Sentinel: ability to execute notification scripts.

2 files changed, 95 insertions, 11 deletions

diff --git a/sentinel.conf b/sentinel.conf
index ca291163d..eb2de6a5d 100644
--- a/sentinel.conf
+++ b/sentinel.conf
@@ -4,7 +4,8 @@
 # The port that this sentinel instance will run on
 port 26379
 
-# sentinel monitor <name> <ip> <redis-port> <quorum>
+# sentinel monitor <master-name> <ip> <redis-port> <quorum>
+#
 # Tells Sentinel to monitor this slave, and to consider it in O_DOWN
 # (Objectively Down) state only if at least <quorum> sentinels agree.
 #
@@ -12,7 +13,8 @@ port 26379
 # The valid charset is A-z 0-9 and the three characters ".-_".
 sentinel monitor mymaster 127.0.0.1 6379 2
 
-# sentinel down-after-milliseconds <mymaster> <milliseconds>
+# sentinel down-after-milliseconds <master-name> <milliseconds>
+#
 # Number of milliseconds the master (or any attached slave or sentinel) should
 # be unreachable (as in, not acceptable reply to PING, continuously, for the
 # specified period) in order to consider it in S_DOWN state (Subjectively
@@ -21,18 +23,21 @@ sentinel monitor mymaster 127.0.0.1 6379 2
 # Default is 30 seconds.
 sentinel down-after-milliseconds mymaster 30000
 
-# sentinel can-failover <mymaster> <yes|no>
+# sentinel can-failover <master-name> <yes|no>
+#
 # Specify if this Sentinel can start the failover for this master.
 sentinel can-failover mymaster yes
 
-# sentinel parallel-syncs <mymaster> <numslaves>
+# sentinel parallel-syncs <master-name> <numslaves>
+#
 # How many slaves we can reconfigure to point to the new slave simultaneously
 # during the failover. Use a low number if you use the slaves to serve query
 # to avoid that all the slaves will be unreachable at about the same
 # time while performing the synchronization with the master.
 sentinel parallel-syncs mymaster 1
 
-# sentinel failover-timeout <mymaster> <milliseconds>
+# sentinel failover-timeout <master-name> <milliseconds>
+#
 # Specifies the failover timeout in milliseconds. When this time has elapsed
 # without any progress in the failover process, it is considered concluded by
 # the sentinel even if not all the attached slaves were correctly configured
@@ -47,3 +52,22 @@ sentinel parallel-syncs mymaster 1
 # Default is 15 minutes.
 sentinel failover-timeout mymaster 900000
 
+# sentinel notification-script <master-name> <script-path>
+# 
+# Call the specified notification script for any sentienl event that is
+# generated in the WARNING level (for instance -sdown, -odown, and so forth).
+# This script should notify the system administrator via email, SMS, or any
+# other messaging system, that there is something wrong with the monitored
+# Redis systems.
+#
+# The script is called with just two arguments: the first is the event type
+# and the second the event description.
+#
+# The script must be exits and executable in order for sentinel to start if
+# this option is provided.
+#
+# Example:
+#
+# sentinel notification-script mymaster /var/redis/notify.sh
+
+
diff --git a/src/sentinel.c b/src/sentinel.c
index 54c675b57..227fb6938 100644
--- a/src/sentinel.c
+++ b/src/sentinel.c
@@ -37,6 +37,8 @@
 #include <arpa/inet.h>
 #include <sys/socket.h>
 
+extern char **environ;
+
 #define REDIS_SENTINEL_PORT 26379
 
 /* ======================== Sentinel global state =========================== */
@@ -169,7 +171,7 @@ typedef struct sentinelRedisInstance {
     struct sentinelRedisInstance *promoted_slave; /* Promoted slave instance. */
     /* Scripts executed to notify admin or reconfigure clients: when they
      * are set to NULL no script is executed. */
-    char *notify_script;
+    char *notification_script;
     char *client_reconfig_script;
 } sentinelRedisInstance;
 
@@ -291,6 +293,7 @@ void sentinelDisconnectInstanceFromContext(const redisAsyncContext *c);
 void sentinelKillLink(sentinelRedisInstance *ri, redisAsyncContext *c);
 const char *sentinelRedisInstanceTypeStr(sentinelRedisInstance *ri);
 void sentinelAbortFailover(sentinelRedisInstance *ri);
+void sentinelEvent(int level, char *type, sentinelRedisInstance *ri, const char *fmt, ...);
 
