Adding support for remote execution daemons.
Squashed commit of the following: commit 69d5ef7a256b86a86d46e5ae374c00fded1497ea Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 12:15:55 2021 -0400 Updating readme commit 94a9f676d0f9cc0b55cdc18c4927eaea40d82c77 Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 12:05:36 2021 -0400 Fixing serialization of attempt records when querying entire dag commit 945e5f90b24abf07c9af1bc4c6bbcb33e93b8069 Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 11:37:59 2021 -0400 Compiles cleanly... commit 8b23e46081d47fb80dc1a2d998fc6dc4bbf301a8 Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 10:43:03 2021 -0400 Adding in missing source file to cmake build list commit 6d10d9791206e2bc15788beadeea580b8e43a853 Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 10:41:43 2021 -0400 Adding new executors commit 42a2c67f4d6ae99df95d917c8621d78cd99837a1 Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 10:27:14 2021 -0400 Fixing missing curl cmake dependency commit 394bc4c5d51ecee7bf14712f719c8bf7e97fb0fa Author: Ian Roddis <tech@kinesin.ca> Date: Thu Dec 16 10:21:58 2021 -0400 Fixing missing curl cmake dependency commit dd9efc8e7e7770ea1bcbccb70a1af9cfcff0414c Author: Ian Roddis <tech@kinesin.ca> Date: Wed Dec 15 17:15:38 2021 -0400 Checkpointing progress commit 3b3b55d6037bb96e46de6763f486f4ecb92fe6a0 Author: Ian Roddis <tech@kinesin.ca> Date: Wed Dec 15 14:21:18 2021 -0400 updating readme commit 303027c11452941b2a0c0d1b04ac5942e79efd74 Author: Ian Roddis <tech@kinesin.ca> Date: Wed Dec 15 14:17:16 2021 -0400 Namespacing daggyd Adding more error checking around deserialization of parameters Adding tests for runner agent commit c592eaeba12e2a449bae401e8c1d9ed236416d52 Author: Ian Roddis <tech@kinesin.ca> Date: Wed Dec 15 11:20:21 2021 -0400 Checkpointing work commit fb1862d1cefe2b53a98659cce3c8c73d88bf5d84 Author: Ian Roddis <tech@kinesin.ca> Date: Wed Dec 15 09:52:29 2021 -0400 Copying daggyd for daggyr template, adding in basic routes
This commit is contained in:
Ian Roddis
193
daggyr/daggyr/daggyr.cpp
Normal file
193
daggyr/daggyr/daggyr.cpp
Normal file
@@ -0,0 +1,193 @@
|
||||
#include <rapidjson/document.h>
|
||||
#include <sys/stat.h>
|
||||
#include <sys/sysinfo.h>
|
||||
|
||||
#include <argparse.hpp>
|
||||
#include <atomic>
|
||||
#include <csignal>
|
||||
#include <daggy/Serialization.hpp>
|
||||
#include <daggyr/Server.hpp>
|
||||
#include <fstream>
|
||||
#include <iostream>
|
||||
|
||||
// Add executors here
|
||||
#include <daggy/executors/task/ForkingTaskExecutor.hpp>
|
||||
#include <daggy/executors/task/SlurmTaskExecutor.hpp>
|
||||
|
||||
// Add loggers here
|
||||
#include <daggy/executors/task/TaskExecutor.hpp>
|
||||
#include <daggy/loggers/dag_run/DAGRunLogger.hpp>
|
||||
#include <daggy/loggers/dag_run/OStreamLogger.hpp>
|
||||
#include <daggy/loggers/dag_run/RedisLogger.hpp>
|
||||
|
||||
namespace rj = rapidjson;
|
||||
|
||||
static std::atomic<bool> running{true};
|
||||
|
||||
void signalHandler(int signal)
|
||||
{
|
||||
switch (signal) {
|
||||
case SIGHUP:
|
||||
break;
|
||||
case SIGINT:
|
||||
case SIGTERM:
|
||||
running = false;
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
void daemonize()
|
||||
{
|
||||
pid_t pid;
|
||||
|
||||
struct sigaction newSigAction;
|
||||
sigset_t newSigSet;
|
||||
|
||||
/* Check if parent process id is set */
|
||||
if (getppid() == 1) {
|
||||
return;
|
||||
}
|
||||
|
||||
/* Set signal mask - signals we want to block */
|
||||
sigemptyset(&newSigSet);
|
||||
sigaddset(&newSigSet,
|
||||
SIGCHLD); /* ignore child - i.e. we don't need to wait for it */
|
||||
sigaddset(&newSigSet, SIGTSTP); /* ignore Tty stop signals */
|
||||
sigaddset(&newSigSet, SIGTTOU); /* ignore Tty background writes */
|
||||
sigaddset(&newSigSet, SIGTTIN); /* ignore Tty background reads */
|
||||
sigprocmask(SIG_BLOCK, &newSigSet,
|
||||
nullptr); /* Block the above specified signals */
|
||||
|
||||
/* Set up a signal handler */
|
||||
newSigAction.sa_handler = signalHandler;
