github/repmgr
1
0
Fork 0
mirror of https://github.com/EnterpriseDB/repmgr.git synced 2026-03-26 16:46:28 +00:00
Code Issues Packages Projects Releases 1 Wiki Activity

repmgrd: retry standby connection after "follow_command" executed

Browse Source 
It's possible that the standby is still starting up after the "follow_command"
completes, so poll for a while until we get a connection.
This commit is contained in:
Ian Barwick
2018-02-28 15:35:47 +09:00
parent c7a585c555
commit 5e8b41e221
1 changed files with 29 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
repmgrd-physical.c
View File

@@ -2179,8 +2179,6 @@ follow_new_primary(int new_primary_id)
return FAILOVER_STATE_FOLLOW_FAIL; return FAILOVER_STATE_FOLLOW_FAIL;
} }
/* /*
* refresh local copy of local and primary node records - we get these * refresh local copy of local and primary node records - we get these
* directly from the primary to ensure they're the current version * directly from the primary to ensure they're the current version
@@ -2203,7 +2201,34 @@ follow_new_primary(int new_primary_id)
return FAILOVER_STATE_FOLLOW_FAIL; return FAILOVER_STATE_FOLLOW_FAIL;
} }
local_conn = establish_db_connection(local_node_info.conninfo, false); {
/*
* It's possible that the standby is still starting up after the "follow_command"
* completes, so poll for a while until we get a connection.
*
* TODO:
* - implement for cascading standby follow too
* - make timeout configurable ("standby_reconnect_timeout")
*/
int i, max = 60;
for (i = 0; i < max; i++)
{
local_conn = establish_db_connection(local_node_info.conninfo, false);
if (PQstatus(local_conn) == CONNECTION_OK)
break;
log_debug("sleeping 1 second; %i of %i attempts to reconnect to local node", i + 1, max);
sleep(1);
}
if (PQstatus(local_conn) != CONNECTION_OK)
{
log_error(_("unable to reconnect to local node %i"),
local_node_info.node_id);
return FAILOVER_STATE_FOLLOW_FAIL;
}
}
/* refresh shared memory settings which will have been zapped by the restart */ /* refresh shared memory settings which will have been zapped by the restart */
repmgrd_set_local_node_id(local_conn, config_file_options.node_id); repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
@@ -2216,8 +2241,7 @@ follow_new_primary(int new_primary_id)
log_notice("%s", event_details.data); log_notice("%s", event_details.data);
create_event_notification( create_event_notification(upstream_conn,
upstream_conn,
&config_file_options, &config_file_options,
local_node_info.node_id, local_node_info.node_id,
"repmgrd_failover_follow", "repmgrd_failover_follow",