[Openais] [PATCH 2/2] cfg: Handle errors from totem_mcast
totem_mcast function can return -1 if corosync is overloaded. Sadly
in many calls of this functions was error code ether not handled at
all, or handled by assert.
Commit changes behaviour to ether return CS_ERR_TRY_AGAIN or put
error code to later layers to handle it.
Signed-off-by: Jan Friesse jfrie...@redhat.com
---
services/cfg.c | 77 ++-
1 files changed, 59 insertions(+), 18 deletions(-)
diff --git a/services/cfg.c b/services/cfg.c
index b7aa63b..24f19f2 100644
--- a/services/cfg.c
+++ b/services/cfg.c
@@ -379,6 +379,7 @@ static int send_shutdown(void)
{
struct req_exec_cfg_shutdown req_exec_cfg_shutdown;
struct iovec iovec;
+ int result;
ENTER();
req_exec_cfg_shutdown.header.size =
@@ -389,10 +390,10 @@ static int send_shutdown(void)
iovec.iov_base = (char *)req_exec_cfg_shutdown;
iovec.iov_len = sizeof (struct req_exec_cfg_shutdown);
- assert (api-totem_mcast (iovec, 1, TOTEM_SAFE) == 0);
+ result = api-totem_mcast (iovec, 1, TOTEM_SAFE);
LEAVE();
- return 0;
+ return (result);
}
static void send_test_shutdown(void *only_conn, void *exclude_conn, int status)
@@ -426,6 +427,9 @@ static void send_test_shutdown(void *only_conn, void
*exclude_conn, int status)
static void check_shutdown_status(void)
{
+ int result;
+ cs_error_t error = CS_OK;
+
ENTER();
/*
@@ -448,9 +452,17 @@ static void check_shutdown_status(void)
shutdown_flags == CFG_SHUTDOWN_FLAG_REGARDLESS) {
TRACE1(shutdown confirmed);
+ /*
+* Tell other nodes we are going down
+*/
+ result = send_shutdown();
+ if (result == -1) {
+ error = CS_ERR_TRY_AGAIN;
+ }
+
res_lib_cfg_tryshutdown.header.size = sizeof(struct
res_lib_cfg_tryshutdown);
res_lib_cfg_tryshutdown.header.id =
MESSAGE_RES_CFG_TRYSHUTDOWN;
- res_lib_cfg_tryshutdown.header.error = CS_OK;
+ res_lib_cfg_tryshutdown.header.error = error;
/*
* Tell originator that shutdown was confirmed
@@ -459,10 +471,6 @@ static void check_shutdown_status(void)
sizeof(res_lib_cfg_tryshutdown));
shutdown_con = NULL;
- /*
-* Tell other nodes we are going down
-*/
- send_shutdown();
}
else {
@@ -698,7 +706,9 @@ static void message_handler_req_lib_cfg_ringreenable (
const void *msg)
{
struct req_exec_cfg_ringreenable req_exec_cfg_ringreenable;
+ struct res_lib_cfg_ringreenable res_lib_cfg_ringreenable;
struct iovec iovec;
+ int result;
ENTER();
req_exec_cfg_ringreenable.header.size =
@@ -711,7 +721,19 @@ static void message_handler_req_lib_cfg_ringreenable (
iovec.iov_base = (char *)req_exec_cfg_ringreenable;
iovec.iov_len = sizeof (struct req_exec_cfg_ringreenable);
- assert (api-totem_mcast (iovec, 1, TOTEM_SAFE) == 0);
+ result = api-totem_mcast (iovec, 1, TOTEM_SAFE);
+
+ if (result == -1) {
+ res_lib_cfg_ringreenable.header.id =
MESSAGE_RES_CFG_RINGREENABLE;
+ res_lib_cfg_ringreenable.header.size = sizeof (struct
res_lib_cfg_ringreenable);
+ res_lib_cfg_ringreenable.header.error = CS_ERR_TRY_AGAIN;
+ api-ipc_response_send (
+ conn,
+ res_lib_cfg_ringreenable,
+ sizeof (struct res_lib_cfg_ringreenable));
+
+ api-ipc_refcnt_dec(conn);
+ }
LEAVE();
}
@@ -836,6 +858,8 @@ static void message_handler_req_lib_cfg_killnode (
struct res_lib_cfg_killnode res_lib_cfg_killnode;
struct req_exec_cfg_killnode req_exec_cfg_killnode;
struct iovec iovec;
+ int result;
+ cs_error_t error = CS_OK;
ENTER();
req_exec_cfg_killnode.header.size =
@@ -848,11 +872,14 @@ static void message_handler_req_lib_cfg_killnode (
iovec.iov_base = (char *)req_exec_cfg_killnode;
iovec.iov_len = sizeof (struct req_exec_cfg_killnode);
- (void)api-totem_mcast (iovec, 1, TOTEM_SAFE);
+ result = api-totem_mcast (iovec, 1, TOTEM_SAFE);
+ if (result == -1) {
+ error = CS_ERR_TRY_AGAIN;
+ }
res_lib_cfg_killnode.header.size = sizeof(struct res_lib_cfg_killnode);
res_lib_cfg_killnode.header.id = MESSAGE_RES_CFG_KILLNODE;
- res_lib_cfg_killnode.header.error = CS_OK;
+ res_lib_cfg_killnode.header.error = error;
[Openais] [PATCH 1/2] cpg: Handle errors from totem_mcast
totem_mcast function can return -1 if corosync is overloaded. Sadly in
many calls of this functions was error code ether not handled at all, or
handled by assert.
Commit changes behaviour to ether return CS_ERR_TRY_AGAIN or put error
code to later layers to handle it.
