A re-initialisation left the previous run's ZMQImagePuller connected: JFJochServices::On replaces its own shared_ptr, but JFJochReceiverService keeps a second reference to the puller of the last run. Two PULL sockets on one PUSH peer share messages round-robin, so the orphaned puller silently took half of the DECTRIS stream - the start message included - and the receiver then waited for a start message that had already been discarded. Once such a run was cancelled, nothing drained the orphaned puller's outside_fifo any more. Its CBOR thread parked in PutBlocking on the full queue (suspend is only tested before the put), the puller thread backed up behind it in cbor_fifo, and neither could reach the disconnect flag again. The next JFJochReceiverService::Start dropped the last reference to that puller, so ~ZMQImagePuller joined two threads that could never exit - while holding state_mutex, inside a calibration sequence that itself holds the state machine's mutex. The whole control plane froze with no way to cancel; only a restart got out of it. * ThreadSafeFIFO gains Stop(), which releases every waiter and makes further blocking operations return at once. Clear() now notifies c_full as well: clearing a full queue used to leave the blocked producer asleep, since the next Get on an empty queue notifies no one. * ZMQImagePuller::Disconnect and TCPImagePuller::Disconnect stop their queues before joining, so a puller whose consumer is gone can always shut down. * JFJochServices::On and ::Off disconnect the previous puller explicitly rather than relying on the shared_ptr going away, so two readers never share the detector stream. ZMQImagePuller_DisconnectWithFullQueue covers the shutdown; it hangs on the previous code. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012bew392LTGP2fkhfRJsMcB
145 lines
4.0 KiB
C++
145 lines
4.0 KiB
C++
// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#pragma once
|
|
|
|
#include <queue>
|
|
#include <mutex>
|
|
#include <condition_variable>
|
|
#include <set>
|
|
|
|
template <class T>
|
|
class ThreadSafeFIFO {
|
|
std::queue<T> queue;
|
|
std::condition_variable c_empty, c_full;
|
|
mutable std::mutex m;
|
|
const size_t max_size;
|
|
size_t max_utilization;
|
|
size_t utilization;
|
|
bool stopped = false;
|
|
public:
|
|
explicit ThreadSafeFIFO(size_t in_max_size = UINT32_MAX) : max_size(in_max_size), max_utilization(0), utilization(0) {}
|
|
|
|
// Release every waiter and make all further blocking operations return at once: puts are
|
|
// dropped, gets answer with a default-constructed element. Used when the owner of the queue is
|
|
// torn down - at that point nobody is going to drain it any more, so a producer blocked on a
|
|
// full queue would never return and the thread join in the destructor would deadlock.
|
|
void Stop() {
|
|
std::unique_lock ul(m);
|
|
stopped = true;
|
|
c_empty.notify_all();
|
|
c_full.notify_all();
|
|
}
|
|
|
|
void Clear() {
|
|
std::unique_lock ul(m);
|
|
queue = {};
|
|
utilization = 0;
|
|
max_utilization = 0;
|
|
// A producer blocked on the full queue has to be told the room it was waiting for is there;
|
|
// nothing else would wake it, as the next Get finds the queue empty and notifies no one.
|
|
c_full.notify_all();
|
|
}
|
|
|
|
bool Put(T val) {
|
|
std::unique_lock ul(m);
|
|
if (queue.size() < max_size) {
|
|
queue.push(val);
|
|
c_empty.notify_one();
|
|
utilization++;
|
|
if (utilization > max_utilization)
|
|
max_utilization = utilization;
|
|
return true;
|
|
} else
|
|
return false;
|
|
};
|
|
|
|
void PutBlocking(T val) {
|
|
std::unique_lock ul(m);
|
|
c_full.wait(ul, [&]{return stopped || (queue.size() < max_size);});
|
|
if (stopped)
|
|
return;
|
|
queue.push(val);
|
|
utilization++;
|
|
if (utilization > max_utilization)
|
|
max_utilization = utilization;
|
|
c_empty.notify_one();
|
|
};
|
|
|
|
bool PutTimeout(T val, std::chrono::milliseconds timeout) {
|
|
std::unique_lock ul(m);
|
|
if (!c_full.wait_for(ul, timeout, [&]{ return stopped || (queue.size() < max_size); }))
|
|
return false;
|
|
if (stopped)
|
|
return false;
|
|
queue.push(val);
|
|
utilization++;
|
|
if (utilization > max_utilization)
|
|
max_utilization = utilization;
|
|
c_empty.notify_one();
|
|
return true;
|
|
}
|
|
|
|
int Get(T &val) {
|
|
std::unique_lock ul(m);
|
|
|
|
if (queue.empty())
|
|
return 0;
|
|
else {
|
|
val = queue.front();
|
|
queue.pop();
|
|
c_full.notify_one();
|
|
utilization--;
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
T GetBlocking() {
|
|
std::unique_lock ul(m);
|
|
c_empty.wait(ul, [&]{return stopped || !queue.empty();});
|
|
if (queue.empty())
|
|
return T{};
|
|
T tmp = queue.front();
|
|
queue.pop();
|
|
c_full.notify_one();
|
|
utilization--;
|
|
return tmp;
|
|
};
|
|
|
|
int GetTimeout(T &val, std::chrono::microseconds timeout) {
|
|
std::unique_lock ul(m);
|
|
if (queue.empty())
|
|
c_empty.wait_for(ul, timeout, [&]{return stopped || !queue.empty();});
|
|
|
|
if (queue.empty())
|
|
return 0;
|
|
else {
|
|
val = queue.front();
|
|
queue.pop();
|
|
c_full.notify_one();
|
|
utilization--;
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
[[nodiscard]] size_t Size() const {
|
|
std::unique_lock ul(m);
|
|
return queue.size();
|
|
}
|
|
|
|
void ClearMaxUtilization() {
|
|
std::unique_lock ul(m);
|
|
max_utilization = utilization;
|
|
}
|
|
|
|
[[nodiscard]] size_t GetMaxUtilization() const {
|
|
std::unique_lock ul(m);
|
|
return max_utilization;
|
|
}
|
|
|
|
[[nodiscard]] size_t GetCurrentUtilization() const {
|
|
std::unique_lock ul(m);
|
|
return utilization;
|
|
}
|
|
};
|