Add retry mechanism and dynamic model loading to SONIC framework

HeterogeneousCore/SonicCore/BuildFile.xml

@@ -2,6 +2,7 @@
 <use name="FWCore/Concurrency"/>
 <use name="FWCore/MessageLogger"/>
 <use name="FWCore/ParameterSet"/>
+<use name="FWCore/PluginManager"/>
 <use name="FWCore/Utilities"/>
 <export>
   <lib name="1"/>

HeterogeneousCore/SonicCore/interface/RetryActionBase.h

@@ -0,0 +1,36 @@
+#ifndef HeterogeneousCore_SonicCore_RetryActionBase
+#define HeterogeneousCore_SonicCore_RetryActionBase
+
+#include "FWCore/PluginManager/interface/PluginFactory.h"
+#include "FWCore/ParameterSet/interface/ParameterSet.h"
+#include "HeterogeneousCore/SonicCore/interface/SonicClientBase.h"
+#include <memory>
+#include <string>
+
+// Base class for retry actions
+class RetryActionBase {
+public:
+  RetryActionBase(const edm::ParameterSet& conf, SonicClientBase* client);
+  virtual ~RetryActionBase() = default;
+
+  bool shouldRetry() const { return shouldRetry_; }  // Getter for shouldRetry_
+
+  virtual void retry() = 0;  // Pure virtual function for execution logic
+  virtual void start() = 0;  // Pure virtual function for execution logic for initialization
+
+protected:
+  void eval();                // interface for calling evaluate in client
+  void finish(bool success);  // interface for calling finish directly in client
+
+protected:
+  SonicClientBase* client_;
+  bool shouldRetry_;  // Flag to track if further retries should happen
+};
+
+// Define the factory for creating retry actions
+using RetryActionFactory =
+    edmplugin::PluginFactory<RetryActionBase*(const edm::ParameterSet&, SonicClientBase* client)>;
+
+#endif
+
+#define DEFINE_RETRY_ACTION(type) DEFINE_EDM_PLUGIN(RetryActionFactory, type, #type);

HeterogeneousCore/SonicCore/interface/SonicClientBase.h

@@ -9,12 +9,15 @@
 #include "HeterogeneousCore/SonicCore/interface/SonicDispatcherPseudoAsync.h"
 
 #include <string>
+#include <vector>
 #include <exception>
 #include <memory>
 #include <optional>
 
 enum class SonicMode { Sync = 1, Async = 2, PseudoAsync = 3 };
 
+class RetryActionBase;
+
 class SonicClientBase {
 public:
   //constructor
@@ -54,14 +57,23 @@ class SonicClientBase {
   SonicMode mode_;
   bool verbose_;
   std::unique_ptr<SonicDispatcher> dispatcher_;
-  unsigned allowedTries_, tries_;
+  unsigned totalTries_;
   std::optional<edm::WaitingTaskWithArenaHolder> holder_;
 
+  // Use a unique_ptr with a custom deleter to avoid incomplete type issues
+  struct RetryDeleter {
+    void operator()(RetryActionBase* ptr) const;
+  };
+
+  using RetryActionPtr = std::unique_ptr<RetryActionBase, RetryDeleter>;
+  std::vector<RetryActionPtr> retryActions_;
+
   //for logging/debugging
   std::string debugName_, clientName_, fullDebugName_;
 
   friend class SonicDispatcher;
   friend class SonicDispatcherPseudoAsync;
+  friend class RetryActionBase;
 };
 
 #endif

HeterogeneousCore/SonicCore/plugins/BuildFile.xml

@@ -0,0 +1,6 @@
+<use name="FWCore/Framework"/>
+<use name="FWCore/PluginManager"/>
+<use name="FWCore/ParameterSet"/>
+<use name="HeterogeneousCore/SonicCore"/>
+<plugin file="*.cc" name="pluginHeterogeneousCoreSonicCore"/>
+

HeterogeneousCore/SonicCore/plugins/RetrySameServerAction.cc

@@ -0,0 +1,28 @@
+#include "HeterogeneousCore/SonicCore/interface/RetryActionBase.h"
+#include "HeterogeneousCore/SonicCore/interface/SonicClientBase.h"
+
+class RetrySameServerAction : public RetryActionBase {
+public:
+  RetrySameServerAction(const edm::ParameterSet& pset, SonicClientBase* client)
+      : RetryActionBase(pset, client), allowedTries_(pset.getUntrackedParameter<unsigned>("allowedTries", 0)) {}
+
+  void start() override { tries_ = 0; };
+
+protected:
+  void retry() override;
+
+private:
+  unsigned allowedTries_, tries_;
+};
+
+void RetrySameServerAction::retry() {
+  ++tries_;
+  //if max retries has not been exceeded, call evaluate again
+  if (tries_ >= allowedTries_) {
+    shouldRetry_ = false;  // Flip flag when max retries are reached
+    edm::LogInfo("RetrySameServerAction") << "Max retry attempts reached. No further retries.";
+  }
+  eval();
+}
+
+DEFINE_RETRY_ACTION(RetrySameServerAction)

