Death/condition notification
QNX SDP8.0High Availability Framework Developer's GuideDeveloper
Fault notification is a crucial part of the availability of a system. Apart from performing recovery per se, we also need to keep track of failures in order to be able to analyze the system at a later point.
For fault notification, you can use standard notification mechanisms such as pulses or signals. Clients specify what pulse/signal with specific values they want for each notification, and a HAM delivers the notifications at the appropriate times.
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <errno.h>
#include <sys/neutrino.h>
#include <sys/iomsg.h>
#include <sys/netmgr.h>
#include <signal.h>
#include <ha/ham.h>
#define PCODE_PTPD_DEATH (_PULSE_CODE_MINAVAIL+1)
#define PCODE_PTPD_DETACH (_PULSE_CODE_MINAVAIL+2)
#define PCODE_NFS_DELAYED (_PULSE_CODE_MINAVAIL+3)
#define PCODE_PTPD_RESTART1 (_PULSE_CODE_MINAVAIL+4)
#define PCODE_PTPD_RESTART2 (_PULSE_CODE_MINAVAIL+5)
#define MYSIG (SIGRTMIN+1)
int fsnfs_value;
/* Signal handler to handle the death notify of fs-nfs3 */
void MySigHandler(int signo, siginfo_t *info, void *extra)
{
printf("Received signal %d, with code = %d, value %d\n",
signo, info->si_code, info->si_value.sival_int);
if (info->si_value.sival_int == fsnfs_value)
printf("FS-nfs3 died, this is the notify signal\n");
return;
}
int main(int argc, char *argv[])
{
int chid, rc;
struct _pulse pulse;
pid_t pid;
int value;
ham_entity_t *ehdl;
ham_condition_t *chdl;
ham_action_t *ahdl;
struct sigaction sa;
int scode;
int svalue;
/* We need a channel to receive the pulse notification on. */
chid = ChannelCreate( _NTO_CHF_PRIVATE );
pid = getpid();
value = 13;
ham_connect(0);
/* Assumes there is already an entity by the name "ptpd2" */
chdl = ham_condition_handle(0, "ptpd2","death",0);
ahdl = ham_action_notify_pulse(chdl, "notifypulsedeath",0, pid,
chid, PCODE_PTPD_DEATH, value, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ham_condition_handle_free(chdl);
ehdl = ham_entity_handle(0, "ptpd2", 0);
chdl = ham_condition(ehdl, CONDDETACH, "detach", HREARMAFTERRESTART);
ahdl = ham_action_notify_pulse(chdl, "notifypulsedetach",0, pid,
chid, PCODE_PTPD_DETACH, value, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ham_condition_handle_free(chdl);
ham_entity_handle_free(ehdl);
fsnfs_value = 18; /* value we expect when fs-nfs dies */
scode = 0;
svalue = fsnfs_value;
sa.sa_sigaction = MySigHandler;
sigemptyset(&sa.sa_mask);
sa.sa_flags = SA_SIGINFO;
sigaction(MYSIG, &sa, NULL);
/*
Assumes there is an entity by the name "Fs-nfs3".
We use "Fs-nfs3" to symbolically represent the entity
fs-nfs3. Any name can be used to represent the
entity, but it's best to use a readable and meaningful name.
*/
ehdl = ham_entity_handle(0, "Fs-nfs3", 0);
/*
Add a new condition, which will be an "independent" condition.
This means that notifications/actions inside this condition
are not affected by "waitfor" delays in other action
sequence threads.
*/
chdl = ham_condition(ehdl,CONDDEATH, "DeathSep",
HCONDINDEPENDENT|HREARMAFTERRESTART);
ahdl = ham_action_notify_signal(chdl, "notifysignaldeath",0, pid,
MYSIG, scode, svalue, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ham_condition_handle_free(chdl);
ham_entity_handle_free(ehdl);
/* Get the condition handle directly without getting the entity first. */
chdl = ham_condition_handle(0, "Fs-nfs3","Death",0);
/*
This action is added to a condition that does not
have a HCONDNOWAIT. Since we are unaware what the condition
already contains, we might end up getting a delayed notification
since the action sequence might have "arbitrary" delays and
"waits" in it.
*/
ahdl = ham_action_notify_pulse(chdl, "delayednfsdeathpulse", 0,
pid, chid, PCODE_NFS_DELAYED, value, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ham_condition_handle_free(chdl);
ehdl = ham_entity_handle(0, "ptpd2", 0);
/* We force this condition to be independent of all others. */
chdl = ham_condition(ehdl, CONDRESTART, "restart",
HREARMAFTERRESTART|HCONDINDEPENDENT);
ahdl = ham_action_notify_pulse(chdl, "notifyrestart_imm", 0,
pid, chid, PCODE_PTPD_RESTART1, value, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ahdl = ham_action_waitfor(chdl, "delay",NULL,6532, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ahdl = ham_action_notify_pulse(chdl, "notifyrestart_delayed", 0,
pid, chid, PCODE_PTPD_RESTART2, value, HREARMAFTERRESTART);
ham_action_handle_free(ahdl);
ham_condition_handle_free(chdl);
ham_entity_handle_free(ehdl);
while (1) {
rc = MsgReceivePulse( chid, &pulse, sizeof( pulse ), NULL );
if (rc < 0) {
if (errno != EINTR) {
exit(EXIT_FAILURE);
}
} else {
switch (pulse.code) {
case PCODE_PTPD_DEATH:
printf("ptpd2 Death Pulse\n");
break;
case PCODE_NFS_DELAYED:
printf("fs-nfs3 died: this is the possibly delayed pulse\n");
break;
case PCODE_PTPD_DETACH:
printf("ptpd2 detached, so quitting\n");
goto the_end;
case PCODE_PTPD_RESTART1:
printf("ptpd2 Restart Pulse: Immediate\n");
break;
case PCODE_PTPD_RESTART2:
printf("ptpd2 Restart Pulse: Delayed\n");
break;
}
}
}
/*
At this point we are no longer waiting for the
information about ptpd2, since we know that monitoring
for it has been removed.
We would still continue to obtain information about the
death of fs-nfs3, since we did not remove those actions.
If we exit now, the next time those actions are executed
they will fail (notifications fail if the receiver does
exist anymore), and they will automatically get removed and
cleaned up.
*/
the_end:
ham_disconnect(0);
exit(0);
}
In the above example a client registers for various different types of notifications relating to significant events concerning ptpd2 and fs-nfs3. Notifications can be sent immediately or after a certain delay.
The notifications can also be received for each condition independently — for the entity's death (CONDDEATH), restart (CONDRESTART), and detaching (CONDDETACH).
The CONDRESTART is asserted by a HAM when an entity is successfully restarted.
Page updated: