[LLDB][Telemetry]Define DebuggerTelemetryInfo and related methods

- This type of entry is used to collect data about the debugger startup/exit
- Tests will be added (They may need to be shell test with a "test-only" TelemetryManager plugin defined. I'm trying to figure out how to get that linked only when tests are running and not to the LLDB binary all the time.

Author: oontvoo

lldb/include/lldb/Core/Telemetry.h

@@ -13,6 +13,7 @@
 #include "lldb/Interpreter/CommandReturnObject.h"
 #include "lldb/Utility/StructuredData.h"
 #include "lldb/lldb-forward.h"
+#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/JSON.h"
@@ -29,6 +30,9 @@ namespace telemetry {
 
 struct LLDBEntryKind : public ::llvm::telemetry::EntryKind {
   static const llvm::telemetry::KindType BaseInfo = 0b11000;
+  static const llvm::telemetry::KindType DebuggerInfo = 0b11001;
+  // There are other entries in between (added in separate PRs)
+  static const llvm::telemetry::KindType MiscInfo = 0b11110;
 };
 
 /// Defines a convenient type for timestamp of various events.
@@ -56,13 +60,83 @@ struct LLDBBaseTelemetryInfo : public llvm::telemetry::TelemetryInfo {
   void serialize(llvm::telemetry::Serializer &serializer) const override;
 };
 
+/// Describes the exit status of a debugger.
+struct ExitDescription {
+  int exit_code;
+  std::string description;
+};
+
+struct DebuggerTelemetryInfo : public LLDBBaseTelemetryInfo {
+  std::string username;
+  std::string lldb_git_sha;
+  std::string lldb_path;
+  std::string cwd;
+  std::optional<ExitDescription> exit_desc;
+
+  DebuggerTelemetryInfo() = default;
+
+  // Provide a copy ctor because we may need to make a copy before
+  // sanitizing the data.
+  // (The sanitization might differ between different Destination classes).
+  DebuggerTelemetryInfo(const DebuggerTelemetryInfo &other) {
+    username = other.username;
+    lldb_git_sha = other.lldb_git_sha;
+    lldb_path = other.lldb_path;
+    cwd = other.cwd;
+  };
+
+  llvm::telemetry::KindType getKind() const override {
+    return LLDBEntryKind::DebuggerInfo;
+  }
+
+  static bool classof(const llvm::telemetry::TelemetryInfo *T) {
+    return T->getKind() == LLDBEntryKind::DebuggerInfo;
+  }
+
+  void serialize(llvm::telemetry::Serializer &serializer) const override;
+};
+
+/// The "catch-all" entry to store a set of non-standard data, such as
+/// error-messages, etc.
+struct MiscTelemetryInfo : public LLDBBaseTelemetryInfo {
+  /// If the event is/can be associated with a target entry,
+  /// this field contains that target's UUID.
+  /// <EMPTY> otherwise.
+  std::string target_uuid;
+
+  /// Set of key-value pairs for any optional (or impl-specific) data
+  std::map<std::string, std::string> meta_data;
+
+  MiscTelemetryInfo() = default;
+
+  MiscTelemetryInfo(const MiscTelemetryInfo &other) {
+    target_uuid = other.target_uuid;
+    meta_data = other.meta_data;
+  }
+
+  llvm::telemetry::KindType getKind() const override {
+    return LLDBEntryKind::MiscInfo;
+  }
+
+  static bool classof(const llvm::telemetry::TelemetryInfo *T) {
+    return T->getKind() == LLDBEntryKind::MiscInfo;
+  }
+
+  void serialize(llvm::telemetry::Serializer &serializer) const override;
+};
+
 /// The base Telemetry manager instance in LLDB.
 /// This class declares additional instrumentation points
 /// applicable to LLDB.
 class TelemetryManager : public llvm::telemetry::Manager {
 public:
   llvm::Error preDispatch(llvm::telemetry::TelemetryInfo *entry) override;
 
+  const llvm::telemetry::Config *getConfig();
+
+  void atDebuggerStartup(DebuggerTelemetryInfo *entry);
+  void atDebuggerExit(DebuggerTelemetryInfo *entry);
+
   virtual llvm::StringRef GetInstanceName() const = 0;
   static TelemetryManager *getInstance();
 
@@ -73,6 +147,10 @@ class TelemetryManager : public llvm::telemetry::Manager {
 
 private:
   std::unique_ptr<llvm::telemetry::Config> m_config;
+  // Each debugger is assigned a unique ID (session_id).
+  // All TelemetryInfo entries emitted for the same debugger instance
+  // will get the same session_id.
+  llvm::DenseMap<Debugger *, std::string> session_ids;
   static std::unique_ptr<TelemetryManager> g_instance;
 };
 

lldb/source/Core/Debugger.cpp

@@ -62,13 +62,19 @@
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/iterator.h"
+#include "llvm/Config/llvm-config.h"
 #include "llvm/Support/DynamicLibrary.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Process.h"
 #include "llvm/Support/ThreadPool.h"
 #include "llvm/Support/Threading.h"
 #include "llvm/Support/raw_ostream.h"
 
