Files
Jungfraujoch/image_pusher/HDF5FilePusher.cpp
T
leonarski_fandClaude Opus 5.5 aca27be862 jfjoch_writer writes rugnux's .mtz, _maps.mtz and _model.cif from the END blocks
New gemmi-only library JFJochRugnuxFiles (writer/), linked by JFJochWriter, so
the writer needs no analysis library and builds with JFJOCH_WRITER_ONLY:
- WriteMergedMtz / WriteMapCoefficientsMtz / PlacedModelStructure make the
  files from the structured blocks; WriteRugnuxResultFiles writes whichever
  blocks END carries beside the master, each under a temporary name and renamed
  into place, an existing file replaced only when the run's overwrite is set.
  A file that fails costs only itself (logged), not the run.
- FillRugnuxResultBlocks reads the blocks back from the files rugnux wrote at
  a prefix (p.mtz, p_maps.mtz, p_model.cif), for the broker to fill END.

WriteMtzReflections now goes through WriteMergedMtz (MergedReflectionsForWriter
builds the block); its output is byte-identical to before, checked by md5 on a
synthetic set in both the Friedel-merged and the anomalous layout.

StreamWriter writes the files after the master and before the END ACK, so the
ACK means they are in place; END receipt and each rename are logged at INFO
with the wall-clock time, for last-frame-to-files latency. The broker's direct
HDF5 pusher writes them too.

Test: rugnux's three files -> blocks -> CBOR -> writer reproduces all of them
(and _model.pdb) byte for byte; a ~25k-reflection END is 2.7 MB.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-17 12:19:51 +02:00

156 lines
5.5 KiB
C++

// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "HDF5FilePusher.h"
#include "../frame_serialize/CBORStream2Deserializer.h"
#include "../frame_serialize/CBORStream2Serializer.h"
HDF5FilePusher::HDF5FilePusher(const std::string &repub_address,
const std::optional<int32_t> &repub_watermark) {
if (!repub_address.empty()) {
repub_socket = std::make_unique<ZMQSocket>(ZMQSocketType::Push);
repub_socket->SendWaterMark(repub_watermark.value_or(default_repub_watermark));
repub_socket->SendTimeout(RepubTimeout);
repub_socket->Bind(repub_address);
}
}
void HDF5FilePusher::Preflight(StartMessage &message) {
// In-process writer, so the check is the same call the FileWriter constructor will make.
FileWriter::Preflight(message);
}
void HDF5FilePusher::StartDataCollection(StartMessage &message) {
if (writer)
throw JFJochException(JFJochExceptionCategory::WrongDAQState, "Image pusher is already writing images");
writer = std::make_unique<FileWriter>(message);
writer->FileClosedCallback([this](const HDF5DataFileStatistics &s) {
live.FileClosed(s.file_number - 1, s.max_image_number + 1); // the statistics count files from 1
});
writer_future = std::async(std::launch::async, &HDF5FilePusher::WriterThread, this);
images_written = 0;
{
serializer.SerializeSequenceStart(message);
live.Begin(message, std::vector<uint8_t>(serialization_buffer.begin(),
serialization_buffer.begin() + serializer.GetBufferSize()));
}
if (repub_socket) {
try {
StartMessage repub_message = message;
repub_message.writer_notification_zmq_addr = "";
serializer.SerializeSequenceStart(repub_message);
repub_active = repub_socket->Send(serialization_buffer.data(), serializer.GetBufferSize(), true);
if (repub_active)
logger.Info("Republish active");
} catch (const JFJochException &e) {
logger.ErrorException(e);
}
}
}
bool HDF5FilePusher::EndDataCollection(const EndMessage &message) {
if (!writer_future.valid())
throw JFJochException(JFJochExceptionCategory::WrongDAQState, "Image pusher wasn't writing files");
writer_queue.PutBlocking({.end = true});
// Release the writer on every exit path. If finalization throws (e.g. a target
// file already exists and overwrite is off) the writer must still be torn down,
// otherwise the next collection fails with "already writing images".
try {
writer_future.get();
if (!writer)
throw JFJochException(JFJochExceptionCategory::WrongDAQState, "Image pusher not ready for writing images");
writer->WriteHDF5(message);
writer->WriteResultFiles(message, logger);
writer->Finalize();
} catch (...) {
writer.reset();
live.End(message.max_image_number, "the writer failed to finish the collection");
throw;
}
writer.reset();
live.End(message.max_image_number);
if (repub_socket) {
try {
serializer.SerializeSequenceEnd(message);
if (repub_active)
repub_socket->Send(serialization_buffer.data(), serializer.GetBufferSize(), true);
} catch (const JFJochException &e) {
logger.ErrorException(e);
}
if (repub_active)
logger.Info("Republish finished");
repub_active = false;
}
return true;
}
bool HDF5FilePusher::SendImage(const uint8_t *image_data, size_t image_size, int64_t image_number) {
if (!writer)
throw JFJochException(JFJochExceptionCategory::WrongDAQState, "Image pusher not ready for sending");
auto deserialized = CBORStream2Deserialize(image_data, image_size);
if (deserialized->data_message) {
writer->Write(*deserialized->data_message);
images_written++;
if (repub_socket && repub_active) {
try {
repub_socket->Send(image_data, image_size, false);
} catch (const JFJochException &e) {
logger.ErrorException(e);
}
}
} else
throw JFJochException(JFJochExceptionCategory::InputParameterInvalid,
"HDF5FilePusher::SendImage accepts only data image");
return true;
}
bool HDF5FilePusher::SendImage(ZeroCopyReturnValue &z) {
writer_queue.PutBlocking(ImagePusherQueueElement{
.image_data = (uint8_t *) z.GetImage(),
.z = &z,
.end = false
});
return true;
}
bool HDF5FilePusher::SendCalibration(const CompressedImage &message) {
if (!writer)
throw JFJochException(JFJochExceptionCategory::WrongDAQState, "Image pusher not ready for sending");
writer->WriteHDF5(message);
return true;
}
void HDF5FilePusher::WriterThread() {
ImagePusherQueueElement e = writer_queue.GetBlocking();
while (!e.end) {
SendImage(e.image_data, e.z->GetImageSize(), e.z->GetImageNumber());
e.z->release();
e = writer_queue.GetBlocking();
}
}
std::string HDF5FilePusher::PrintSetup() const {
std::filesystem::path currentPath = std::filesystem::current_path();
return "HDF5FilePusher: Images are written directly to file in base directory " + currentPath.string();
}
std::optional<uint64_t> HDF5FilePusher::GetImagesWritten() const {
return images_written;
}
size_t HDF5FilePusher::GetConnectedWriters() const {
return 1;
}