1f5841c8ed
SYSLIB CHANGES: - SEF must be used by every system process and is thereby part of the system library. - The framework provides a receive() interface (sef_receive) for system processes to automatically catch known system even messages and process them. - SEF provides a default behavior for each type of system event, but allows system processes to register callbacks to override the default behavior. - Custom (local to the process) or predefined (provided by SEF) callback implementations can be registered to SEF. - SEF currently includes support for 2 types of system events: 1. SEF Ping. The event occurs every time RS sends a ping to figure out whether a system process is still alive. The default callback implementation provided by SEF is to notify RS back to let it know the process is alive and kicking. 2. SEF Live update. The event occurs every time RS sends a prepare to update message to let a system process know an update is available and to prepare for it. The live update support is very basic for now. SEF only deals with verifying if the prepare state can be supported by the process, dumping the state for debugging purposes, and providing an event-driven programming model to the process to react to state changes check-in when ready to update. - SEF should be extended in the future to integrate support for more types of system events. Ideally, all the cross-cutting concerns should be integrated into SEF to avoid duplicating code and ease extensibility. Examples include: * PM notify messages primarily used at shutdown. * SYSTEM notify messages primarily used for signals. * CLOCK notify messages used for system alarms. * Debug messages. IS could still be in charge of fkey handling but would forward the debug message to the target process (e.g. PM, if the user requested debug information about PM). SEF would then catch the message and do nothing unless the process has registered an appropriate callback to deal with the event. This simplifies the programming model to print debug information, avoids duplicating code, and reduces the effort to print debug information. SYSTEM PROCESSES CHANGES: - Every system process registers SEF callbacks it needs to override the default system behavior and calls sef_startup() right after being started. - sef_startup() does almost nothing now, but will be extended in the future to support callbacks of its own to let RS control and synchronize with every system process at initialization time. - Every system process calls sef_receive() now rather than receive() directly, to let SEF handle predefined system events. RS CHANGES: - RS supports a basic single-component live update protocol now, as follows: * When an update command is issued (via "service update *"), RS notifies the target system process to prepare for a specific update state. * If the process doesn't respond back in time, the update is aborted. * When the process responds back, RS kills it and marks it for refreshing. * The process is then automatically restarted as for a buggy process and can start running again. * Live update is currently prototyped as a controlled failure.
181 lines
5.4 KiB
C
181 lines
5.4 KiB
C
/* Data Store Server.
|
|
* This service implements a little publish/subscribe data store that is
|
|
* crucial for the system's fault tolerance. Components that require state
|
|
* can store it here, for later retrieval, e.g., after a crash and subsequent
|
|
* restart by the reincarnation server.
|
|
*
|
|
* Created:
|
|
* Oct 19, 2005 by Jorrit N. Herder
|
|
*/
|
|
|
|
#include "inc.h" /* include master header file */
|
|
#include <minix/endpoint.h>
|
|
|
|
/* Allocate space for the global variables. */
|
|
endpoint_t who_e; /* caller's proc number */
|
|
int callnr; /* system call number */
|
|
int sys_panic; /* flag to indicate system-wide panic */
|
|
|
|
extern int errno; /* error number set by system library */
|
|
|
|
/* Declare some local functions. */
|
|
FORWARD _PROTOTYPE(void init_server, (int argc, char **argv) );
|
|
FORWARD _PROTOTYPE(void exit_server, (void) );
|
|
FORWARD _PROTOTYPE(void sig_handler, (void) );
|
|
FORWARD _PROTOTYPE(void get_work, (message *m_ptr) );
|
|
FORWARD _PROTOTYPE(void reply, (int whom, message *m_ptr) );
|
|
|
|
/* SEF functions and variables. */
|
|
FORWARD _PROTOTYPE( void sef_local_startup, (void) );
|
|
|
|
/*===========================================================================*
|
|
* main *
|
|
*===========================================================================*/
|
|
PUBLIC int main(int argc, char **argv)
|
|
{
|
|
/* This is the main routine of this service. The main loop consists of
|
|
* three major activities: getting new work, processing the work, and
|
|
* sending the reply. The loop never terminates, unless a panic occurs.