+#ifdef LLVM_BUILD_TELEMETRY
+#include "lldb/Core/Telemetry.h"
+#include <chrono>
+#endif
+
 #include <cstdio>
 #include <cstdlib>
 #include <cstring>
@@ -761,12 +767,29 @@ void Debugger::InstanceInitialize() {
 
 DebuggerSP Debugger::CreateInstance(lldb::LogOutputCallback log_callback,
                                     void *baton) {
+#ifdef LLVM_BUILD_TELEMETRY
+  lldb_private::telemetry::SteadyTimePoint start_time =
+      std::chrono::steady_clock::now();
+#endif
   DebuggerSP debugger_sp(new Debugger(log_callback, baton));
   if (g_debugger_list_ptr && g_debugger_list_mutex_ptr) {
     std::lock_guard<std::recursive_mutex> guard(*g_debugger_list_mutex_ptr);
     g_debugger_list_ptr->push_back(debugger_sp);
   }
   debugger_sp->InstanceInitialize();
+
+#ifdef LLVM_BUILD_TELEMETRY
+  if (auto *telemetry_manager = telemetry::TelemetryManager::getInstance()) {
+    if (telemetry_manager->getConfig()->EnableTelemetry) {
+      lldb_private::telemetry::DebuggerTelemetryInfo entry;
+      entry.start_time = start_time;
+      entry.end_time = std::chrono::steady_clock::now();
+      entry.debugger = debugger_sp.get();
+      telemetry_manager->atDebuggerStartup(&entry);
+    }
+  }
+#endif
+
   return debugger_sp;
 }
 
@@ -985,6 +1008,10 @@ void Debugger::Clear() {
   //     static void Debugger::Destroy(lldb::DebuggerSP &debugger_sp);
   //     static void Debugger::Terminate();
   llvm::call_once(m_clear_once, [this]() {
+#ifdef LLVM_BUILD_TELEMETRY
+    lldb_private::telemetry::SteadyTimePoint quit_start_time =
+        std::chrono::steady_clock::now();
+#endif
     ClearIOHandlers();
     StopIOHandlerThread();
     StopEventHandlerThread();
@@ -1007,6 +1034,19 @@ void Debugger::Clear() {
 
     if (Diagnostics::Enabled())
       Diagnostics::Instance().RemoveCallback(m_diagnostics_callback_id);
+
+#ifdef LLVM_BUILD_TELEMETRY
+    if (auto telemetry_manager = telemetry::TelemetryManager::getInstance()) {
+      if (telemetry_manager->getConfig()->EnableTelemetry) {
+        // TBD: We *may* have to send off the log BEFORE the ClearIOHanders()?
+        lldb_private::telemetry::DebuggerTelemetryInfo entry;
+        entry.start_time = quit_start_time;
+        entry.end_time = std::chrono::steady_clock::now();
+        entry.debugger = this;
+        telemetry_manager->atDebuggerExit(&entry);
+      }
+    }
+#endif
   });
 }
 

lldb/source/Core/Telemetry.cpp

@@ -10,14 +10,20 @@
 
 #ifdef LLVM_BUILD_TELEMETRY
 
-#include "lldb/Core/Telemetry.h"
 #include "lldb/Core/Debugger.h"
+#include "lldb/Core/Telemetry.h"
+#include "lldb/Host/FileSystem.h"
+#include "lldb/Host/HostInfo.h"
+#include "lldb/Target/Process.h"
+#include "lldb/Target/Statistics.h"
 #include "lldb/Utility/LLDBLog.h"
 #include "lldb/Utility/UUID.h"
+#include "lldb/Version/Version.h"
 #include "lldb/lldb-enumerations.h"
 #include "lldb/lldb-forward.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/Error.h"
+#include "llvm/Support/Path.h"
 #include "llvm/Support/RandomNumberGenerator.h"
 #include "llvm/Telemetry/Telemetry.h"
 #include <chrono>
@@ -35,15 +41,7 @@ static uint64_t ToNanosec(const SteadyTimePoint Point) {
   return std::chrono::nanoseconds(Point.time_since_epoch()).count();
 }
 
-void LLDBBaseTelemetryInfo::serialize(Serializer &serializer) const {
-  serializer.write("entry_kind", getKind());
-  serializer.write("session_id", SessionId);
-  serializer.write("start_time", ToNanosec(start_time));
-  if (end_time.has_value())
-    serializer.write("end_time", ToNanosec(end_time.value()));
-}
-
-[[maybe_unused]] static std::string MakeUUID(Debugger *debugger) {
+static std::string MakeUUID(Debugger *debugger) {
   uint8_t random_bytes[16];
   if (auto ec = llvm::getRandomBytes(random_bytes, 16)) {
     LLDB_LOG(GetLog(LLDBLog::Object),
@@ -56,16 +54,107 @@ void LLDBBaseTelemetryInfo::serialize(Serializer &serializer) const {
   return UUID(random_bytes).GetAsString();
 }
 