|
||||
sigemptyset(&newSigAction.sa_mask);
|
||||
newSigAction.sa_flags = 0;
|
||||
|
||||
/* Signals to handle */
|
||||
sigaction(SIGHUP, &newSigAction, nullptr); /* catch hangup signal */
|
||||
sigaction(SIGTERM, &newSigAction, nullptr); /* catch term signal */
|
||||
sigaction(SIGINT, &newSigAction, nullptr); /* catch interrupt signal */
|
||||
|
||||
// Fork once
|
||||
pid = fork();
|
||||
if (pid < 0) {
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
if (pid > 0) {
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
/* On success: The child process becomes session leader */
|
||||
if (setsid() < 0) {
|
||||
std::cerr << "Unable to setsid" << std::endl;
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
/* Catch, ignore and handle signals */
|
||||
signal(SIGCHLD, SIG_IGN);
|
||||
signal(SIGHUP, SIG_IGN);
|
||||
|
||||
/* Fork off for the second time*/
|
||||
pid = fork();
|
||||
if (pid < 0)
|
||||
exit(EXIT_FAILURE);
|
||||
if (pid > 0)
|
||||
exit(EXIT_SUCCESS);
|
||||
|
||||
umask(0);
|
||||
|
||||
/* Change the working directory to the root directory */
|
||||
/* or another appropriated directory */
|
||||
auto rc = chdir("/");
|
||||
(void)rc;
|
||||
|
||||
/* Close all open file descriptors */
|
||||
for (int x = sysconf(_SC_OPEN_MAX); x >= 0; x--) {
|
||||
close(x);
|
||||
}
|
||||
}
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
argparse::ArgumentParser args("Daggy");
|
||||
|
||||
args.add_argument("-v", "--verbose")
|
||||
.default_value(false)
|
||||
.implicit_value(true);
|
||||
args.add_argument("-d", "--daemon").default_value(false).implicit_value(true);
|
||||
args.add_argument("--config").default_value(std::string{});
|
||||
|
||||
try {
|
||||
args.parse_args(argc, argv);
|
||||
}
|
||||
catch (std::exception &e) {
|
||||
std::cout << "Error: " << e.what() << std::endl;
|
||||
std::cout << args;
|
||||
exit(1);
|
||||
}
|
||||
|
||||
struct sysinfo systemInfo;
|
||||
|
||||
sysinfo(&systemInfo);
|
||||
|
||||
bool verbose = args.get<bool>("--verbose");
|
||||
bool asDaemon = args.get<bool>("--daemon");
|
||||
auto configFile = args.get<std::string>("--config");
|
||||
std::string listenIP = "127.0.0.1";
|
||||
int listenPort = 2504;
|
||||
size_t webThreads = 50;
|
||||
ssize_t maxCores = std::max(1U, std::thread::hardware_concurrency() - 2);
|
||||
ssize_t maxMemoryMB =
|
||||
std::max((systemInfo.totalram / (1024 * 1024) * 0.75), 100.0);
|
||||
|
||||
if (!configFile.empty()) {
|
||||
std::ifstream ifh(configFile);
|
||||
std::string config;
|
||||
std::getline(ifh, config, '\0');
|
||||
ifh.close();
|
||||
|
||||
rj::Document doc;
|
||||
daggy::checkRJParse(doc.Parse(config.c_str()));
|
||||
|
||||
if (doc.HasMember("ip"))
|
||||
listenIP = doc["ip"].GetString();
|
||||
if (doc.HasMember("port"))
|
||||
listenPort = doc["port"].GetInt();
|
||||
if (doc.HasMember("web-threads"))
|
||||
webThreads = doc["web-threads"].GetInt64();
|
||||
if (doc.HasMember("capacity-overrides")) {
|
||||
const auto &co = doc["capacity-overrides"];
|
||||
if (co.HasMember("cores"))
|
||||
maxCores = co["cores"].GetInt64();
|
||||
if (co.HasMember("memoryMB"))
|
||||
maxCores = co["memoryMB"].GetInt64();
|
||||
}
|
||||
}
|
||||
|
||||
if (verbose) {
|
||||
std::cout << "Server running at http://" << listenIP << ':' << listenPort
|
||||
<< std::endl
|
||||
<< "Max Cores: " << maxCores << std::endl
|
||||
<< "Max Memory: " << maxMemoryMB << " MB" << std::endl
|
||||
<< "Max Web Clients: " << webThreads << std::endl
|
||||
<< std::endl
|
||||
<< "Ctrl-C to exit" << std::endl;
|
||||
}
|
||||
|
||||
if (asDaemon) {
|
||||
daemonize();
|
||||
}
|
||||
|
||||
Pistache::Address listenSpec(listenIP, listenPort);
|
||||
daggy::daggyr::Server server(listenSpec, maxCores, maxMemoryMB);
|
||||
server.init(webThreads);
|
||||
server.start();
|
||||
|
||||
running = true;
|
||||
while (running) {
|
||||
std::this_thread::sleep_for(std::chrono::seconds(30));
|
||||
}
|
||||
server.shutdown();
|
||||
}
|
||||
Reference in New Issue
Block a user