+ if (master->notification_script) {
+ sentinelScheduleScriptExecution(master->notification_script,
+ type,msg,NULL);
+ }
+ }
+}
+
+/* ============================ script execution ============================ */
+
+/* Release a script job structure and all the associated data. */
+void sentinelReleaseScriptJob(sentinelScriptJob *sj) {
+ int j = 0;
+
+ while(sj->argv[j]) sdsfree(sj->argv[j++]);
+ zfree(sj->argv);
+ zfree(sj);
+}
+
+#define SENTINEL_SCRIPT_MAX_ARGS 16
+void sentinelScheduleScriptExecution(char *path, ...) {
+ va_list ap;
+ char *argv[SENTINEL_SCRIPT_MAX_ARGS+1];
+ int argc = 1;
+ sentinelScriptJob *sj;
+
+ va_start(ap, path);
+ while(argc < SENTINEL_SCRIPT_MAX_ARGS) {
+ argv[argc] = va_arg(ap,char*);
+ if (!argv[argc]) break;
+ argv[argc] = sdsnew(argv[argc]); /* Copy the string. */
+ argc++;
+ }
+ va_end(ap);
+ argv[0] = sdsnew(path);
+
+ sj = zmalloc(sizeof(*sj));
+ sj->flags = SENTINEL_SCRIPT_NONE;
+ sj->retry_num = 0;
+ sj->argv = zmalloc(sizeof(char*)*(argc+1));
+ sj->start_time = 0;
+ sj->pid = 0;
+ memcpy(sj->argv,argv,sizeof(char*)*(argc+1));
+
+ listAddNodeTail(sentinel.scripts_queue,sj);
+
+ /* Remove the oldest non running script if we already hit the limit. */
+ if (listLength(sentinel.scripts_queue) > SENTINEL_SCRIPT_MAX_QUEUE) {
+ listNode *ln;
+ listIter li;
+
+ listRewind(sentinel.scripts_queue,&li);
+ while ((ln = listNext(&li)) != NULL) {
+ sj = ln->value;
+
+ if (sj->flags & SENTINEL_SCRIPT_RUNNING) continue;
+ /* The first node is the oldest as we add on tail. */
+ listDelNode(sentinel.scripts_queue,ln);
+ sentinelReleaseScriptJob(sj);
+ break;
+ }
+ redisAssert(listLength(sentinel.scripts_queue) <=
+ SENTINEL_SCRIPT_MAX_QUEUE);
+ }
+}
+
+/* Lookup a script in the scripts queue via pid, and returns the list node
+ * (so that we can easily remove it from the queue if needed). */
+listNode *sentinelGetScriptListNodeByPid(pid_t pid) {
+ listNode *ln;
+ listIter li;
+
+ listRewind(sentinel.scripts_queue,&li);
+ while ((ln = listNext(&li)) != NULL) {
+ sentinelScriptJob *sj = ln->value;
+
+ if ((sj->flags & SENTINEL_SCRIPT_RUNNING) && sj->pid == pid)
+ return ln;
+ }
+ return NULL;
+}
+
+/* Run pending scripts if we are not already at max number of running
+ * scripts. */
+void sentinelRunPendingScripts(void) {
+ listNode *ln;
+ listIter li;
+ mstime_t now = mstime();
+
+ /* Find jobs that are not running and run them, from the top to the
+ * tail of the queue, so we run older jobs first. */
+ listRewind(sentinel.scripts_queue,&li);
+ while (sentinel.running_scripts < SENTINEL_SCRIPT_MAX_RUNNING &&
+ (ln = listNext(&li)) != NULL)
+ {
+ sentinelScriptJob *sj = ln->value;
+ pid_t pid;
+
+ /* Skip if already running. */
+ if (sj->flags & SENTINEL_SCRIPT_RUNNING) continue;
+
+ /* Skip if it's a retry, but not enough time has elapsed. */
+ if (sj->start_time && sj->start_time > now) continue;
+
+ sj->flags |= SENTINEL_SCRIPT_RUNNING;
+ sj->start_time = mstime();
+ sj->retry_num++;
+ pid = fork();
+
+ if (pid == -1) {
+ /* Parent (fork error).
+ * We report fork errors as signal 99, in order to unify the
+ * reporting with other kind of errors. */
+ sentinelEvent(REDIS_WARNING,"-script-error",NULL,
+ "%s %d %d", sj->argv[0], 99, 0);
+ sj->flags &= ~SENTINEL_SCRIPT_RUNNING;
+ sj->pid = 0;
+ } else if (pid == 0) {
+ /* Child */
+ execve(sj->argv[0],sj->argv,environ);
+ /* If we are here an error occurred. */
+ _exit(2); /* Don't retry execution. */
+ } else {
+ sentinel.running_scripts++;
+ sj->pid = pid;
+ sentinelEvent(REDIS_DEBUG,"+script-child",NULL,"%ld",(long)pid);
+ }
+ }
+}
+
+/* How much to delay the execution of a script that we need to retry after
+ * an error?
+ *
+ * We double the retry delay for every further retry we do. So for instance
+ * if RETRY_DELAY is set to 30 seconds and the max number of retries is 10
+ * starting from the second attempt to execute the script the delays are:
+ * 30 sec, 60 sec, 2 min, 4 min, 8 min, 16 min, 32 min, 64 min, 128 min. */
+mstime_t sentinelScriptRetryDelay(int retry_num) {
+ mstime_t delay = SENTINEL_SCRIPT_RETRY_DELAY;
+
+ while (retry_num-- > 1) delay *= 2;
+ return delay;
+}
+
+/* Check for scripts that terminated, and remove them from the queue if the
+ * script terminated successfully. If instead the script was terminated by
+ * a signal, or returned exit code "1", it is scheduled to run again if
+ * the max number of retries did not already elapsed. */
+void sentinelCollectTerminatedScripts(void) {
+ int statloc;
+ pid_t pid;
+
+ while ((pid = wait3(&statloc,WNOHANG,NULL)) > 0) {
+ int exitcode = WEXITSTATUS(statloc);
+ int bysignal = 0;
+ listNode *ln;
+ sentinelScriptJob *sj;
+
+ if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc);
+ sentinelEvent(REDIS_DEBUG,"-script-child",NULL,"%ld %d %d",
+ (long)pid, exitcode, bysignal);
+
+ ln = sentinelGetScriptListNodeByPid(pid);
+ if (ln == NULL) {
+ redisLog(REDIS_WARNING,"wait3() returned a pid (%ld) we can't find in our scripts execution queue!", (long)pid);
+ continue;
+ }
+ sj = ln->value;
+
+ /* If the script was terminated by a signal or returns an
+ * exit code of "1" (that means: please retry), we reschedule it
+ * if the max number of retries is not already reached. */
+ if ((bysignal || exitcode == 1) &&
+ sj->retry_num != SENTINEL_SCRIPT_MAX_RETRY)
+ {
+ sj->flags &= ~SENTINEL_SCRIPT_RUNNING;
+ sj->pid = 0;
+ sj->start_time = mstime() +
+ sentinelScriptRetryDelay(sj->retry_num);
+ } else {
+ /* Otherwise let's remove the script, but log the event if the
+ * execution did not terminated in the best of the ways. */
+ if (bysignal || exitcode != 0) {
+ sentinelEvent(REDIS_WARNING,"-script-error",NULL,
+ "%s %d %d", sj->argv[0], bysignal, exitcode);
+ }
+ listDelNode(sentinel.scripts_queue,ln);
+ sentinelReleaseScriptJob(sj);
+ sentinel.running_scripts--;
projects / redis.git / blobdiff