[Cluster-devel] [PATCH 1/5] rgmanager: Add extra service status call (RHEL5)

[Cluster-devel] [PATCH 1/5] rgmanager: Add extra service status call (RHEL5)

[Lon Hohberger]

Pass the flags and last transition time back to caller
if the caller requests it with an additional parameter.

Resolves: rhbz#743214

Signed-off-by: Lon Hohberger <lhh@redhat.com>
---
 rgmanager/src/daemons/slang_event.c |  105 +++++++++++++++++++++++++++++++++--
 1 files changed, 100 insertions(+), 5 deletions(-)

diff --git a/rgmanager/src/daemons/slang_event.c b/rgmanager/src/daemons/slang_event.c
index 468706f..c9cca7a 100644
--- a/rgmanager/src/daemons/slang_event.c
+++ b/rgmanager/src/daemons/slang_event.c
@@ -30,6 +30,7 @@
 
 #include <stdio.h>
 #include <string.h>
+#define HAVE_LONG_LONG 1
 #include <slang.h>
 #include <sys/syslog.h>
 #include <malloc.h>
@@ -229,14 +230,68 @@ get_service_state_internal(char *svcName, rg_state_t *svcStatus)
 
 
 /*
-   (restarts, last_owner, owner, state) = get_service_status(servicename)
+   (rte, restarts, last_owner, owner, state) =
+		service_status(servicename)
+
+For extra information (flags, transition time)
+   (transition_time, flags, rte, restarts, owner, state) = 
+                service_status(servicename, 1);
  */
-void
-sl_service_status(char *svcName)
+static void
+sl_service_status(void)
 {
+	char *svcName = NULL;
+	char *state_str;
 	rg_state_t svcStatus;
 	int restarts_exceeded = 0;
-	char *state_str;
+	int nargs = 0, t = 0, extra = 0, flags = 0;
+	unsigned long long mtime;
+
+	nargs = SLang_Num_Function_Args;
+
+	/* Takes one or two args */
+	if (nargs <= 0 || nargs > 2) {
+		SLang_verror(SL_Syntax_Error,
+		     (char *)"%s: Wrong # of args (%d), must be 1 or 2\n",
+		     __FUNCTION__,
+		     nargs);
+		return;
+	}
+
+	if (nargs == 2) {
+		t = SLang_peek_at_stack();
+		if (t != SLANG_INT_TYPE) {
+			SLang_verror(SL_Syntax_Error,
+				     (char *)"%s: expected type %d got %d\n",
+				     __FUNCTION__, SLANG_INT_TYPE, t);
+			return;
+		}
+
+		if (SLang_pop_integer(&extra) < 0) {
+			SLang_verror(SL_Syntax_Error,
+			    (char *)"%s: Failed to pop integer from stack!\n",
+			    __FUNCTION__);
+			return;
+		}
+	}
+
+	t = SLang_peek_at_stack();
+	if (t != SLANG_STRING_TYPE) {
+		SLang_verror(SL_Syntax_Error,
+			     (char *)"%s: expected type %d got %d\n",
+			     __FUNCTION__,
+			     SLANG_STRING_TYPE, t);
+		return;
+	}
+
+	if (SLpop_string(&svcName) < 0) {
+		SLang_verror(SL_Syntax_Error,
+		    (char *)"%s: Failed to pop string from stack!\n",
+		    __FUNCTION__);
+		return;
+	}
+
+	/* Ok, got our parameters */
 
 	if (get_service_state_internal(svcName, &svcStatus) < 0) {
 		SLang_verror(SL_RunTime_Error,
@@ -246,6 +301,28 @@ sl_service_status(char *svcName)
 		return;
 	}
 
