Name KvikIO thread-pool workers for profiling

cpp/include/kvikio/defaults.hpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -121,7 +121,7 @@ std::tuple<std::string_view, T, bool> getenv_or(
  */
 class defaults {
  private:
-  ThreadPool _thread_pool{get_num_threads_from_env()};
+  ThreadPool _thread_pool{get_num_threads_from_env(), make_thread_pool_init_task("kvikio")};
   CompatMode _compat_mode;
   std::size_t _task_size;
   std::size_t _gds_threshold;

cpp/include/kvikio/threadpool_wrapper.hpp

@@ -1,17 +1,58 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 
 #pragma once
 
+#include <array>
+#include <atomic>
+#include <cstdio>
+#include <functional>
+#include <memory>
+#include <string>
+
 #include <BS_thread_pool.hpp>
 
+#include <pthread.h>
+
 namespace kvikio {
 
 /**
  * @brief Thread pool type used for parallel I/O operations.
  */
 using ThreadPool = BS::thread_pool;
 
+/**
+ * @brief Build a `BS::thread_pool` init task that names each worker thread.
+ *
+ * The returned functor is intended to be passed to `BS::thread_pool`'s
+ * constructor or `reset()` overloads that accept an `init_task`. It runs
+ * once per worker as the pool starts each thread, setting the OS-level
+ * thread name (`comm` on Linux) to `"<prefix>-<index>"` so profilers such
+ * as nsys, `top -H`, and `/proc/<pid>/task/<tid>/comm` show meaningful
+ * names instead of the parent process name.
+ *
+ * The per-thread index is assigned via an atomic counter captured by the
+ * returned functor, so different pools can share the same prefix without
+ * colliding.
+ *
+ * Linux caps thread names at 15 characters plus NUL, so keep @p prefix
+ * short (typically 10 characters or fewer).
+ *
+ * @param prefix Name prefix, e.g. `"kvikio"` or `"kvikio-dev"`.
+ * @return An init task suitable for `BS::thread_pool`.
+ */
+[[nodiscard]] inline std::function<void()> make_thread_pool_init_task(std::string prefix)
+{
+  auto counter = std::make_shared<std::atomic<unsigned int>>(0);
+  return [counter = std::move(counter), prefix = std::move(prefix)]() {
+    unsigned int const idx = counter->fetch_add(1, std::memory_order_relaxed);
+    // Linux comm limit is 15 chars + NUL.
+    std::array<char, 16> name{};
+    std::snprintf(name.data(), name.size(), "%s-%u", prefix.c_str(), idx);
+    pthread_setname_np(pthread_self(), name.data());
+  };
+}
+
 }  // namespace kvikio

cpp/src/defaults.cpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -18,6 +18,7 @@
 #include <kvikio/http_status_codes.hpp>
 #include <kvikio/remote_handle.hpp>
 #include <kvikio/shim/cufile.hpp>
+#include <kvikio/threadpool_wrapper.hpp>
 #include <string_view>
 
 namespace kvikio {
@@ -220,7 +221,7 @@ void defaults::set_thread_pool_nthreads(unsigned int nthreads)
 {
   KVIKIO_EXPECT(
     nthreads > 0, "number of threads must be a positive integer", std::invalid_argument);
-  thread_pool().reset(nthreads);
+  thread_pool().reset(nthreads, make_thread_pool_init_task("kvikio"));
 }
 
 unsigned int defaults::num_threads() { return thread_pool_nthreads(); }

cpp/src/file_handle.cpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -80,7 +80,8 @@ ThreadPool* get_thread_pool_per_block_device(std::string const& file_path)
     }
 
     // First file on this block device: create a new dedicated thread pool
-    auto thread_pool = std::make_shared<ThreadPool>(defaults::num_threads());
+    auto thread_pool = std::make_shared<ThreadPool>(defaults::num_threads(),
+                                                    make_thread_pool_init_task("kvikio-dev"));
     dev_id_to_thread_pool_map.emplace(block_dev_info.id, thread_pool);
     file_path_to_thread_pool_map.emplace(file_path, thread_pool);
     return thread_pool.get();