#include "lib/events/events.h"
#include "../common/rb_tree.h"
-static struct {
- struct timeval start;
- const char *script_running;
-} child_state;
-
static void ctdb_event_script_timeout(struct event_context *ev, struct timed_event *te, struct timeval t, void *p);
/*
- ctdbd sends us a SIGTERM when we should time out the current script
+ ctdbd sends us a SIGTERM when we should die.
*/
static void sigterm(int sig)
{
- char tbuf[100], buf[200];
- time_t t;
-
- DEBUG(DEBUG_ERR,("Timed out running script '%s' after %.1f seconds pid :%d\n",
- child_state.script_running, timeval_elapsed(&child_state.start), getpid()));
-
- t = time(NULL);
-
- strftime(tbuf, sizeof(tbuf)-1, "%Y%m%d%H%M%S", localtime(&t));
- sprintf(buf, "{ pstree -p; cat /proc/locks; ls -li /var/ctdb/ /var/ctdb/persistent; }"
- " >/tmp/ctdb.event.%s.%d", tbuf, getpid());
- system(buf);
-
- DEBUG(DEBUG_ERR,("Logged timedout eventscript : %s\n", buf));
-
/* all the child processes will be running in the same process group */
kill(-getpgrp(), SIGKILL);
_exit(1);
{
struct ctdb_event_script_state *state
= talloc_get_type(p, struct ctdb_event_script_state);
- struct ctdb_script_wire *current = get_current_script(state);
+ struct ctdb_script_wire *current;
unsigned int slen, min;
+ /* We may have been aborted to run something else. Discard */
+ if (state->scripts == NULL) {
+ return;
+ }
+
+ current = get_current_script(state);
+
/* Append, but don't overfill buffer. It starts zero-filled. */
slen = strlen(current->output);
min = MIN(len, sizeof(current->output) - slen - 1);
}
if (!(st.st_mode & S_IXUSR)) {
- DEBUG(DEBUG_INFO,("Event script %s is not executable. Ignoring this event script\n", full));
+ DEBUG(DEBUG_DEBUG,("Event script %s is not executable. Ignoring this event script\n", full));
errno = ENOEXEC;
talloc_free(full);
return false;
int ret;
TALLOC_CTX *tmp_ctx = talloc_new(ctdb);
- child_state.start = timeval_current();
ret = child_setup(ctdb);
if (ret != 0)
goto out;
cmdstr = child_command_string(ctdb, tmp_ctx, from_user,
current->name, call, options);
CTDB_NO_MEMORY(ctdb, cmdstr);
- child_state.script_running = cmdstr;
- DEBUG(DEBUG_INFO,("Executing event script %s\n",cmdstr));
+ DEBUG(DEBUG_DEBUG,("Executing event script %s\n",cmdstr));
if (current->status) {
ret = current->status;
}
}
+static void debug_timeout(struct ctdb_event_script_state *state)
+{
+ struct ctdb_script_wire *current = get_current_script(state);
+ char *cmd;
+ pid_t pid;
+ time_t t;
+ char tbuf[100], buf[200];
+
+ cmd = child_command_string(state->ctdb, state,
+ state->from_user, current->name,
+ state->call, state->options);
+ CTDB_NO_MEMORY_VOID(state->ctdb, cmd);
+
+ DEBUG(DEBUG_ERR,("Timed out running script '%s' after %.1f seconds pid :%d\n",
+ cmd, timeval_elapsed(¤t->start), state->child));
+ talloc_free(cmd);
+
+ t = time(NULL);
+ strftime(tbuf, sizeof(tbuf)-1, "%Y%m%d%H%M%S", localtime(&t));
+ sprintf(buf, "{ pstree -p; cat /proc/locks; ls -li /var/ctdb/ /var/ctdb/persistent; }"
+ " >/tmp/ctdb.event.%s.%d", tbuf, getpid());
+
+ pid = fork();
+ if (pid == 0) {
+ ctdb_reduce_priority(state->ctdb);
+ system(buf);
+ /* Now we can kill the child */
+ kill(state->child, SIGTERM);
+ exit(0);
+ }
+ if (pid == -1) {
+ DEBUG(DEBUG_ERR,("Fork for debug script failed : %s\n",
+ strerror(errno)));
+ } else {
