Merge bitcoin/bitcoin#31000: bench: add support for custom data directory

fa66e0887c bench: add support for custom data directory (furszy)
ad9c2cceda test, bench: specialize working directory name (furszy)

Pull request description:

  Expands the benchmark framework with the existing `-testdatadir` arg,
  enabling the ability to change the benchmark data directory.

  This is useful for running benchmarks on different storage devices, and
  not just under the OS `/tmp/` directory.

  A good use case is #28574, where we are benchmarking the wallet
  migration process on an HDD.

ACKs for top commit:
  maflcko:
    re-ACK fa66e0887c
  achow101:
    ACK fa66e0887c
  tdb3:
    re ACK fa66e0887c
  hodlinator:
    re-ACK fa66e0887c
  pablomartin4btc:
    re-ACK fa66e0887c

Tree-SHA512: 4e87206c07e26fe193c07074ae9eb0cc9c70a58aeea8cf27d18fb5425d77e4b00dbe0e6d6a75c17b427744e9066458b9a84e5ef7b0420f02a4fccb9c5ef4dacc

src/bench/bench.cpp

@@ -27,9 +27,26 @@ using util::Join;
 
 const std::function<void(const std::string&)> G_TEST_LOG_FUN{};
 
-const std::function<std::vector<const char*>()> G_TEST_COMMAND_LINE_ARGUMENTS{};
+/**
+ * Retrieves the available test setup command line arguments that may be used
+ * in the benchmark. They will be used only if the benchmark utilizes a
+ * 'BasicTestingSetup' or any child of it.
+ */
+static std::function<std::vector<const char*>()> g_bench_command_line_args{};
+const std::function<std::vector<const char*>()> G_TEST_COMMAND_LINE_ARGUMENTS = []() {
+    return g_bench_command_line_args();
+};
 
-const std::function<std::string()> G_TEST_GET_FULL_NAME{};
+/**
+ * Retrieve the name of the currently in-use benchmark.
+ * This is applicable only to benchmarks that utilize the unit test
+ * framework context setup (e.g. ones using 'MakeNoLogFileContext<TestingSetup>()').
+ * It places the datadir of each benchmark run within their respective benchmark name.
+ */
+static std::string g_running_benchmark_name;
+const std::function<std::string()> G_TEST_GET_FULL_NAME = []() {
+    return g_running_benchmark_name;
+};
 
 namespace {
 
@@ -94,6 +111,14 @@ void BenchRunner::RunAll(const Args& args)
         std::cout << "Running with -sanity-check option, output is being suppressed as benchmark results will be useless." << std::endl;
     }
 
+    // Load inner test setup args
+    g_bench_command_line_args = [&args]() {
+        std::vector<const char*> ret;
+        ret.reserve(args.setup_args.size());
+        for (const auto& arg : args.setup_args) ret.emplace_back(arg.c_str());
+        return ret;
+    };
+
     std::vector<ankerl::nanobench::Result> benchmarkResults;
     for (const auto& [name, bench_func] : benchmarks()) {
         const auto& [func, priority_level] = bench_func;
@@ -117,6 +142,7 @@ void BenchRunner::RunAll(const Args& args)
             bench.output(nullptr);
         }
         bench.name(name);
+        g_running_benchmark_name = name;
         if (args.min_time > 0ms) {
             // convert to nanos before dividing to reduce rounding errors
             std::chrono::nanoseconds min_time_ns = args.min_time;

src/bench/bench.h

@@ -61,6 +61,7 @@ struct Args {
     fs::path output_json;
     std::string regex_filter;
     uint8_t priority;
+    std::vector<std::string> setup_args;
 };
 
 class BenchRunner

src/bench/bench_bitcoin.cpp

@@ -8,6 +8,7 @@
 #include <tinyformat.h>
 #include <util/fs.h>
 #include <util/string.h>
+#include <test/util/setup_common.h>
 
 #include <chrono>
 #include <cstdint>
@@ -27,6 +28,7 @@ static const std::string DEFAULT_PRIORITY{"all"};
 static void SetupBenchArgs(ArgsManager& argsman)
 {
     SetupHelpOptions(argsman);
+    SetupCommonTestArgs(argsman);
 
     argsman.AddArg("-asymptote=<n1,n2,n3,...>", "Test asymptotic growth of the runtime of an algorithm, if supported by the benchmark", ArgsManager::ALLOW_ANY, OptionsCategory::OPTIONS);
     argsman.AddArg("-filter=<regex>", strprintf("Regular expression filter to select benchmark by name (default: %s)", DEFAULT_BENCH_FILTER), ArgsManager::ALLOW_ANY, OptionsCategory::OPTIONS);
@@ -60,6 +62,18 @@ static uint8_t parsePriorityLevel(const std::string& str) {
     return levels;
 }
 
