Fix CPU accounting for external generator subprocesses

GeneratorFileOrCmd forks an external generator but the child was only
reaped from ~GeneratorHepMC(), which is not reached on the DPL device
teardown path. Its CPU therefore never showed up in RUSAGE_CHILDREN.

Generators: add Generator::stop(), called from GeneratorTask::run() once
the stream ends, to reap the child deterministically.

Framework: add a Monitoring .stop callback to take the final CPU
measurement on the RUNNING -> READY transition. This also covers devices
that end their own stream via readyToQuit(), for which postEOS is never
invoked.

Fixes https://its.cern.ch/jira/browse/O2-7096

Assisted by Claude Opus 5

Author: sawenzel

Framework/Core/src/CommonServices.cxx

@@ -127,6 +127,12 @@ o2::framework::ServiceSpec CommonServices::monitoringSpec()
         monitoring->setRunNumber(std::stoul(extRunNumber));
       } catch (...) {
       } },
+    // Final measurement here rather than in ~Monitoring() at .exit, which is
+    // not reliably reached before the process exits. Unlike postEOS this also
+    // covers devices that quit themselves via readyToQuit().
+    .stop = [](ServiceRegistryRef, void* service) {
+                       auto* monitoring = reinterpret_cast<Monitoring*>(service);
+                       monitoring->finalizeProcessMonitoring(); },
     .exit = [](ServiceRegistryRef registry, void* service) {
                        auto* monitoring = reinterpret_cast<Monitoring*>(service);
                        monitoring->flushBuffer();

Generators/include/Generators/Generator.h

@@ -105,6 +105,10 @@ class Generator : public FairGenerator
   /** notification methods **/
   virtual void notifyEmbedding(const o2::dataformats::MCEventHeader* eventHeader){};
 
+  /** Release external resources (forked subprocesses, open files, ...) once
+   * the generator is no longer needed, without relying on destructor timing **/
+  virtual void stop() {}
+
   void setTriggerOkHook(std::function<void(std::vector<TParticle> const& p, int eventCount)> f) { mTriggerOkHook = f; }
   void setTriggerFalseHook(std::function<void(std::vector<TParticle> const& p, int eventCount)> f) { mTriggerFalseHook = f; }
 

Generators/include/Generators/GeneratorHepMC.h

@@ -86,6 +86,9 @@ class GeneratorHepMC : public Generator, public GeneratorFileOrCmd
    */
   Bool_t importParticles() override;
 
+  /** Terminate the background command (if any), see Generator::stop(). */
+  void stop() override;
+
   /** setters **/
   void setEventsToSkip(uint64_t val) { mEventsToSkip = val; };
   void setVersion(const int& ver) { mVersion = ver; };

Generators/include/Generators/GeneratorService.h

@@ -70,6 +70,9 @@ class GeneratorService
   void generateEvent_MCTracks(o2::pmr::vector<MCTrack>& tracks, o2::dataformats::MCEventHeader& header);
   void generateEvent_TParticles(std::vector<TParticle>& tparts, o2::dataformats::MCEventHeader& header);
 
+  /** Calls Generator::stop() on all registered generators **/
+  void stopGenerators();
+
  private:
   PrimaryGenerator mPrimGen;
   o2::data::Stack mStack;

Generators/src/GeneratorHepMC.cxx

@@ -66,13 +66,20 @@ GeneratorHepMC::~GeneratorHepMC()
   if (mEvent) {
     delete mEvent;
   }
+  stop();
+  removeTemp();
+}
+
+/*****************************************************************/
+
+void GeneratorHepMC::stop()
+{
   if (not mCmd.empty()) {
     // Must be executed before removing the temporary file
     // otherwise the current child process might still be writing on it
     // causing unwanted stdout messages which could slow down the system
     terminateCmd();
   }
-  removeTemp();
 }
 
 /*****************************************************************/

Generators/src/GeneratorService.cxx

@@ -14,6 +14,8 @@
 #include "SimConfig/SimConfig.h"
 #include "Generators/Generator.h"
 #include "DataFormatsCalibration/MeanVertexObject.h"
+#include <TCollection.h>
+#include <TObjArray.h>
 
 using namespace o2::eventgen;
 
@@ -90,3 +92,17 @@ void GeneratorService::generateEvent_TParticles(std::vector<TParticle>& tracks,
   tracks.clear();
   tracks = mStack.getPrimaries();
 }
+
+void GeneratorService::stopGenerators()
+{
+  auto* generators = mPrimGen.GetListOfGenerators();
+  if (!generators) {
+    return;
+  }
+  TIter next(generators);
+  while (TObject* obj = next()) {
+    if (auto* gen = dynamic_cast<o2::eventgen::Generator*>(obj)) {
+      gen->stop();
+    }
+  }
+}

run/dpl_eventgen.cxx

@@ -132,6 +132,9 @@ struct GeneratorTask {
       }
     }
     if (eventCounter >= nEvents || time_expired) {
+      // terminate and reap external generator subprocesses here: device
+      // teardown is not guaranteed to run the generators' destructors
+      genservice->stopGenerators();
       pc.services().get<ControlService>().endOfStream();
       pc.services().get<ControlService>().readyToQuit(QuitRequest::Me);