+	if (extra) {
+		/* push transition time and flags on to the stack */
+
+		mtime = (unsigned long long)svcStatus.rs_transition;
+		if (SLang_push_ulong_long(mtime) < 0) {
+			SLang_verror(SL_RunTime_Error,
+				     (char *)"%s: Failed to push mtime %s",
+				     __FUNCTION__,
+				     svcName);
+			return;
+		}
+
+		flags = (int)svcStatus.rs_flags;
+		if (SLang_push_integer(flags) < 0) {
+			SLang_verror(SL_RunTime_Error,
+				     (char *)"%s: Failed to push flags %s",
+				     __FUNCTION__,
+				     svcName);
+			return;
+		}
+	}
+
 	restarts_exceeded = check_restart(svcName);
 	if (SLang_push_integer(restarts_exceeded) < 0) {
 		SLang_verror(SL_RunTime_Error,
@@ -928,6 +1005,8 @@ array_to_string(char *buf, int buflen, int *array, int arraylen)
 void
 sl_clulog(int level)
 {
+	unsigned long long s_ullval;
+	unsigned long s_ulval;
 	int t, nargs, len;
 	//int level;
 	int s_intval;
@@ -937,6 +1016,7 @@ sl_clulog(int level)
 	char tmp[256];
 	int need_free;
 	int remain = sizeof(logbuf)-2;
+	SLang_Any_Type *stuff = NULL;
 
 	nargs = SLang_Num_Function_Args;
 	if (nargs < 1)
@@ -960,6 +1040,16 @@ sl_clulog(int level)
 			}
 			free(nodes);
 			break;
+		case SLANG_ULONG_TYPE:
+			if (SLang_pop_ulong(&s_ulval) < 0)
+				return;
+			len=snprintf(tmp, sizeof(tmp) - 1, "%lu", s_ulval);
+			break;
+		case SLANG_ULLONG_TYPE:
+			if (SLang_pop_ulong_long(&s_ullval) < 0)
+				return;
+			len=snprintf(tmp, sizeof(tmp) - 1, "%llu", s_ullval);
+			break;
 		case SLANG_INT_TYPE:
 			if (SLang_pop_integer(&s_intval) < 0)
 				return;
@@ -976,6 +1066,11 @@ sl_clulog(int level)
 			need_free = 0;
 			len=snprintf(tmp, sizeof(tmp) - 1,
 				     "{UnknownType %d}", t);
+			SLang_pop_anytype(&stuff);
+			if (stuff) {
+				SLang_free_anytype(stuff);
+				stuff = NULL;
+			}
 			break;
 		}
 
@@ -1075,7 +1170,7 @@ SLang_Intrin_Fun_Type rgmanager_slang[] =
 	MAKE_INTRINSIC_0("service_start", sl_start_service, SLANG_INT_TYPE),
 	MAKE_INTRINSIC_0((char *)"service_migrate", sl_migrate_service,
 			 SLANG_INT_TYPE),
-	MAKE_INTRINSIC_S("service_status", sl_service_status,
+	MAKE_INTRINSIC_0((char *)"service_status", sl_service_status,
 			 SLANG_VOID_TYPE),
 	MAKE_INTRINSIC_S("service_freeze", sl_service_freeze,
 			 SLANG_INT_TYPE),
-- 
1.7.3.4

[Cluster-devel] [PATCH 2/5] rgmanager: Avoid duplicate restart of service (RHEL5)

[Lon Hohberger]

If B depends on A and both A and B are running on
node 1 and node 1 fails, the stop events generated
will inadvertently cause B to be restarted after
the initial failover.

This patch resolves this issue by comparing the
start times in central_processing mode.

A known limitation to this patch is that in order
for this patch to work correctly, the cluster nodes'
time must be approximately in sync.

Resolves: rhbz#743214

Signed-off-by: Lon Hohberger <lhh@redhat.com>
---
 rgmanager/src/resources/default_event_script.sl |   19 ++++++++++++++++++-
 1 files changed, 18 insertions(+), 1 deletions(-)

diff --git a/rgmanager/src/resources/default_event_script.sl b/rgmanager/src/resources/default_event_script.sl
index cdde066..2d5503f 100644
--- a/rgmanager/src/resources/default_event_script.sl
+++ b/rgmanager/src/resources/default_event_script.sl
@@ -444,6 +444,8 @@ define default_service_event_handler()
 	variable tmp;
 	variable owner;
 	variable state;
+	variable d_trans, s_trans;
+	variable s_state;
 
 	debug("Executing default service event handler");
 