+static std::vector<std::string> parseTestSetupArgs(const ArgsManager& argsman)
+{
+    // Parses unit test framework arguments supported by the benchmark framework.
+    std::vector<std::string> args;
+    static std::vector<std::string> AVAILABLE_ARGS = {"-testdatadir"};
+    for (const std::string& arg_name : AVAILABLE_ARGS) {
+        auto op_arg = argsman.GetArg(arg_name);
+        if (op_arg) args.emplace_back(strprintf("%s=%s", arg_name, *op_arg));
+    }
+    return args;
+}
+
 int main(int argc, char** argv)
 {
     ArgsManager argsman;
@@ -131,6 +145,7 @@ int main(int argc, char** argv)
         args.regex_filter = argsman.GetArg("-filter", DEFAULT_BENCH_FILTER);
         args.sanity_check = argsman.GetBoolArg("-sanity-check", false);
         args.priority = parsePriorityLevel(argsman.GetArg("-priority-level", DEFAULT_PRIORITY));
+        args.setup_args = parseTestSetupArgs(argsman);
 
         benchmark::BenchRunner::RunAll(args);
 

src/test/util/setup_common.cpp

@@ -75,8 +75,6 @@ using node::VerifyLoadedChainstate;
 const std::function<std::string(const char*)> G_TRANSLATION_FUN = nullptr;
 
 constexpr inline auto TEST_DIR_PATH_ELEMENT{"test_common bitcoin"}; // Includes a space to catch possible path escape issues.
-/** Random context to get unique temp data dirs. Separate from m_rng, which can be seeded from a const env var */
-static FastRandomContext g_rng_temp_path;
 
 struct NetworkSetup
 {
@@ -87,8 +85,7 @@ struct NetworkSetup
 };
 static NetworkSetup g_networksetup_instance;
 
-/** Register test-only arguments */
+void SetupCommonTestArgs(ArgsManager& argsman)
-static void SetupUnitTestArgs(ArgsManager& argsman)
 {
     argsman.AddArg("-testdatadir", strprintf("Custom data directory (default: %s<random_string>)", fs::PathToString(fs::temp_directory_path() / TEST_DIR_PATH_ELEMENT / "")),
                    ArgsManager::ALLOW_ANY, OptionsCategory::DEBUG_TEST);
@@ -127,7 +124,7 @@ BasicTestingSetup::BasicTestingSetup(const ChainType chainType, TestOpts opts)
     gArgs.ClearPathCache();
     {
         SetupServerArgs(*m_node.args);
-        SetupUnitTestArgs(*m_node.args);
+        SetupCommonTestArgs(*m_node.args);
         std::string error;
         if (!m_node.args->ParseParameters(arguments.size(), arguments.data(), error)) {
             m_node.args->ClearArgs();
@@ -139,10 +136,10 @@ BasicTestingSetup::BasicTestingSetup(const ChainType chainType, TestOpts opts)
     // data directories use a random name that doesn't overlap with other tests.
     SeedRandomForTest(SeedRand::FIXED_SEED);
 
+    const std::string test_name{G_TEST_GET_FULL_NAME ? G_TEST_GET_FULL_NAME() : ""};
     if (!m_node.args->IsArgSet("-testdatadir")) {
-        // By default, the data directory has a random name
+        const auto now{TicksSinceEpoch<std::chrono::nanoseconds>(SystemClock::now())};
-        const auto rand_str{g_rng_temp_path.rand256().ToString()};
+        m_path_root = fs::temp_directory_path() / TEST_DIR_PATH_ELEMENT / test_name / util::ToString(now);
-        m_path_root = fs::temp_directory_path() / TEST_DIR_PATH_ELEMENT / rand_str;
         TryCreateDirectories(m_path_root);
     } else {
         // Custom data directory
@@ -151,8 +148,7 @@ BasicTestingSetup::BasicTestingSetup(const ChainType chainType, TestOpts opts)
         if (root_dir.empty()) ExitFailure("-testdatadir argument is empty, please specify a path");
 
         root_dir = fs::absolute(root_dir);
-        const std::string test_path{G_TEST_GET_FULL_NAME ? G_TEST_GET_FULL_NAME() : ""};
+        m_path_lock = root_dir / TEST_DIR_PATH_ELEMENT / fs::PathFromString(test_name);
-        m_path_lock = root_dir / TEST_DIR_PATH_ELEMENT / fs::PathFromString(test_path);
         m_path_root = m_path_lock / "datadir";
 
         // Try to obtain the lock; if unsuccessful don't disturb the existing test.

src/test/util/setup_common.h

@@ -45,6 +45,9 @@ extern const std::function<std::string()> G_TEST_GET_FULL_NAME;
 
 static constexpr CAmount CENT{1000000};
 
+/** Register common test args. Shared across binaries that rely on the test framework. */
+void SetupCommonTestArgs(ArgsManager& argsman);
+
 struct TestOpts {
     std::vector<const char*> extra_args{};
     bool coins_db_in_memory{true};