Release query vector memory after execution (#2346) (#2349)

Signed-off-by: Vijayan Balasubramanian <[email protected]> (cherry picked from commit 646d8b7) Co-authored-by: Vijayan Balasubramanian <[email protected]>
opensearch-project · Dec 21, 2024 · b01edd5 · b01edd5
1 parent 8bb3c39
commit b01edd5
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -25,6 +25,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Bug Fixes
 * Fixing the bug when a segment has no vector field present for disk based vector search (#2282)[https://github.com/opensearch-project/k-NN/pull/2282]
 * Allow validation for non knn index only after 2.17.0 (#2315)[https://github.com/opensearch-project/k-NN/pull/2315]
+* Release query vector memory after execution (#2346)[https://github.com/opensearch-project/k-NN/pull/2346]
 ### Infrastructure
 * Updated C++ version in JNI from c++11 to c++17 [#2259](https://github.com/opensearch-project/k-NN/pull/2259)
 * Upgrade bytebuddy and objenesis version to match OpenSearch core and, update github ci runner for macos [#2279](https://github.com/opensearch-project/k-NN/pull/2279)

diff --git a/jni/src/faiss_wrapper.cpp b/jni/src/faiss_wrapper.cpp
@@ -1180,6 +1180,7 @@ jobjectArray knn_jni::faiss_wrapper::RangeSearchWithFilter(knn_jni::JNIUtilInter
             jniUtil->ReleaseLongArrayElements(env, filterIdsJ, filteredIdsArray, JNI_ABORT);
             throw;
         }
+        jniUtil->ReleaseLongArrayElements(env, filterIdsJ, filteredIdsArray, JNI_ABORT);
     } else {
         faiss::SearchParameters *searchParameters = nullptr;
         faiss::SearchParametersHNSW hnswParams;
@@ -1202,6 +1203,7 @@ jobjectArray knn_jni::faiss_wrapper::RangeSearchWithFilter(knn_jni::JNIUtilInter
             throw;
         }
     }
+    jniUtil->ReleaseFloatArrayElements(env, queryVectorJ, rawQueryVector, JNI_ABORT);
 
     // lims is structured to support batched queries, it has a length of nq + 1 (where nq is the number of queries),
     // lims[i] - lims[i-1] gives the number of results for the i-th query. With a single query we used in k-NN,