HeterogeneousCore/SonicCore/src/RetryActionBase.cc

@@ -0,0 +1,15 @@
+#include "HeterogeneousCore/SonicCore/interface/RetryActionBase.h"
+
+// Constructor implementation
+RetryActionBase::RetryActionBase(const edm::ParameterSet& conf, SonicClientBase* client)
+    : client_(client), shouldRetry_(true) {
+  if (client_ == nullptr) {
+    throw cms::Exception("RetryActionBase") << "client pointer cannot be null";
+  }
+}
+
+void RetryActionBase::eval() { client_->evaluate(); }
+
+void RetryActionBase::finish(bool success) { client_->finish(success); }
+
+EDM_REGISTER_PLUGINFACTORY(RetryActionFactory, "RetryActionFactory");

HeterogeneousCore/SonicCore/src/SonicClientBase.cc

@@ -1,18 +1,34 @@
 #include "HeterogeneousCore/SonicCore/interface/SonicClientBase.h"
+#include "HeterogeneousCore/SonicCore/interface/RetryActionBase.h"
 #include "FWCore/Utilities/interface/Exception.h"
 #include "FWCore/ParameterSet/interface/allowedValues.h"
 
+// Custom deleter implementation
+void SonicClientBase::RetryDeleter::operator()(RetryActionBase* ptr) const { delete ptr; }
+
 SonicClientBase::SonicClientBase(const edm::ParameterSet& params,
                                  const std::string& debugName,
                                  const std::string& clientName)
-    : allowedTries_(params.getUntrackedParameter<unsigned>("allowedTries", 0)),
-      debugName_(debugName),
-      clientName_(clientName),
-      fullDebugName_(debugName_) {
+    : debugName_(debugName), clientName_(clientName), fullDebugName_(debugName_) {
   if (!clientName_.empty())
     fullDebugName_ += ":" + clientName_;
 
+  const auto& retryPSetList = params.getParameter<std::vector<edm::ParameterSet>>("Retry");
   std::string modeName(params.getParameter<std::string>("mode"));
+
+  for (const auto& retryPSet : retryPSetList) {
+    const std::string& actionType = retryPSet.getParameter<std::string>("retryType");
+
+    auto retryAction = RetryActionFactory::get()->create(actionType, retryPSet, this);
+    if (retryAction) {
+      //Convert to  RetryActionPtr Type from raw pointer of retryAction
+      retryActions_.emplace_back(RetryActionPtr(retryAction.release()));
+    } else {
+      throw cms::Exception("Configuration")
+          << "Unknown Retry type " << actionType << " for SonicClient: " << fullDebugName_;
+    }
+  }
+
   if (modeName == "Sync")
     setMode(SonicMode::Sync);
   else if (modeName == "Async")
@@ -40,24 +56,34 @@ void SonicClientBase::start(edm::WaitingTaskWithArenaHolder holder) {
   holder_ = std::move(holder);
 }
 
-void SonicClientBase::start() { tries_ = 0; }
+void SonicClientBase::start() {
+  totalTries_ = 0;
+  // initialize all actions
+  for (auto& action : retryActions_) {
+    action->start();
+  }
+}
 