+ DEBUG(DEBUG_ERR,("Logged timedout eventscript : %s\n", buf));
+ /* Don't kill child until timeout done. */
+ state->child = 0;
+ }
+}
+
/* called when child times out */
static void ctdb_event_script_timeout(struct event_context *ev, struct timed_event *te,
struct timeval t, void *p)
DEBUG(DEBUG_ERR,("Event script timed out : %s %s %s count : %u pid : %d\n",
current->name, ctdb_eventscript_call_names[state->call], state->options, ctdb->event_script_timeouts, state->child));
- state->scripts->scripts[state->current].status = -ETIME;
-
- if (kill(state->child, 0) != 0) {
- DEBUG(DEBUG_ERR,("Event script child process already dead, errno %s(%d)\n", strerror(errno), errno));
- state->child = 0;
+ /* ignore timeouts for these events */
+ switch (state->call) {
+ case CTDB_EVENT_START_RECOVERY:
+ case CTDB_EVENT_RECOVERED:
+ case CTDB_EVENT_TAKE_IP:
+ case CTDB_EVENT_RELEASE_IP:
+ case CTDB_EVENT_STOPPED:
+ case CTDB_EVENT_MONITOR:
+ case CTDB_EVENT_STATUS:
+ state->scripts->scripts[state->current].status = 0;
+ DEBUG(DEBUG_ERR,("Ignoring hung script for %s call %d\n", state->options, state->call));
+ break;
+ default:
+ state->scripts->scripts[state->current].status = -ETIME;
+ debug_timeout(state);
}
talloc_free(state);
{
switch (call) {
/* These all take no arguments. */
+ case CTDB_EVENT_INIT:
+ case CTDB_EVENT_SETUP:
case CTDB_EVENT_STARTUP:
case CTDB_EVENT_START_RECOVERY:
case CTDB_EVENT_RECOVERED:
case CTDB_EVENT_RELEASE_IP:
return count_words(options) == 3;
+ case CTDB_EVENT_UPDATE_IP: /* old interface, new interface, IP address, netmask bits. */
+ return count_words(options) == 4;
+
default:
DEBUG(DEBUG_ERR,(__location__ "Unknown ctdb_eventscript_call %u\n", call));
return false;
/* we guarantee that only some specifically allowed event scripts are run
while in recovery */
const enum ctdb_eventscript_call allowed_calls[] = {
- CTDB_EVENT_START_RECOVERY, CTDB_EVENT_SHUTDOWN, CTDB_EVENT_RELEASE_IP, CTDB_EVENT_STOPPED };
+ CTDB_EVENT_INIT,
+ CTDB_EVENT_SETUP,
+ CTDB_EVENT_START_RECOVERY,
+ CTDB_EVENT_SHUTDOWN,
+ CTDB_EVENT_RELEASE_IP,
+ CTDB_EVENT_STOPPED
+ };
int i;
for (i=0;i<ARRAY_SIZE(allowed_calls);i++) {
if (call == allowed_calls[i]) break;
ctdb->current_monitor = NULL;
}
- if (!from_user && (call == CTDB_EVENT_MONITOR || call == CTDB_EVENT_STATUS)) {
- ctdb->current_monitor = state;
- }
-
DEBUG(DEBUG_INFO,(__location__ " Starting eventscript %s %s\n",
ctdb_eventscript_call_names[state->call],
state->options));
return -1;
}
state->current = 0;
+ state->child = 0;
+
+ if (!from_user && (call == CTDB_EVENT_MONITOR || call == CTDB_EVENT_STATUS)) {
+ ctdb->current_monitor = state;
+ }
+
talloc_set_destructor(state, event_script_destructor);
/* Nothing to do? */
return 0;
}
- state->scripts->scripts[0].status = fork_child_for_script(ctdb, state);
- if (state->scripts->scripts[0].status != 0) {
- /* Callback is called from destructor, with fail result. */
- talloc_free(state);
- return 0;
- }
+ state->scripts->scripts[0].status = fork_child_for_script(ctdb, state);
+ if (state->scripts->scripts[0].status != 0) {
+ /* Callback is called from destructor, with fail result. */
+ talloc_free(state);
+ return 0;
+ }
if (!timeval_is_zero(&state->timeout)) {
event_add_timed(ctdb->ev, state, timeval_current_ofs(state->timeout.tv_sec, state->timeout.tv_usec), ctdb_event_script_timeout, state);