TIKA-4863 - omp thread limit (#3105)

Author: tballison

CHANGES.txt

@@ -1,5 +1,11 @@
 Release 4.1.0 - unreleased
 
+   * The tika-server full and tika-grpc Docker images set OMP_THREAD_LIMIT=1:
+     the distro tesseract links OpenMP and runs up to 4 threads per OCR
+     process, which oversubscribes the CPU under forked parse workers;
+     single-threaded tesseract with process-level parallelism is the
+     tesseract project's guidance for servers (TIKA-XXXX).
+
    * embedded-limits maxDepth counts embedding levels again instead of the
      parsers a parse passes through; with AutoDetectParser over DefaultParser
      every value above 1 used to stop one level early (TIKA-4857).

tika-grpc/docker-build/Dockerfile

@@ -56,6 +56,8 @@ USER $UID_GID
 
 EXPOSE 9090
 ENV TIKA_VERSION=$VERSION
+# tesseract links libgomp; one thread per OCR process - parallelism comes from the forked parse workers
+ENV OMP_THREAD_LIMIT=1
 ENV TIKA_GRPC_MAX_INBOUND_MESSAGE_SIZE=$TIKA_GRPC_MAX_INBOUND_MESSAGE_SIZE
 ENV TIKA_GRPC_MAX_OUTBOUND_MESSAGE_SIZE=$TIKA_GRPC_MAX_OUTBOUND_MESSAGE_SIZE
 ENV TIKA_GRPC_NUM_THREADS=$TIKA_GRPC_NUM_THREADS

tika-server/docker-build/full/Dockerfile

@@ -73,6 +73,8 @@ RUN set -eux \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 ARG TIKA_VERSION
 ENV TIKA_VERSION=$TIKA_VERSION
+# tesseract links libgomp; one thread per OCR process - parallelism comes from the forked parse workers
+ENV OMP_THREAD_LIMIT=1
 
 COPY --from=fetch_tika /opt/tika-server /opt/tika-server
 # WORKDIR sets the CWD so tika-server's plugin-root fallback resolves

tika-server/docker-build/full/Dockerfile.snapshot

@@ -44,6 +44,8 @@ RUN set -eux \
     && apt-get clean -y \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 ENV TIKA_VERSION=$TIKA_VERSION
+# tesseract links libgomp; one thread per OCR process - parallelism comes from the forked parse workers
+ENV OMP_THREAD_LIMIT=1
 # Snapshot workflow tars the bin distribution into <context>/tika-server/, so
 # this COPY lands the thin jar + lib/ + plugins/ at /opt/tika-server/, matching
 # the release-variant Dockerfile.