#include "daemon.h"
#include <errno.h>
#include <fcntl.h>
+#include <signal.h>
#include <stdlib.h>
#include <string.h>
+#include <sys/resource.h>
#include <sys/wait.h>
#include <unistd.h>
+#include "command-line.h"
#include "fatal-signal.h"
#include "dirs.h"
#include "lockfile.h"
char *
make_pidfile_name(const char *name)
{
- return (!name ? xasprintf("%s/%s.pid", ovs_rundir, program_name)
- : *name == '/' ? xstrdup(name)
- : xasprintf("%s/%s", ovs_rundir, name));
+ return (!name
+ ? xasprintf("%s/%s.pid", ovs_rundir, program_name)
+ : abs_file_name(ovs_rundir, name));
}
/* Sets up a following call to daemonize() to create a pidfile named 'name'.
static void
monitor_daemon(pid_t daemon_pid)
{
- /* XXX Should limit the rate at which we restart the daemon. */
/* XXX Should log daemon's stderr output at startup time. */
const char *saved_program_name;
+ time_t last_restart;
+ char *status_msg;
saved_program_name = program_name;
program_name = xasprintf("monitor(%s)", program_name);
+ status_msg = xstrdup("healthy");
+ last_restart = TIME_MIN;
for (;;) {
int retval;
int status;
+ proctitle_set("%s: monitoring pid %lu (%s)",
+ saved_program_name, (unsigned long int) daemon_pid,
+ status_msg);
+
do {
retval = waitpid(daemon_pid, &status, 0);
} while (retval == -1 && errno == EINTR);
if (retval == -1) {
ovs_fatal(errno, "waitpid failed");
} else if (retval == daemon_pid) {
- char *status_msg = process_status_msg(status);
+ char *s = process_status_msg(status);
+ free(status_msg);
+ status_msg = xasprintf("pid %lu died, %s",
+ (unsigned long int) daemon_pid, s);
+ free(s);
+
if (should_restart(status)) {
- VLOG_ERR("%s daemon died unexpectedly (%s), restarting",
- saved_program_name, status_msg);
- free(status_msg);
+ if (WCOREDUMP(status)) {
+ /* Disable further core dumps to save disk space. */
+ struct rlimit r;
+
+ r.rlim_cur = 0;
+ r.rlim_max = 0;
+ if (setrlimit(RLIMIT_CORE, &r) == -1) {
+ VLOG_WARN("failed to disable core dumps: %s",
+ strerror(errno));
+ }
+ }
+
+ /* Throttle restarts to no more than once every 10 seconds. */
+ if (time(NULL) < last_restart + 10) {
+ VLOG_WARN("%s, waiting until 10 seconds since last "
+ "restart", status_msg);
+ for (;;) {
+ time_t now = time(NULL);
+ time_t wakeup = last_restart + 10;
+ if (now >= wakeup) {
+ break;
+ }
+ sleep(wakeup - now);
+ }
+ }
+ last_restart = time(NULL);
+ VLOG_ERR("%s, restarting", status_msg);
daemon_pid = fork_and_wait_for_startup(&daemonize_fd);
if (!daemon_pid) {
break;
}
} else {
- VLOG_INFO("%s daemon exited normally (%s), exiting",
- saved_program_name, status_msg);
+ VLOG_INFO("%s, exiting", status_msg);
exit(0);
}
}
}
+ free(status_msg);
/* Running in new daemon process. */
+ proctitle_restore();
free((char *) program_name);
program_name = saved_program_name;
}