Files
Jungfraujoch/image_pusher/HDF5FilePusher.cpp
T
leonarski_fandClaude Opus 5.5 509a54ef92 Broker: tell a reader which data files of the current collection are closed
So that rugnux can process a collection while it is written, the broker reports each data file once
a writer has closed it and renamed it into place:

- Writer: FileWriter takes a callback, called for every closed data file. StreamWriter uses it on TCP
  to send an acknowledgement with ack_for = FILE_CLOSED (new TCPFrameType 10): file number and the
  images the file holds. TCP protocol version 5. Files closed at END are reported before the END
  acknowledgement.
- LiveCollection (image_pusher): the start message the writer of the master file received, the
  closed files, the end. Fed by the TCP pusher (FILE_CLOSED acknowledgements; end once every writer
  acknowledged END) and by the in-process HDF5 pusher (the FileWriter callback). The ZeroMQ pusher
  has no back channel and offers none.
- Two routes, protected by the dataset's bearer tokens like the other dataset routes:
  - GET /live/start.cbor: that start message;
  - GET /live/events: server-sent events (collection, file, end, superseded) with the history first
    and a keepalive every 10 s. One follower at a time; a second gets 409.
  Documented in jfjoch_api.yaml; they add no schema, so the generated C++ model is unchanged.
- The HTTP server's thread pool is set explicitly (16, up to 64): an event stream holds a thread for
  the whole collection.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SVmAWnzCmRKAXVUCdc4iNi
2026-10-08 15:52:21 +02:00

155 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->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;
}