 void SonicClientBase::finish(bool success, std::exception_ptr eptr) {
   //retries are only allowed if no exception was raised
   if (!success and !eptr) {
-    ++tries_;
-    //if max retries has not been exceeded, call evaluate again
-    if (tries_ < allowedTries_) {
-      evaluate();
-      //avoid calling doneWaiting() twice
-      return;
-    }
-    //prepare an exception if exceeded
-    else {
-      edm::Exception ex(edm::errors::ExternalFailure);
-      ex << "SonicCallFailed: call failed after max " << tries_ << " tries";
-      eptr = make_exception_ptr(ex);
+    ++totalTries_;
+    edm::LogInfo("SonicClientBase") << "finish: failed after total tries of " << totalTries_;
+    for (const auto& action : retryActions_) {
+      if (action->shouldRetry()) {
+        edm::LogInfo("SonicClientBase") << "Calling retry()";
+        // retry() must trigger eval() or finish()
+        action->retry();
+        // return because another finish() was already called inside client->evaluate()
+        return;
+      }
     }
+    //prepare an exception if no more retry actions left
+    edm::LogInfo("SonicClientBase") << "SonicCallFailed: call failed, no retry actions available after " << totalTries_
+                                    << " tries.";
+    edm::Exception ex(edm::errors::ExternalFailure);
+    ex << "SonicCallFailed: call failed, no retry actions available after " << totalTries_ << " tries.";
+    eptr = make_exception_ptr(ex);
   }
   if (holder_) {
     holder_->doneWaiting(eptr);
@@ -74,7 +100,20 @@ void SonicClientBase::fillBasePSetDescription(edm::ParameterSetDescription& desc
   //restrict allowed values
   desc.ifValue(edm::ParameterDescription<std::string>("mode", "PseudoAsync", true),
                edm::allowedValues<std::string>("Sync", "Async", "PseudoAsync"));
-  if (allowRetry)
-    desc.addUntracked<unsigned>("allowedTries", 0);
+  if (allowRetry) {
+    // Defines the structure of each entry in the VPSet
+    edm::ParameterSetDescription retryDesc;
+    retryDesc.add<std::string>("retryType", "RetrySameServerAction");
+    retryDesc.addUntracked<unsigned>("allowedTries", 0);
+
+    // Define a default retry action
+    edm::ParameterSet defaultRetry;
+    defaultRetry.addParameter<std::string>("retryType", "RetrySameServerAction");
+    defaultRetry.addUntrackedParameter<unsigned>("allowedTries", 0);
+
+    // Add the VPSet with the default retry action
+    desc.addVPSet("Retry", retryDesc, {defaultRetry});
+  }
+  desc.add("sonicClientBase", desc);
   desc.addUntracked<bool>("verbose", false);
 }

HeterogeneousCore/SonicCore/test/DummyClient.h

@@ -36,7 +36,7 @@ class DummyClient : public SonicClient<int> {
     this->output_ = this->input_ * factor_;
 
     //simulate a failure
-    if (this->tries_ < fails_)
+    if (this->totalTries_ < fails_)
       this->finish(false);
     else
       this->finish(true);

HeterogeneousCore/SonicCore/test/sonicTestAna_cfg.py

@@ -16,16 +16,27 @@
         mode = cms.string("Sync"),
         factor = cms.int32(-1),
         wait = cms.int32(10),
-        allowedTries = cms.untracked.uint32(0),
         fails = cms.uint32(0),
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(0),
+          )
+        )
     ),
 )
 
 process.dummySyncAnaRetry = process.dummySyncAna.clone(
     Client = dict(
         wait = 2,
-        allowedTries = 2,
         fails = 1,
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(2),
+          )
+        )
+
     )
 )
 

HeterogeneousCore/SonicCore/test/sonicTest_cfg.py

@@ -17,15 +17,19 @@
 
 process.options.numberOfThreads = 2
 process.options.numberOfStreams = 0
-
 process.dummySync = _moduleClass(_moduleName,
     input = cms.int32(1),
     Client = cms.PSet(
         mode = cms.string("Sync"),
         factor = cms.int32(-1),
         wait = cms.int32(10),
-        allowedTries = cms.untracked.uint32(0),
         fails = cms.uint32(0),
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(0)
+          )
+        )
     ),
 )
 
@@ -35,8 +39,14 @@
         mode = cms.string("PseudoAsync"),
         factor = cms.int32(2),
         wait = cms.int32(10),
-        allowedTries = cms.untracked.uint32(0),
         fails = cms.uint32(0),
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(0)
+          )
+        )
+
     ),
 )
 
@@ -46,32 +56,53 @@
         mode = cms.string("Async"),
         factor = cms.int32(5),
         wait = cms.int32(10),
-        allowedTries = cms.untracked.uint32(0),
         fails = cms.uint32(0),
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(0)
+          )
+        )
     ),
 )
 
 process.dummySyncRetry = process.dummySync.clone(
     Client = dict(
         wait = 2,
-        allowedTries = 2,
         fails = 1,
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(2)
+          )
+        )
+
     )
 )
 
 process.dummyPseudoAsyncRetry = process.dummyPseudoAsync.clone(
     Client = dict(
         wait = 2,
-        allowedTries = 2,
         fails = 1,
+        Retry = cms.VPSet(
+          cms.PSet(
+            retryType = cms.string('RetrySameServerAction'),
+            allowedTries = cms.untracked.uint32(2)
+          )
+        )
     )
 )
 
 process.dummyAsyncRetry = process.dummyAsync.clone(
     Client = dict(
         wait = 2,
-        allowedTries = 2,
         fails = 1,
+        Retry = cms.VPSet(
+          cms.PSet(
+            allowedTries = cms.untracked.uint32(2),
+            retryType = cms.string('RetrySameServerAction')
+          )
+        )
     )
 )
 

HeterogeneousCore/SonicTriton/BuildFile.xml

@@ -10,6 +10,7 @@
 <iftool name="cuda">
   <use name="cuda"/>
 </iftool>
+
 <export>
-  <lib   name="1"/>
+  <lib name="1"/>
 </export>