Signed-off-by: Jan Friesse jfrie...@redhat.com
---
services/cpg.c | 31 ++-
1 files changed, 26 insertions(+), 5 deletions(-)
diff --git a/services/cpg.c b/services/cpg.c
index 6669fbd..18767bd 100644
--- a/services/cpg.c
+++ b/services/cpg.c
@@ -865,12 +865,19 @@ static void cpg_pd_finalize (struct cpg_pd *cpd)
static int cpg_lib_exit_fn (void *conn)
{
struct cpg_pd *cpd = (struct cpg_pd *)api-ipc_private_data_get (conn);
+ int result;
log_printf(LOGSYS_LEVEL_DEBUG, exit_fn for conn=%p\n, conn);
if (cpd-group_name.length 0) {
- cpg_node_joinleave_send (cpd-pid, cpd-group_name,
+ result = cpg_node_joinleave_send (cpd-pid, cpd-group_name,
MESSAGE_REQ_EXEC_CPG_PROCLEAVE,
CONFCHG_CPG_REASON_PROCDOWN);
+ if (result == -1) {
+ /*
+* Call this function again later
+*/
+ return (result);
+ }
}
cpg_pd_finalize (cpd);
@@ -1289,6 +1296,7 @@ static void message_handler_req_lib_cpg_join (void *conn,
const void *message)
struct res_lib_cpg_join res_lib_cpg_join;
cs_error_t error = CPG_OK;
struct list_head *iter;
+ int result;
/* Test, if we don't have same pid and group name joined */
for (iter = cpg_pd_list_head.next; iter != cpg_pd_list_head; iter =
iter-next) {
@@ -1327,9 +1335,15 @@ static void message_handler_req_lib_cpg_join (void
*conn, const void *message)
memcpy (cpd-group_name, req_lib_cpg_join-group_name,
sizeof (cpd-group_name));
- cpg_node_joinleave_send (req_lib_cpg_join-pid,
+ result = cpg_node_joinleave_send (req_lib_cpg_join-pid,
req_lib_cpg_join-group_name,
MESSAGE_REQ_EXEC_CPG_PROCJOIN, CONFCHG_CPG_REASON_JOIN);
+
+ if (result == -1) {
+ error = CPG_ERR_TRY_AGAIN;
+ cpd-cpd_state = CPD_STATE_UNJOINED;
+ goto response_send;
+ }
break;
case CPD_STATE_LEAVE_STARTED:
error = CPG_ERR_BUSY;
@@ -1356,6 +1370,7 @@ static void message_handler_req_lib_cpg_leave (void
*conn, const void *message)
cs_error_t error = CPG_OK;
struct req_lib_cpg_leave *req_lib_cpg_leave = (struct
req_lib_cpg_leave *)message;
struct cpg_pd *cpd = (struct cpg_pd *)api-ipc_private_data_get (conn);
+ int result;
log_printf(LOGSYS_LEVEL_DEBUG, got leave request on %p\n, conn);
@@ -1372,10 +1387,14 @@ static void message_handler_req_lib_cpg_leave (void
*conn, const void *message)
case CPD_STATE_JOIN_COMPLETED:
error = CPG_OK;
cpd-cpd_state = CPD_STATE_LEAVE_STARTED;
- cpg_node_joinleave_send (req_lib_cpg_leave-pid,
+ result = cpg_node_joinleave_send (req_lib_cpg_leave-pid,
req_lib_cpg_leave-group_name,
MESSAGE_REQ_EXEC_CPG_PROCLEAVE,
CONFCHG_CPG_REASON_LEAVE);
+ if (result == -1) {
+ error = CPG_ERR_TRY_AGAIN;
+ cpd-cpd_state = CPD_STATE_JOIN_COMPLETED;
+ }
break;
}
@@ -1458,8 +1477,10 @@ static void message_handler_req_lib_cpg_mcast (void
*conn, const void *message)
req_exec_cpg_iovec[1].iov_base = (char
*)req_lib_cpg_mcast-message;
req_exec_cpg_iovec[1].iov_len = msglen;
- result = api-totem_mcast (req_exec_cpg_iovec, 2, TOTEM_AGREED);
- assert(result == 0);
+ result = api-totem_mcast (req_exec_cpg_iovec, 2, TOTEM_AGREED);
+ if (result == -1) {
+ error = CPG_ERR_TRY_AGAIN;
+ }
}
res_lib_cpg_mcast.header.size = sizeof(res_lib_cpg_mcast);
--
1.7.1
___
Openais mailing list
Openais@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/openais
Re: [Openais] Corosync Compatability
On Wed, Jul 27, 2011 at 1:28 PM, manish.gu...@ionidea.com wrote: Thank you Steave, We are currentely using corosync-1.2.1 and pacemaker 1.0.10 Can we use the same version of pacemaker with corosync-1.4 I'd say its likely. Try on one node - you'll find out pretty quickly if its not going to work On Tue, July 26, 2011 7:12 pm, Steven Dake wrote: On 07/26/2011 01:52 AM, manish.gu...@ionidea.com wrote: Hi, I am facing problem with redundent Communication Channel. I am using Coroync 1.2 In this auto failback of redundent channel is not Supported. But 1.4 provide support. Corosync-1.4 id compatiable with which version of pacemaker corosync 1.4 should work with all versions of pacemaker. What version of pm are you using? Regards -steve ___ Openais mailing list Openais@lists.linux-foundation.org https://lists.linux-foundation.org/mailman/listinfo/openais ___ Openais mailing list Openais@lists.linux-foundation.org https://lists.linux-foundation.org/mailman/listinfo/openais ___ Openais mailing list Openais@lists.linux-foundation.org https://lists.linux-foundation.org/mailman/listinfo/openais