 /* ========================= Dictionary types =============================== */
 
@@ -403,7 +406,29 @@ void releaseSentinelAddr(sentinelAddr *sa) {
 /* =========================== Events notification ========================== */
 
 void sentinelCallNotificationScript(char *scriptpath, char *type, char *msg) {
-    /* TODO: implement it. */
+    pid_t pid = fork();
+
+    if (pid == -1) {
+        /* Parent on error. */
+        sentinelEvent(REDIS_WARNING,"-notification-script-error",NULL,
+                      "#can't fork: %s",strerror(errno));
+        return;
+    } else if (pid == 0) {
+        /* Child */
+        char *argv[4];
+
+        argv[0] = scriptpath;
+        argv[1] = type;
+        argv[2] = msg;
+        argv[3] = NULL;
+        execve(scriptpath,argv,environ);
+        /* If we are here an error occurred. */
+        sentinelEvent(REDIS_WARNING,"-notification-script-error",NULL,
+                      "#execve(2): %s",strerror(errno));
+        _exit(1);
+    } else {
+        sentinelEvent(REDIS_DEBUG,"+child",NULL,"%ld",(long)pid);
+    }
 }
 
 /* Send an event to log, pub/sub, user notification script.
@@ -480,8 +505,9 @@ void sentinelEvent(int level, char *type, sentinelRedisInstance *ri,
     if (level == REDIS_WARNING && ri != NULL) {
         sentinelRedisInstance *master = (ri->flags & SRI_MASTER) ?
                                          ri : ri->master;
-        if (master->notify_script) {
-            sentinelCallNotificationScript(master->notify_script,type,msg);
+        if (master->notification_script) {
+            sentinelCallNotificationScript(master->notification_script,
+                                           type,msg);
         }
     }
 }
@@ -584,7 +610,7 @@ sentinelRedisInstance *createSentinelRedisInstance(char *name, int flags, char *
     ri->failover_start_time = 0;
     ri->failover_timeout = SENTINEL_DEFAULT_FAILOVER_TIMEOUT;
     ri->promoted_slave = NULL;
-    ri->notify_script = NULL;
+    ri->notification_script = NULL;
     ri->client_reconfig_script = NULL;
 
     /* Add into the right table. */
@@ -608,7 +634,7 @@ void releaseSentinelRedisInstance(sentinelRedisInstance *ri) {
     /* Free other resources. */
     sdsfree(ri->name);
     sdsfree(ri->runid);
-    sdsfree(ri->notify_script);
+    sdsfree(ri->notification_script);
     sdsfree(ri->client_reconfig_script);
     sdsfree(ri->slave_master_host);
     sdsfree(ri->leader);
@@ -881,6 +907,21 @@ char *sentinelHandleConfiguration(char **argv, int argc) {
         ri = sentinelGetMasterByName(argv[1]);
         if (!ri) return "No such master with specified name.";
         ri->parallel_syncs = atoi(argv[2]);
+   } else if (!strcasecmp(argv[0],"notification-script") && argc == 3) {
+        /* notification-script <name> <path> */
+        ri = sentinelGetMasterByName(argv[1]);
+        if (!ri) return "No such master with specified name.";
+        if (access(argv[2],X_OK) == -1)
+            return "Notification script seems non existing or non executable.";
+        ri->notification_script = sdsnew(argv[2]);
+   } else if (!strcasecmp(argv[0],"client-reconfig-script") && argc == 3) {
+        /* client-reconfig-script <name> <path> */
+        ri = sentinelGetMasterByName(argv[1]);
+        if (!ri) return "No such master with specified name.";
+        if (access(argv[2],X_OK) == -1)
+            return "Client reconfiguration script seems non existing or "
+                   "non executable.";
+        ri->client_reconfig_script = sdsnew(argv[2]);
     } else {
         return "Unrecognized sentinel configuration statement.";
     }
@@ -2511,8 +2552,27 @@ void sentinelCheckTiltCondition(void) {
     sentinel.previous_time = mstime();
 }
 
+/* Handle terminated childs resulting from calls to notifications and client
+ * reconfigurations scripts. */
+void sentinelHandleChildren(void) {
+    int statloc;
+    pid_t pid;
+
+    if ((pid = wait3(&statloc,WNOHANG,NULL)) != 0) {
+        int exitcode = WEXITSTATUS(statloc);
+        int bysignal = 0;
+        
+        if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc);
+        sentinelEvent(REDIS_DEBUG,"-child",NULL,"%ld %d %d",
+            (long)pid, exitcode, bysignal);
+
+        /* TODO: remove client reconfiguration scripts from the queue. */
+    }
+}
+
 void sentinelTimer(void) {
     sentinelCheckTiltCondition();
     sentinelHandleDictOfRedisInstances(sentinel.masters);
+    sentinelHandleChildren();
 }