Change default KvikIO parameters in cuDF: set the thread pool size to 4, and compatibility mode to ON

cpp/include/cudf/io/config_utils.hpp

@@ -37,10 +37,13 @@ bool is_gds_enabled();
 bool is_kvikio_enabled();
 
 /**
- * @brief Set kvikIO thread pool size according to the environment variable KVIKIO_NTHREADS. If
- * KVIKIO_NTHREADS is not set, use 8 threads by default.
+ * @brief Set KvikIO parameters, including:
+ * - Compatibility mode, according to the environment variable KVIKIO_COMPAT_MODE. If
+ *   KVIKIO_COMPAT_MODE is not set, enable it by default, which enforces the use of POSIX I/O.
+ * - Thread pool size, according to the environment variable KVIKIO_NTHREADS. If KVIKIO_NTHREADS is
+ *   not set, use 4 threads by default.
  */
-void set_thread_pool_nthreads_from_env();
+void set_up_kvikio();
 
 }  // namespace cufile_integration
 

cpp/src/io/utilities/config_utils.cpp

@@ -52,11 +52,14 @@ bool is_gds_enabled() { return is_always_enabled() or get_env_policy() == usage_
 
 bool is_kvikio_enabled() { return get_env_policy() == usage_policy::KVIKIO; }
 
-void set_thread_pool_nthreads_from_env()
+void set_up_kvikio()
 {
   static std::once_flag flag{};
   std::call_once(flag, [] {
-    auto nthreads = getenv_or<unsigned int>("KVIKIO_NTHREADS", 8U);
+    auto const compat_mode = kvikio::detail::getenv_or<bool>("KVIKIO_COMPAT_MODE", true);
+    kvikio::defaults::compat_mode_reset(compat_mode);
+
+    auto const nthreads = getenv_or<unsigned int>("KVIKIO_NTHREADS", 4u);
     kvikio::defaults::thread_pool_nthreads_reset(nthreads);
   });
 }

cpp/src/io/utilities/data_sink.cpp

@@ -42,7 +42,7 @@ class file_sink : public data_sink {
     if (!_output_stream.is_open()) { detail::throw_on_file_open_failure(filepath, true); }
 
     if (cufile_integration::is_kvikio_enabled()) {
-      cufile_integration::set_thread_pool_nthreads_from_env();
+      cufile_integration::set_up_kvikio();
       _kvikio_file = kvikio::FileHandle(filepath, "w");
       CUDF_LOG_INFO("Writing a file using kvikIO, with compatibility mode {}.",
                     _kvikio_file.is_compat_mode_on() ? "on" : "off");

cpp/src/io/utilities/datasource.cpp

@@ -48,7 +48,7 @@ class file_source : public datasource {
   {
     detail::force_init_cuda_context();
     if (cufile_integration::is_kvikio_enabled()) {
-      cufile_integration::set_thread_pool_nthreads_from_env();
+      cufile_integration::set_up_kvikio();
       _kvikio_file = kvikio::FileHandle(filepath);
       CUDF_LOG_INFO("Reading a file using kvikIO, with compatibility mode {}.",
                     _kvikio_file.is_compat_mode_on() ? "on" : "off");

docs/cudf/source/user_guide/io/io.md

@@ -91,15 +91,27 @@ SDK is available for download
 [here](https://developer.nvidia.com/gpudirect-storage). GDS is also
 included in CUDA Toolkit 11.4 and higher.
 
-Use of GPUDirect Storage in cuDF is enabled by default, but can be
-disabled through the environment variable `LIBCUDF_CUFILE_POLICY`.
+Use of GPUDirect Storage in cuDF is disabled by default, but can be
+enabled through the environment variable `LIBCUDF_CUFILE_POLICY`.
 This variable also controls the GDS compatibility mode.
 
 There are four valid values for the environment variable:
 
-- "GDS": Enable GDS use; GDS compatibility mode is *off*.
-- "ALWAYS": Enable GDS use; GDS compatibility mode is *on*.
-- "KVIKIO": Enable GDS through [KvikIO](https://github.com/rapidsai/kvikio).
+- "GDS": Enable GDS use. If the cuFile library cannot be properly loaded,
+fall back to the GDS compatibility mode.
+- "ALWAYS": Enable GDS use. If the cuFile library cannot be properly loaded,
+throw an exception.
+- "KVIKIO": Enable GDS compatibility mode through [KvikIO](https://github.com/rapidsai/kvikio).
+Note that KvikIO also provides the environment variable `KVIKIO_COMPAT_MODE` for GDS
+control that may alter the effect of "KVIKIO" option in cuDF:
+  - By default, `KVIKIO_COMPAT_MODE` is unset. In this case, cuDF enforces
+    the GDS compatibility mode, and the system configuration check for GDS I/O
+    is never performed.
+  - If `KVIKIO_COMPAT_MODE=ON`, this is the same with the above case.
+  - If `KVIKIO_COMPAT_MODE=OFF`, KvikIO enforces GDS I/O without system
+    configuration check, and will error out if GDS requirements are not met. The
+    only exceptional case is that if the system does not support files being
+    opened with the `O_DIRECT` flag, the GDS compatibility mode will be used.
 - "OFF": Completely disable GDS use.
 
 If no value is set, behavior will be the same as the "KVIKIO" option.