[Cluster-devel] [DLM PATCH] dlm_controld: outputs explicit info about stateful merging

[Eric Ren]

When there are 3 or more partitions that merge, none may see enough
clean nodes. Therefore, DLM would be stuck there forever unitl
administrator manually reset/restart enough nodes to produce sufficient
clean nodes. Therefore, output explicit information for higher code (e.g. pcmk)
about the stateful merging state. Now, higher code can use `dlm status
-v` to get "stateful_merge_wait". If it equals "1", we know dlm is
waiting manual intervention. Then, higher code can choose one of nodes
to fence. DLM will continue to work if "clean nodes >= stateful merged
nodes" becomes true.

David advised me to do the right thing;-) Thanks a lot!

Signed-off-by: Eric Ren 
---
 dlm_controld/daemon_cpg.c | 11 +--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/dlm_controld/daemon_cpg.c b/dlm_controld/daemon_cpg.c
index 356e80d..0d55027 100644
--- a/dlm_controld/daemon_cpg.c
+++ b/dlm_controld/daemon_cpg.c
@@ -118,6 +118,7 @@ static int zombie_count;
 
 static int fence_result_pid;
 static unsigned int fence_result_try;
+static int stateful_merge_wait; /* cluster is stuck in waiting for manual 
intervention */
 
 static void send_fence_result(int nodeid, int result, uint32_t flags, uint64_t 
walltime);
 static void send_fence_clear(int nodeid, int result, uint32_t flags, uint64_t 
walltime);
@@ -847,10 +848,14 @@ static void daemon_fence_work(void)
 
if ((clean_count >= merge_count) && !part_count && (low == 
our_nodeid))
kick_stateful_merge_members();
+   if ((clean_count < merge_count) && !part_count)
+   stateful_merge_wait = 1;
 
retry = 1;
goto out;
}
+   if (stateful_merge_wait)
+   stateful_merge_wait = 0;
 
/*
 * startup fencing
@@ -2382,7 +2387,8 @@ static int print_state_daemon(char *str)
 "fence_pid=%d "
 "fence_in_progress_unknown=%d "
 "zombie_count=%d "
-"monotime=%llu ",
+"monotime=%llu "
+"stateful_merge_wait=%d ",
 daemon_member_count,
 daemon_joined_count,
 daemon_remove_count,
@@ -2392,7 +2398,8 @@ static int print_state_daemon(char *str)
 daemon_fence_pid,
 fence_in_progress_unknown,
 zombie_count,
-(unsigned long long)monotime());
+(unsigned long long)monotime(),
+stateful_merge_wait);
 
return strlen(str) + 1;
 }
-- 
2.6.6

[Cluster-devel] [DLM PATCH] dlm_controld: outputs explicit info about stateful merging

[Eric Ren]

When there are 3 or more partitions that merge, none may see enough
clean nodes. Therefore, DLM would be stuck there forever unitl
administrator manually reset/restart enough nodes to produce sufficient
clean nodes. Therefore, output explicit information for higher code (e.g. pcmk)
about the stateful merging state. Now, higher code can use `dlm status
-v` to get "stateful_merge_wait". If it equals "1", we know dlm is
waiting manual intervention. Then, higher code can choose one of nodes
to fence. DLM will continue to work if "clean nodes >= stateful merged
nodes" becomes true.

David advised me to do the right thing;-) Thanks a lot!

Signed-off-by: Eric Ren 
---
 dlm_controld/daemon_cpg.c | 10 --
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/dlm_controld/daemon_cpg.c b/dlm_controld/daemon_cpg.c
index 356e80d..8f6434f 100644
--- a/dlm_controld/daemon_cpg.c
+++ b/dlm_controld/daemon_cpg.c
@@ -118,6 +118,7 @@ static int zombie_count;
 
 static int fence_result_pid;
 static unsigned int fence_result_try;
+static int stateful_merge_wait; /* cluster is stuck in waiting for manual 
intervention */
 
 static void send_fence_result(int nodeid, int result, uint32_t flags, uint64_t 
walltime);
 static void send_fence_clear(int nodeid, int result, uint32_t flags, uint64_t 
walltime);
@@ -847,10 +848,13 @@ static void daemon_fence_work(void)
 
if ((clean_count >= merge_count) && !part_count && (low == 
our_nodeid))
kick_stateful_merge_members();
+   if ((clean_count < merge_count) && !part_count)
+   stateful_merge_wait = 1;
 
retry = 1;
goto out;
}
+   stateful_merge_wait = 0; /* where should this line go? */
 
/*
 * startup fencing
@@ -2382,7 +2386,8 @@ static int print_state_daemon(char *str)
 "fence_pid=%d "
 "fence_in_progress_unknown=%d "
 "zombie_count=%d "
-"monotime=%llu ",
+"monotime=%llu "
+"stateful_merge_wait=%d ",
 daemon_member_count,
 daemon_joined_count,
 daemon_remove_count,
@@ -2392,7 +2397,8 @@ static int print_state_daemon(char *str)
 daemon_fence_pid,
 fence_in_progress_unknown,
 zombie_count,
-(unsigned long long)monotime());
+(unsigned long long)monotime(),
+stateful_merge_wait);
 
return strlen(str) + 1;
 }
-- 
2.6.6