tree without accounting
+for some other overheads and assume the computation overlaps with the IO. If your dataset
+happens to have TB-level size, then you might need thousands of trees to get a generalized
+model. These calculations can help you get an estimate on the expected training time.
+
+However, sometimes we can ameliorate this limitation. One should also consider that the OS
+(mostly talking about the Linux kernel) can usually cache the data on host memory. It only
+evicts pages when new data comes in and there's no room left. In practice, at least some
+portion of the data can persist on the host memory throughout the entire training
+session. We are aware of this cache when optimizing the external memory fetcher. The
+compressed cache is usually smaller than the raw input data, especially when the input is
+dense without any missing value. If the host memory can fit a significant portion of this
+compressed cache, then the performance should be decent after initialization. Our
+development so far focus on two fronts of optimization for external memory:
+
+- Avoid iterating through the data whenever appropriate.
+- If the OS can cache the data, the performance should be close to in-core training.
 
 Starting with XGBoost 2.0, the implementation of external memory uses ``mmap``. It is not
-yet tested against system errors like disconnected network devices (`SIGBUS`). Also, it's
-worth noting that most tests have been conducted on Linux distributions.
+tested against system errors like disconnected network devices (`SIGBUS`). In the face of
+a bus error, you will see a hard crash and need to clean up the cache files. If the
+training session might take a long time and you are using solutions like NVMe-oF, we
+recommend checkpointing your model periodically. Also, it's worth noting that most tests
+have been conducted on Linux distributions.
 
-Another important point to keep in mind is that creating the initial cache for XGBoost may
-take some time. The interface to external memory is through custom iterators, which may or
-may not be thread-safe. Therefore, initialization is performed sequentially.
 
+Another important point to keep in mind is that creating the initial cache for XGBoost may
+take some time. The interface to external memory is through custom iterators, which we can
+not assume to be thread-safe. Therefore, initialization is performed sequentially. Using
+the `xgboost.config_context` with `verbosity=2` can give you some information on what
+XGBoost is doing during the wait if you don't mind the extra output.
+
+*******************************
+Compared to the QuantileDMatrix
+*******************************
+
+Passing an iterator to the :py:class:`~xgboost.QuantileDmatrix` enables direct
+construction of `QuantileDmatrix` with data chunks. On the other hand, if it's passed to
+:py:class:`~xgboost.DMatrix`, it instead enables the external memory feature. The
+:py:class:`~xgboost.QuantileDmatrix` concatenates the data on memory after compression and
+doesn't fetch data during training. On the other hand, the external memory `DMatrix`
+fetches data batches from external memory on-demand.  Use the `QuantileDMatrix` (with
+iterator if necessary) when you can fit most of your data in memory. The training would be
+an order of magnitute faster than using external memory.
 
 ****************
 Text File Inputs

doc/tutorials/index.rst

@@ -11,22 +11,22 @@ See `Awesome XGBoost <https://github.com/dmlc/xgboost/tree/master/demo>`_ for mo
 
   model
   saving_model
+  learning_to_rank
+  dart
+  monotonic
+  feature_interaction_constraint
+  aft_survival_analysis
+  categorical
+  multioutput
+  rf
   kubernetes
   Distributed XGBoost with XGBoost4J-Spark <https://xgboost.readthedocs.io/en/latest/jvm/xgboost4j_spark_tutorial.html>
   Distributed XGBoost with XGBoost4J-Spark-GPU <https://xgboost.readthedocs.io/en/latest/jvm/xgboost4j_spark_gpu_tutorial.html>
   dask
   spark_estimator
   ray
-  dart
-  monotonic
-  rf
-  feature_interaction_constraint
-  learning_to_rank
-  aft_survival_analysis
+  external_memory
   c_api_tutorial
   input_format
   param_tuning
-  external_memory
   custom_metric_obj
-  categorical
-  multioutput

doc/tutorials/learning_to_rank.rst

@@ -48,8 +48,9 @@ Notice that the samples are sorted based on their query index in a non-decreasin
   import xgboost as xgb
 
   # Make a synthetic ranking dataset for demonstration
-  X, y = make_classification(random_state=rng)
-  rng = np.random.default_rng(1994)
+  seed = 1994 
+  X, y = make_classification(random_state=seed)
+  rng = np.random.default_rng(seed)
   n_query_groups = 3
   qid = rng.integers(0, 3, size=X.shape[0])
 

doc/tutorials/param_tuning.rst

@@ -58,3 +58,46 @@ This can affect the training of XGBoost model, and there are two ways to improve
 
   - In such a case, you cannot re-balance the dataset
   - Set parameter ``max_delta_step`` to a finite number (say 1) to help convergence
+
+
+*********************
+Reducing Memory Usage
+*********************
+
+If you are using a HPO library like :py:class:`sklearn.model_selection.GridSearchCV`,
+please control the number of threads it can use. It's best to let XGBoost to run in
+parallel instead of asking `GridSearchCV` to run multiple experiments at the same
+time. For instance, creating a fold of data for cross validation can consume a significant
+amount of memory:
+
+.. code-block:: python
+
+    # This creates a copy of dataset. X and X_train are both in memory at the same time.
+
+    # This happens for every thread at the same time if you run `GridSearchCV` with
+    # `n_jobs` larger than 1
+
+    X_train, X_test, y_train, y_test = train_test_split(X, y)
+
+.. code-block:: python
+
+    df = pd.DataFrame()
+    # This creates a new copy of the dataframe, even if you specify the inplace parameter
+    new_df = df.drop(...)
+
+.. code-block:: python
+
+    array = np.array(...)
+    # This may or may not make a copy of the data, depending on the type of the data
+    array.astype(np.float32)
+
+.. code-block::
+
+    # np by default uses double, do you actually need it?
+    array = np.array(...)
+
+You can find some more specific memory reduction practices scattered through the documents
+For instances: :doc:`/tutorials/dask`, :doc:`/gpu/index`,
+:doc:`/contrib/scaling`. However, before going into these, being conscious about making
+data copies is a good starting point. It usually consumes a lot more memory than people
+expect.

rabit/include/rabit/internal/io.h

@@ -19,8 +19,7 @@
 #include "rabit/internal/utils.h"
 #include "rabit/serializable.h"
 
-namespace rabit {
-namespace utils {
+namespace rabit::utils {
 /*! \brief re-use definition of dmlc::SeekStream */
 using SeekStream = dmlc::SeekStream;
 /**
@@ -31,9 +30,6 @@ struct MemoryFixSizeBuffer : public SeekStream {
   // similar to SEEK_END in libc
   static std::size_t constexpr kSeekEnd = std::numeric_limits<std::size_t>::max();
 
- protected:
-  MemoryFixSizeBuffer() = default;
-
  public:
   /**
    * @brief Ctor
@@ -68,7 +64,7 @@ struct MemoryFixSizeBuffer : public SeekStream {
    * @brief Current position in the buffer (stream).
    */
   std::size_t Tell() override { return curr_ptr_; }
-  virtual bool AtEnd() const { return curr_ptr_ == buffer_size_; }
+  [[nodiscard]] virtual bool AtEnd() const { return curr_ptr_ == buffer_size_; }
 
  protected:
   /*! \brief in memory buffer */
@@ -119,6 +115,5 @@ struct MemoryBufferStream : public SeekStream {
   /*! \brief current pointer */
   size_t curr_ptr_;
 };  // class MemoryBufferStream
-}  // namespace utils
-}  // namespace rabit
+}  // namespace rabit::utils
 #endif  // RABIT_INTERNAL_IO_H_