@@ -498,17 +500,32 @@ define default_service_event_handler()
 			continue;
 		}
 
-		(,,, owner, state) = service_status(services[x]);
+		(d_trans,,,, owner, state) = service_status(services[x], 1);
 		if ((service_state == "started") and (owner < 0) and
 		    (state == "stopped")) {
 			info("Dependency met; starting ", services[x]);
 			nodes = allowed_nodes(services[x]);
 			()=move_or_start(services[x], nodes);
+			continue;
 		}
 
 		% service died - stop service(s) that depend on the dead
 		if ((service_owner < 0) and (owner >= 0) and
 		    (depend_mode != "soft")) {
+
+			% grab the -current- state of the service here
+			% If the service is running, and its dependent service
+			% as above is running and the dependent service was
+			% started at or after the service, then stopping it
+			% will result in unwanted service outage.
+			(s_trans,,,, s_state) = service_status(service_name);
+			if ((s_state == "started") and (state == "started") and
+			    (d_trans >= s_trans)) {
+				debug("Skipping ", services[x],
+				      "; restart not needed");
+				continue;
+			}
+
 			info("Dependency lost; stopping ", services[x]);
 			()=service_stop(services[x]);
 		}
-- 
1.7.3.4

[Cluster-devel] [PATCH 3/5] rgmanager: Fix call to service_status() (RHEL5)

[Lon Hohberger]

This patch simply fixes the calls to service_status(), the
s_trans variable was being incorrectly set.

Resolves: rhbz#743214

Signed-off-by: Lon Hohberger <lhh@redhat.com>
---
 rgmanager/src/resources/default_event_script.sl |    7 +++++--
 1 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/rgmanager/src/resources/default_event_script.sl b/rgmanager/src/resources/default_event_script.sl
index 2d5503f..f2c7bc1 100644
--- a/rgmanager/src/resources/default_event_script.sl
+++ b/rgmanager/src/resources/default_event_script.sl
@@ -500,7 +500,7 @@ define default_service_event_handler()
 			continue;
 		}
 
-		(d_trans,,,, owner, state) = service_status(services[x], 1);
+		(d_trans,,,,, owner, state) = service_status(services[x], 1);
 		if ((service_state == "started") and (owner < 0) and
 		    (state == "stopped")) {
 			info("Dependency met; starting ", services[x]);
@@ -518,9 +518,12 @@ define default_service_event_handler()
 			% as above is running and the dependent service was
 			% started@or after the service, then stopping it
 			% will result in unwanted service outage.
-			(s_trans,,,, s_state) = service_status(service_name);
+			(s_trans,,,,,, s_state) = service_status(service_name, 1);
 			if ((s_state == "started") and (state == "started") and
 			    (d_trans >= s_trans)) {
+				%debug("S:", service_name, " trans ", s_trans);
+				%debug("D:", services[x], " trans ", d_trans);
+
 				debug("Skipping ", services[x],
 				      "; restart not needed");
 				continue;
-- 
1.7.3.4

[Cluster-devel] [PATCH 4/5] rgmanager: Fix tiny memory leak in sl_service_status (RHEL5)

[Lon Hohberger]

Resolves: rhbz#743214

Signed-off-by: Lon Hohberger <lhh@redhat.com>
---
 rgmanager/src/daemons/slang_event.c |   23 ++++++++++++++---------
 1 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/rgmanager/src/daemons/slang_event.c b/rgmanager/src/daemons/slang_event.c
index c9cca7a..b033656 100644
--- a/rgmanager/src/daemons/slang_event.c
+++ b/rgmanager/src/daemons/slang_event.c
@@ -234,7 +234,8 @@ get_service_state_internal(char *svcName, rg_state_t *svcStatus)
 		service_status(servicename)
 
 For extra information (flags, transition time)
-   (transition_time, flags, rte, restarts, owner, state) = 
+   (transition_time, flags, rte, restarts, last_owner,
+    owner, state) =
                 service_status(servicename, 1);
  */
 static void
@@ -298,7 +299,7 @@ sl_service_status(void)
 			     "%s: Failed to get status for %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	if (extra) {
@@ -310,7 +311,7 @@ sl_service_status(void)
 				     (char *)"%s: Failed to push mtime %s",
 				     __FUNCTION__,
 				     svcName);
-			return;
+			goto out_free;
 		}
 
 		flags = (int)svcStatus.rs_flags;
@@ -319,7 +320,7 @@ sl_service_status(void)
 				     (char *)"%s: Failed to push flags %s",
 				     __FUNCTION__,
 				     svcName);
-			return;
+			goto out_free;
 		}
 	}
 