|
|
*/
|
|
message m;
|
|
int result;
|
|
sigset_t sigset;
|
|
|
|
/* SEF local startup. */
|
|
sef_local_startup();
|
|
|
|
/* Initialize the server, then go to work. */
|
|
init_server(argc, argv);
|
|
|
|
/* Main loop - get work and do it, forever. */
|
|
while (TRUE) {
|
|
|
|
/* Wait for incoming message, sets 'callnr' and 'who'. */
|
|
get_work(&m);
|
|
|
|
if (is_notify(callnr)) {
|
|
switch (_ENDPOINT_P(who_e)) {
|
|
case PM_PROC_NR:
|
|
sig_handler();
|
|
break;
|
|
default:
|
|
report("DS","warning, got illegal notify from:",
|
|
m.m_source);
|
|
result = EINVAL;
|
|
goto send_reply;
|
|
}
|
|
|
|
/* done, get a new message */
|
|
}
|
|
|
|
switch (callnr) {
|
|
case DS_PUBLISH:
|
|
result = do_publish(&m);
|
|
break;
|
|
case DS_RETRIEVE:
|
|
result = do_retrieve(&m);
|
|
break;
|
|
case DS_SUBSCRIBE:
|
|
result = do_subscribe(&m);
|
|
break;
|
|
case DS_CHECK:
|
|
result = do_check(&m);
|
|
break;
|
|
case GETSYSINFO:
|
|
result = do_getsysinfo(&m);
|
|
break;
|
|
default:
|
|
report("DS","warning, got illegal request from:", m.m_source);
|
|
result = EINVAL;
|
|
}
|
|
|
|
send_reply:
|
|
/* Finally send reply message, unless disabled. */
|
|
if (result != EDONTREPLY) {
|
|
m.m_type = result; /* build reply message */
|
|
reply(who_e, &m); /* send it away */
|
|
}
|
|
}
|
|
return(OK); /* shouldn't come here */
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* sef_local_startup *
|
|
*===========================================================================*/
|
|
PRIVATE void sef_local_startup()
|
|
{
|
|
/* No live update support for now. */
|
|
|
|
/* Let SEF perform startup. */
|
|
sef_startup();
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* init_server *
|
|
*===========================================================================*/
|
|
PRIVATE void init_server(int argc, char **argv)
|
|
{
|
|
/* Initialize the data store server. */
|
|
int i, s;
|
|
struct sigaction sigact;
|
|
|
|
/* Initialize DS. */
|
|
ds_init();
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* sig_handler *
|
|
*===========================================================================*/
|
|
PRIVATE void sig_handler()
|
|
{
|
|
/* Signal handler. */
|
|
sigset_t sigset;
|
|
int sig;
|
|
|
|
/* Try to obtain signal set from PM. */
|
|
if (getsigset(&sigset) != 0) return;
|
|
|
|
/* Check for known signals. */
|
|
if (sigismember(&sigset, SIGTERM)) {
|
|
exit_server();
|
|
}
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* exit_server *
|
|
*===========================================================================*/
|
|
PRIVATE void exit_server()
|
|
{
|
|
/* Shut down the information service. */
|
|
|
|
/* Done. Now exit. */
|
|
exit(0);
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* get_work *
|
|
*===========================================================================*/
|
|
PRIVATE void get_work(m_ptr)
|
|
message *m_ptr; /* message buffer */
|
|
{
|
|
int status = 0;
|
|
status = sef_receive(ANY, m_ptr); /* this blocks until message arrives */
|
|
if (OK != status)
|
|
panic("DS","failed to receive message!", status);
|
|
who_e = m_ptr->m_source; /* message arrived! set sender */
|
|
callnr = m_ptr->m_type; /* set function call number */
|
|
}
|
|
|
|
/*===========================================================================*
|
|
* reply *
|
|
*===========================================================================*/
|
|
PRIVATE void reply(who_e, m_ptr)
|
|
int who_e; /* destination */
|
|
message *m_ptr; /* message buffer */
|
|
{
|
|
int s;
|
|
s = send(who_e, m_ptr); /* send the message */
|
|
if (OK != s)
|
|
printf("DS: unable to send reply to %d: %d\n", who_e, s);
|
|
}
|
|
|