Index: compiler-rt/trunk/include/xray/xray_records.h =================================================================== --- compiler-rt/trunk/include/xray/xray_records.h +++ compiler-rt/trunk/include/xray/xray_records.h @@ -24,6 +24,14 @@ FDR_LOG = 1, }; +// FDR mode use of the union field in the XRayFileHeader. +struct alignas(16) FdrAdditionalHeaderData { + uint64_t ThreadBufferSize; +}; + +static_assert(sizeof(FdrAdditionalHeaderData) == 16, + "FdrAdditionalHeaderData != 16 bytes"); + // This data structure is used to describe the contents of the file. We use this // for versioning the supported XRay file formats. struct alignas(32) XRayFileHeader { @@ -42,10 +50,15 @@ // The frequency by which TSC increases per-second. alignas(8) uint64_t CycleFrequency = 0; - // The current civiltime timestamp, as retrived from 'clock_gettime'. This - // allows readers of the file to determine when the file was created or - // written down. - struct timespec TS; + union { + char FreeForm[16]; + // The current civiltime timestamp, as retrived from 'clock_gettime'. This + // allows readers of the file to determine when the file was created or + // written down. + struct timespec TS; + + struct FdrAdditionalHeaderData FdrData; + }; } __attribute__((packed)); static_assert(sizeof(XRayFileHeader) == 32, "XRayFileHeader != 32 bytes"); Index: compiler-rt/trunk/lib/xray/xray_buffer_queue.h =================================================================== --- compiler-rt/trunk/lib/xray/xray_buffer_queue.h +++ compiler-rt/trunk/lib/xray/xray_buffer_queue.h @@ -98,6 +98,9 @@ __sanitizer::memory_order_acquire); } + /// Returns the configured size of the buffers in the buffer queue. + size_t ConfiguredBufferSize() const { return BufferSize; } + /// Sets the state of the BufferQueue to finalizing, which ensures that: /// /// - All subsequent attempts to retrieve a Buffer will fail. Index: compiler-rt/trunk/lib/xray/xray_fdr_logging.cc =================================================================== --- compiler-rt/trunk/lib/xray/xray_fdr_logging.cc +++ compiler-rt/trunk/lib/xray/xray_fdr_logging.cc @@ -125,12 +125,16 @@ // before setting the values in the header. Header.ConstantTSC = 1; Header.NonstopTSC = 1; - clock_gettime(CLOCK_REALTIME, &Header.TS); + Header.FdrData = FdrAdditionalHeaderData{LocalBQ->ConfiguredBufferSize()}; retryingWriteAll(Fd, reinterpret_cast(&Header), reinterpret_cast(&Header) + sizeof(Header)); + LocalBQ->apply([&](const BufferQueue::Buffer &B) { - retryingWriteAll(Fd, reinterpret_cast(B.Buffer), - reinterpret_cast(B.Buffer) + B.Size); + uint64_t BufferSize = B.Size; + if (BufferSize > 0) { + retryingWriteAll(Fd, reinterpret_cast(B.Buffer), + reinterpret_cast(B.Buffer) + B.Size); + } }); __sanitizer::atomic_store(&LogFlushStatus, XRayLogFlushStatus::XRAY_LOG_FLUSHED, Index: compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h =================================================================== --- compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h +++ compiler-rt/trunk/lib/xray/xray_fdr_logging_impl.h @@ -311,10 +311,24 @@ __sanitizer::atomic_sint32_t &LoggingStatus, const std::shared_ptr &BQ) XRAY_NEVER_INSTRUMENT { // Bail out right away if logging is not initialized yet. - if (__sanitizer::atomic_load(&LoggingStatus, - __sanitizer::memory_order_acquire) != - XRayLogInitStatus::XRAY_LOG_INITIALIZED) + // We should take the opportunity to release the buffer though. + auto Status = __sanitizer::atomic_load(&LoggingStatus, + __sanitizer::memory_order_acquire); + if (Status != XRayLogInitStatus::XRAY_LOG_INITIALIZED) { + if (RecordPtr != nullptr && + (Status == XRayLogInitStatus::XRAY_LOG_FINALIZING || + Status == XRayLogInitStatus::XRAY_LOG_FINALIZED)) { + writeEOBMetadata(); + auto EC = BQ->releaseBuffer(Buffer); + if (EC != BufferQueue::ErrorCode::Ok) { + Report("Failed to release buffer at %p; error=%s\n", Buffer.Buffer, + BufferQueue::getErrorString(EC)); + return; + } + RecordPtr = nullptr; + } return; + } // We use a thread_local variable to keep track of which CPUs we've already // run, and the TSC times for these CPUs. This allows us to stop repeating the