Files
Jungfraujoch/tests/CMakeLists.txt
T
leonarski_fandClaude Fable 5.1 060a89cd7d CUDA: allocation streams are handed back, not leaked; a handled pool failure leaves no error
A long-running broker began cancelling every data collection with

    Device decoding failed (CUDA (GPU) error (out of memory)), falling back to host decompression
    CUDA (GPU) error (out of memory)

while nvidia-smi showed the cards less than a fifth full. Two defects, both in CUDAMemHelpers.h and
both from the pooled allocator (cudaMallocAsync) that came with rc.162.

The leak. cuda_allocation_stream() kept one stream per (thread, device) in a thread_local map of raw
cudaStream_t and never destroyed them. That was written against rugnux, where the worker threads live
as long as the process. The broker starts fresh std::async threads for every data collection - 16 or
64 of them - so every collection left that many streams behind. Measured: 0.56 MB of device memory
per leaked stream, linear to 4928 streams, never returned, with nothing on the host side growing.

The RAII wrapper (CudaStream) was there but not used at this site, and using it as-is - a stream
destroyed when its thread exits - would not have been safe: ShadowFinder builds its GPU accumulator
on a throw-away std::async thread and frees it from another thread long after, and that free is
ordered on the allocating thread's stream. So the streams are still never destroyed, but a thread
now only borrows one: CudaStream objects live in a process-wide per-device idle list, a thread takes
one on first use and hands it back when it exits. Their number is bounded by the threads that were
ever alive at once instead of by the threads ever started. The list itself is deliberately leaked, so
that nothing calls into CUDA during static destruction.

Replaying the broker's pattern against the real header, 60 collections of 64 threads:
    before   3840 streams, 260 -> 2424 MB of device memory
    after      64 streams, 260 ->  358 MB

The stale error. Every helper here throws a named message, yet the log carried the raw CUDA string,
so the failure came through a cuda_err() and not from an allocation. CudaDevicePtr falls back to
cudaMalloc when cudaMallocAsync fails, silently - but the failed call stays behind as the thread's
last error, and the cudaGetLastError() that follows the next kernel launch reports it. The buffers
were all allocated; the frame was lost anyway, once on the device-decode route (caught, hence the
warning) and once more on the host fallback (fatal). The pooled attempt failing, and a stream that
cannot be created, are both handled by falling back, so both now clear the error they leave.

What finite resource the production cards ran out of at under 4 GB used was not established - no
cap on the number of streams was found up to 4928 on the card this was measured on. The leak is the
only thing on this path that grows with uptime.

tests/CUDAMemHelpersTest.cpp: later threads end up on the same stream, concurrent threads on
different ones, a buffer is freed cleanly after its allocating thread has exited (and another has
borrowed its stream), and a pool that cannot serve a request leaves no error behind - the last by
capping a memory pool at 4 MB so that the pooled attempt fails and the fallback succeeds.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-20 18:45:03 +02:00

