From d36a4c832775a2a437fe8dc11bf4a15faea4c8ba Mon Sep 17 00:00:00 2001
From: Matthew Kotila <matthew.r.kotila@gmail.com>
Date: Thu, 28 Sep 2023 00:47:06 +0000
Subject: [PATCH] Throw exception when request period larger than max tokens
 rather than infinite loop

---
 src/c++/perf_analyzer/periodic_concurrency_worker.cc | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/c++/perf_analyzer/periodic_concurrency_worker.cc b/src/c++/perf_analyzer/periodic_concurrency_worker.cc
index 9fbaee3cc..001ef009d 100644
--- a/src/c++/perf_analyzer/periodic_concurrency_worker.cc
+++ b/src/c++/perf_analyzer/periodic_concurrency_worker.cc
@@ -55,6 +55,14 @@ PeriodicConcurrencyWorker::WorkerCallback(uint32_t infer_context_id)
     period_completed_callback_();
   }
   if (ctxs_.at(infer_context_id)->HasReceivedFinalResponse()) {
+    bool has_not_completed_period{
+        ctxs_.at(infer_context_id)->GetNumResponsesForCurrentRequest() <
+        request_period_};
+    if (has_not_completed_period) {
+      throw std::runtime_error(
+          "Request received final response before request period was reached. "
+          "Request period parameter must be less than or equal to max tokens.");
+    }
     request_completed_callback_();
   }
 }