I am trying to debug sporadic access violations that occur inside a boost::interprocess message queue. (access violation reading an address in the shared memory region).
Environment: boost 1.54, VC++2010. Occurs in both Debug & Release builds.
It always occurs on or about line 854 (in case of reception) in message_queue.hpp: Comments were added by me
recvd_size = top_msg.len; // top_msg points to invalid location
Or line 756 (in case of sending)
BOOST_ASSERT(free_msg_hdr.priority == 0); // free_msg_hdr points to invalid location
It appears as though this is related to the message queue creation. If a message queue is created "properly" (i.e. without the possible race condition), the error never occurs. Otherwise it might occur on timed_receive() or timed_send() on the queue at seemingly random times.
I came up with a short example that represents the problem: Unfortunately I cannot run it on Coliru, since it requires two processes. One has to be started without any parameters, the second with any single parameter. After a number of runs, one of the processes will crash in message_queue.
#include <iostream>
#include <boost/interprocess/ipc/message_queue.hpp>
#include <boost/thread.hpp>
#include <boost/assert.hpp>
#include <boost/date_time.hpp>
using namespace boost::interprocess;
using namespace boost::posix_time;
using boost::posix_time::microsec_clock; // microsec_clock is ambiguous between boost::posix_time and boost::interprocess. What are the odds?
int main(int argc, wchar_t** argv)
{
while(true)
{
int proc = 0;
message_queue* queues[2] = {NULL, NULL};
std::string names[] = {"msgq0", "msgq1"};
if(1 == argc)
{
proc = 0;
message_queue::remove(names[0].c_str());
if(NULL != queues[0]) { delete queues[0]; queues[0] = NULL; }
queues[0] = new message_queue(open_or_create, names[0].c_str(), 128, 10240);
bool bRet = false;
do
{
try
{
if(NULL != queues[1]) { delete queues[1]; queues[1] = NULL; }
queues[1]=new message_queue(open_only, names[1].c_str());
bRet = true;
}
catch(const interprocess_exception&)
{
//boost::this_thread::sleep(boost::posix_time::milliseconds(2));
delete queues[1];
queues[1] = NULL;
continue;
}
}while(!bRet);
}
else
{
proc = 1;
message_queue::remove(names[1].c_str());
if(NULL != queues[1]) { delete queues[1]; queues[1] = NULL; }
queues[1] = new message_queue(open_or_create, names[1].c_str(), 128, 10240);
bool bRet = false;
do
{
try
{
if(NULL != queues[0]) { delete queues[0]; queues[0] = NULL; }
queues[0]=new message_queue(open_only, names[0].c_str());
bRet = true;
}
catch(const interprocess_exception&)
{
//boost::this_thread::sleep(boost::posix_time::milliseconds(2));
delete queues[0];
queues[0] = NULL;
continue;
}
}while(!bRet);
}
long long nCnt = 0;
for(int i = 0; i < 1; ++i)
{
if(proc)
{
std::string sOut;
sOut = "Proc1 says: Hello ProcA " + std::to_string(nCnt) + " ";
sOut.resize(10230, ':');
for(int n = 0; n < 3; ++n)
{
queues[1]->timed_send(sOut.data(), sOut.size(), 0, ptime(boost::posix_time::microsec_clock::universal_time()) + milliseconds(1));
}
bool bMessage = false;
for(int n = 0; n < 3; ++n)
{
size_t nRec; unsigned int nPrio;
std::string sIn; sIn.resize(10240);
bMessage = queues[0]->timed_receive(&sIn[0], 10240, nRec, nPrio, ptime(boost::posix_time::microsec_clock::universal_time()) + milliseconds(1));
if(bMessage)
{
sIn.resize(nRec);
//std::cout << sIn << " ";
}
}
if(bMessage)
{
//std::cout << std::endl;
}
}
else
{
std::string sOut;
sOut = "Proc0 says: Hello Procccccccdadae4325a " + std::to_string(nCnt);
sOut.resize(10240, '.');
for(int n = 0; n < 3; ++n)
{
queues[0]->timed_send(sOut.data(), sOut.size(), 0, ptime(boost::posix_time::microsec_clock::universal_time()) + milliseconds(1));
}
bool bMessage = false;
for(int n = 0; n < 3; ++n)
{
size_t nRec; unsigned int nPrio;
std::string sIn; sIn.resize(10240);
bMessage = queues[1]->timed_receive(&sIn[0], 10240, nRec, nPrio, ptime(boost::posix_time::microsec_clock::universal_time()) + milliseconds(1));
if(bMessage)
{
sIn.resize(nRec);
//std::cout << sIn << " ";
}
}
if(bMessage)
{
//std::cout << std::endl;
}
}
nCnt++;
boost::this_thread::sleep(boost::posix_time::milliseconds(10));
}
}
return 0;
}
I am still thinking I might be doing something wrong, since I cannot find anything about this problem anywhere else, and the boost libraries are normally very good.
Is there anything I might be doing wrong with the usage of the message_queue in this example?