129 lines
4.3 KiB
CMake

ADD_EXECUTABLE(jfjoch_test
DiffractionExperimentTest.cpp
RawToConvertedGeometryTest.cpp
../common/RawToConvertedGeometry.h
../common/DiffractionExperiment.h
CheckImageOutput.h
FPGAIntegrationTest.cpp
StrongPixelSetTest.cpp
AdaptiveThresholdTest.cpp
AdaptiveSpotFinderCPUTest.cpp
ZSTDCompressorTest.cpp
FrameTransformationTest.cpp
HDF5WritingTest.cpp PedestalCalcTest.cpp
ZMQImagePusherTest.cpp StreamWriterTest.cpp
CoordTest.cpp JFJochStateMachineTest.cpp
JFJochReceiverIntegrationTest.cpp
AcquisitionCountersTest.cpp
IndexingUnitTest.cpp
ThreadSafeFIFOSetTest.cpp
FPGANetworkTest.cpp
JFPedestalTest.cpp
JFCalibrationTest.cpp
AzimuthalIntegrationTest.cpp
StatusVectorTest.cpp
CBORTest.cpp
DetectorGeometryTest.cpp DetectorSetupTest.cpp DiffractionGeometryTest.cpp
FPGASpotFindingUnitTest.cpp
PreviewCounterTest.cpp
FPGAFrameGeneratorTest.cpp
FPGAHostWriterTest.cpp
DiffractionSpotTest.cpp
TIFFTest.cpp
JFJochReceiverProcessingTest.cpp
JPEGTest.cpp
HistogramTest.cpp
ROIMapTest.cpp
ROIIntegrationCPUTest.cpp
ROIIntegrationGPUTest.cpp
BraggIntegrationEngineGPUTest.cpp
BraggIntegrationEngineCompressedImageTest.cpp
BraggStencilTest.cpp
LossyFilterTest.cpp
ImageBufferTest.cpp
PixelMaskTest.cpp
RegressionTest.cpp
FPGAHLSModulesTest.cpp
ZMQPreviewSocketTest.cpp
DetectorSettingsTest.cpp
AutoIncrVectorTest.cpp
ModuleSummationTest.cpp
ZMQMetadataSocketTest.cpp
JFJochReaderTest.cpp
ShadowFinderTest.cpp
ParallelForTest.cpp
RugnuxTest.cpp
ResultReportTest.cpp
RugnuxLargeTest.cpp
TestData.h
MovingAverageTest.cpp
ImageMetadataTest.cpp
JFJochReceiverLiteTest.cpp
GridScanSettingsTest.cpp
JFJochReceiverPlotsTest.cpp
GoniometerAxisTest.cpp
DetGeomCalibTest.cpp
RingsFromProfileTest.cpp
CalibrationTest.cpp
XtalOptimizerTest.cpp
CrystalLatticeTest.cpp
FPGAPTPTest.cpp
ResolutionShellsTest.cpp
ImageSpotFinderCPUTest.cpp
ImageSpotFinderGPUTest.cpp
BSLZ4DecoderGPUTest.cpp
BSLZ4DecoderGPUFuzzTest.cpp
ImagePreprocessorGPUFusedTest.cpp
AdaptiveSpotFinderGPUTest.cpp
SpotExtractorGPUParityTest.cpp
CUDAMemHelpersTest.cpp
CalcBraggPredictionTest.cpp
SpotUtilsTest.cpp
LatticeSearchTest.cpp
LePageLatticeTest.cpp
TimeTest.cpp
RotationIndexerTest.cpp
SpindleBlindFractionTest.cpp
SpindleCuspLossTest.cpp
TopPixelsTest.cpp
HKLKeyTest.cpp
TCPImagePusherTest.cpp
PreflightTest.cpp
ModelValidationTest.cpp
SearchSpaceGroupTest.cpp
SearchSpaceGroupTwinTest.cpp
SyntheticMergedReflections.h
XDSPluginTest.cpp
MergeScaleTest.cpp
AnisotropyAnalysisTest.cpp
ModelScalingTest.cpp
TwinningAnalysisTest.cpp
TranslationalNCSTest.cpp
RfreeFlagsTest.cpp
FrenchWilsonTest.cpp
ReindexAmbiguityTest.cpp
LoadReferenceMtzFreeFlagsTest.cpp
WriteReflectionsTest.cpp
UnitCellTest.cpp
CCTest.cpp
MultiLatticeSearchTest.cpp
LatticeReductionTest.cpp
BeamCenterFromBackgroundTest.cpp
BeamCenterFFTTest.cpp
BeamCenterFFTGPUTest.cpp
BeamCenterFromSpotsTest.cpp
)
target_link_libraries(jfjoch_test Catch2WithMain JFJochBroker JFJochReceiver JFJochReader JFJochStreamWriter
Rugnux JFJochImageAnalysis JFJochCommon JFJochHLSSimulation JFJochPreview
jfjoch_xds_plugin)
target_include_directories(jfjoch_test PRIVATE .)
find_package(Threads REQUIRED)
add_library(enospc_shim MODULE enospc_shim.c)
target_link_libraries(enospc_shim PRIVATE Threads::Threads dl)
set_target_properties(enospc_shim PROPERTIES PREFIX "" POSITION_INDEPENDENT_CODE ON) # remove "lib"
ADD_EXECUTABLE(jfjoch_hdf5_enospc_test jfjoch_hdf5_enospc_test.cpp)
target_link_libraries(jfjoch_hdf5_enospc_test Catch2WithMain JFJochWriter)