+void LLDBBaseTelemetryInfo::serialize(Serializer &serializer) const {
+  serializer.write("entry_kind", getKind());
+  serializer.write("session_id", SessionId);
+  serializer.write("start_time", ToNanosec(start_time));
+  if (end_time.has_value())
+    serializer.write("end_time", ToNanosec(end_time.value()));
+}
+
+void DebuggerTelemetryInfo::serialize(Serializer &serializer) const {
+  LLDBBaseTelemetryInfo::serialize(serializer);
+
+  serializer.write("username", username);
+  serializer.write("lldb_git_sha", lldb_git_sha);
+  serializer.write("lldb_path", lldb_path);
+  serializer.write("cwd", cwd);
+  if (exit_desc.has_value()) {
+    serializer.write("exit_code", exit_desc->exit_code);
+    serializer.write("exit_desc", exit_desc->description);
+  }
+}
+
+void MiscTelemetryInfo::serialize(Serializer &serializer) const {
+  LLDBBaseTelemetryInfo::serialize(serializer);
+  serializer.write("target_uuid", target_uuid);
+  serializer.beginObject("meta_data");
+  for (const auto &kv : meta_data)
+    serializer.write(kv.first, kv.second);
+  serializer.endObject();
+}
+
 TelemetryManager::TelemetryManager(std::unique_ptr<Config> config)
     : m_config(std::move(config)) {}
 
 llvm::Error TelemetryManager::preDispatch(TelemetryInfo *entry) {
-  // Do nothing for now.
-  // In up-coming patch, this would be where the manager
-  // attach the session_uuid to the entry.
+  LLDBBaseTelemetryInfo *lldb_entry =
+      llvm::dyn_cast<LLDBBaseTelemetryInfo>(entry);
+  std::string session_id = "";
+  if (Debugger *debugger = lldb_entry->debugger) {
+    auto session_id_pos = session_ids.find(debugger);
+    if (session_id_pos != session_ids.end())
+      session_id = session_id_pos->second;
+    else
+      session_id_pos->second = session_id = MakeUUID(debugger);
+  }
+  lldb_entry->SessionId = session_id;
+
   return llvm::Error::success();
 }
 
+const Config *getConfig() { return m_config.get(); }
+
+void TelemetryManager::atDebuggerStartup(DebuggerTelemetryInfo *entry) {
+  UserIDResolver &resolver = lldb_private::HostInfo::GetUserIDResolver();
+  std::optional<llvm::StringRef> opt_username =
+      resolver.GetUserName(lldb_private::HostInfo::GetUserID());
+  if (opt_username)
+    entry->username = *opt_username;
+
+  entry->lldb_git_sha =
+      lldb_private::GetVersion(); // TODO: find the real git sha?
+
+  entry->lldb_path = HostInfo::GetProgramFileSpec().GetPath();
+
+  llvm::SmallString<64> cwd;
+  if (!llvm::sys::fs::current_path(cwd)) {
+    entry->cwd = cwd.c_str();
+  } else {
+    MiscTelemetryInfo misc_info;
+    misc_info.meta_data["internal_errors"] = "Cannot determine CWD";
+    if (auto er = dispatch(&misc_info)) {
+      LLDB_LOG(GetLog(LLDBLog::Object),
+               "Failed to dispatch misc-info at startup");
+    }
+  }
+
+  if (auto er = dispatch(entry)) {
+    LLDB_LOG(GetLog(LLDBLog::Object), "Failed to dispatch entry at startup");
+  }
+}
+
+void TelemetryManager::atDebuggerExit(DebuggerTelemetryInfo *entry) {
+  // There must be a reference to the debugger at this point.
+  assert(entry->debugger != nullptr);
+
+  if (auto *selected_target =
+          entry->debugger->GetSelectedExecutionContext().GetTargetPtr()) {
+    if (!selected_target->IsDummyTarget()) {
+      const lldb::ProcessSP proc = selected_target->GetProcessSP();
+      if (proc == nullptr) {
+        // no process has been launched yet.
+        entry->exit_desc = {-1, "no process launched."};
+      } else {
+        entry->exit_desc = {proc->GetExitStatus(), ""};
+        if (const char *description = proc->GetExitDescription())
+          entry->exit_desc->description = std::string(description);
+      }
+    }
+  }
+  dispatch(entry);
+}
+
 std::unique_ptr<TelemetryManager> TelemetryManager::g_instance = nullptr;
 TelemetryManager *TelemetryManager::getInstance() { return g_instance.get(); }