@@ -329,7 +330,7 @@ sl_service_status(void)
 			     "%s: Failed to push restarts_exceeded %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	if (SLang_push_integer(svcStatus.rs_restarts) < 0) {
@@ -337,7 +338,7 @@ sl_service_status(void)
 			     "%s: Failed to push restarts for %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	if (SLang_push_integer(svcStatus.rs_last_owner) < 0) {
@@ -345,7 +346,7 @@ sl_service_status(void)
 			     "%s: Failed to push last owner of %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	switch(svcStatus.rs_state) {
@@ -363,7 +364,7 @@ sl_service_status(void)
 			     "%s: Failed to push owner of %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	if (svcStatus.rs_flags & RG_FLAG_FROZEN) {
@@ -379,7 +380,7 @@ sl_service_status(void)
 			     "%s: Failed to duplicate state of %s",
 			     __FUNCTION__,
 			     svcName);
-		return;
+		goto out_free;
 	}
 
 	if (SLang_push_malloced_string(state_str) < 0) {
@@ -389,6 +390,10 @@ sl_service_status(void)
 			     svcName);
 		free(state_str);
 	}
+
+out_free:
+	if (svcName)
+		free(svcName);
 }
 
 
-- 
1.7.3.4

[Cluster-devel] [PATCH 5/5] rgmanager: Fix dependency issue related to ordering (RHEL5)

[Lon Hohberger]

If you ordered two services the opposite way in cluster.conf
('b' first, which depends on 'a'), then rgmanager would fail
over 'b' despite the fact that 'a' was not running yet - this
is because the state of 'a' was not set to 'stopped' - so we
need to check for a node-death event in move_or_start().

Resolves: rhbz#743214

Signed-off-by: Lon Hohberger <lhh@redhat.com>
---
 rgmanager/src/resources/default_event_script.sl |    8 +++++---
 1 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/rgmanager/src/resources/default_event_script.sl b/rgmanager/src/resources/default_event_script.sl
index f2c7bc1..be434e9 100644
--- a/rgmanager/src/resources/default_event_script.sl
+++ b/rgmanager/src/resources/default_event_script.sl
@@ -156,7 +156,9 @@ define move_or_start(service, node_list)
 	depends = service_property(service, "depend");
 	if (depends != "") {
 		(,,, owner, state) = service_status(depends);
-		if (owner < 0) {
+		if ((owner < 0) or
+                    ((event_type == EVENT_NODE) and (owner == node_id) and
+		     (node_state == 0))) {
 			debug(service, " is not runnable; dependency not met");
 			()=service_stop(service);
 			return ERR_DEPEND;
@@ -521,8 +523,8 @@ define default_service_event_handler()
 			(s_trans,,,,,, s_state) = service_status(service_name, 1);
 			if ((s_state == "started") and (state == "started") and
 			    (d_trans >= s_trans)) {
-				%debug("S:", service_name, " trans ", s_trans);
-				%debug("D:", services[x], " trans ", d_trans);
+				debug("S:", service_name, " trans ", s_trans);
+				debug("D:", services[x], " trans ", d_trans);
 
 				debug("Skipping ", services[x],
 				      "; restart not needed");
-- 
1.7.3.4

[Cluster-devel] [PATCH 5/5] rgmanager: Fix dependency issue related to ordering (RHEL5)

[Lon Hohberger]

On 01/05/2012 10:57 AM, Lon Hohberger wrote:

> @@ -521,8 +523,8 @@ define default_service_event_handler()
>   			(s_trans,,,,,, s_state) = service_status(service_name, 1);
>   			if ((s_state == "started") and (state == "started") and
>   			    (d_trans>= s_trans)) {
> -				%debug("S:", service_name, " trans ", s_trans);
> -				%debug("D:", services[x], " trans ", d_trans);
> +				debug("S:", service_name, " trans ", s_trans);
> +				debug("D:", services[x], " trans ", d_trans);
>
>   				debug("Skipping ", services[x],
>   				      "; restart not needed");

Oops, the above won't be part of the patch set once merged.

-- Lon