github/repmgr
1
0
Fork 0
mirror of https://github.com/EnterpriseDB/repmgr.git synced 2026-03-22 22:56:29 +00:00
Code Issues Packages Projects Releases 1 Wiki Activity

Standardize on "ID: %i" when logging node IDs

Browse Source 
Previously there was a mix of "id:", "node id:", "node ID:" and "node_id:".
This commit is contained in:
Ian Barwick
2019-04-30 17:07:33 +09:00
parent 6c3b4c0db8
commit 52905f1eb3
8 changed files with 74 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
doc/configuration-file-log-settings.sgml
View File

@@ -98,7 +98,7 @@
describing <application>repmgrd</application>'s current state, e.g.: describing <application>repmgrd</application>'s current state, e.g.:
</para> </para>
<programlisting> <programlisting>
[2018-07-12 00:47:32] [INFO] monitoring connection to upstream node "node1" (node ID: 1)</programlisting> [2018-07-12 00:47:32] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
</listitem> </listitem>
</varlistentry> </varlistentry>

22
doc/repmgrd-automatic-failover.sgml
View File

@@ -288,13 +288,13 @@
<application>repmgrd</application> on the primary has started up, while two child <application>repmgrd</application> on the primary has started up, while two child
nodes are being provisioned: nodes are being provisioned:
<programlisting> <programlisting>
[2019-04-24 15:25:33] [INFO] monitoring primary node "node1" (node ID: 1) in normal state [2019-04-24 15:25:33] [INFO] monitoring primary node "node1" (ID: 1) in normal state
[2019-04-24 15:25:35] [NOTICE] new node "node2" (node ID: 2) has connected [2019-04-24 15:25:35] [NOTICE] new node "node2" (ID: 2) has connected
[2019-04-24 15:25:35] [NOTICE] 1 (of 1) child nodes are connected, but at least 2 child nodes required [2019-04-24 15:25:35] [NOTICE] 1 (of 1) child nodes are connected, but at least 2 child nodes required
[2019-04-24 15:25:35] [INFO] no child nodes have detached since repmgrd startup [2019-04-24 15:25:35] [INFO] no child nodes have detached since repmgrd startup
(...) (...)
[2019-04-24 15:25:44] [NOTICE] new node "node3" (node ID: 3) has connected [2019-04-24 15:25:44] [NOTICE] new node "node3" (ID: 3) has connected
[2019-04-24 15:25:46] [INFO] monitoring primary node "node1" (node ID: 1) in normal state [2019-04-24 15:25:46] [INFO] monitoring primary node "node1" (ID: 1) in normal state
(...)</programlisting> (...)</programlisting>
</para> </para>
<para> <para>
@@ -302,9 +302,9 @@
is now waiting <varname>child_nodes_disconnect_timeout</varname> seconds is now waiting <varname>child_nodes_disconnect_timeout</varname> seconds
before executing <varname>child_nodes_disconnect_command</varname>: before executing <varname>child_nodes_disconnect_command</varname>:
<programlisting> <programlisting>
[2019-04-24 15:28:11] [INFO] monitoring primary node "node1" (node ID: 1) in normal state [2019-04-24 15:28:11] [INFO] monitoring primary node "node1" (ID: 1) in normal state
[2019-04-24 15:28:17] [INFO] monitoring primary node "node1" (node ID: 1) in normal state [2019-04-24 15:28:17] [INFO] monitoring primary node "node1" (ID: 1) in normal state
[2019-04-24 15:28:19] [NOTICE] node "node3" (node ID: 3) has disconnected [2019-04-24 15:28:19] [NOTICE] node "node3" (ID: 3) has disconnected
[2019-04-24 15:28:19] [NOTICE] 1 (of 2) child nodes are connected, but at least 2 child nodes required [2019-04-24 15:28:19] [NOTICE] 1 (of 2) child nodes are connected, but at least 2 child nodes required
[2019-04-24 15:28:19] [INFO] most recently detached child node was 3 (ca. 0 seconds ago), not triggering "child_nodes_disconnect_command" [2019-04-24 15:28:19] [INFO] most recently detached child node was 3 (ca. 0 seconds ago), not triggering "child_nodes_disconnect_command"
[2019-04-24 15:28:19] [DETAIL] "child_nodes_disconnect_timeout" set To 30 seconds [2019-04-24 15:28:19] [DETAIL] "child_nodes_disconnect_timeout" set To 30 seconds
@@ -552,7 +552,7 @@
$ repmgr cluster event --event=child_node_disconnect $ repmgr cluster event --event=child_node_disconnect
Node ID | Name | Event | OK | Timestamp | Details Node ID | Name | Event | OK | Timestamp | Details
---------+-------+-----------------------+----+---------------------+-------------------------------------------- ---------+-------+-----------------------+----+---------------------+--------------------------------------------
1 | node1 | child_node_disconnect | t | 2019-04-24 12:41:36 | node "node3" (node ID: 3) has disconnected</programlisting> 1 | node1 | child_node_disconnect | t | 2019-04-24 12:41:36 | node "node3" (ID: 3) has disconnected</programlisting>
</para> </para>
</listitem> </listitem>
</varlistentry> </varlistentry>
@@ -574,7 +574,7 @@ $ repmgr cluster event --event=child_node_disconnect
$ repmgr cluster event --event=child_node_reconnect $ repmgr cluster event --event=child_node_reconnect
Node ID | Name | Event | OK | Timestamp | Details Node ID | Name | Event | OK | Timestamp | Details
---------+-------+----------------------+----+---------------------+------------------------------------------------------------ ---------+-------+----------------------+----+---------------------+------------------------------------------------------------
1 | node1 | child_node_reconnect | t | 2019-04-24 12:42:19 | node "node3" (node ID: 3) has reconnected after 42 seconds</programlisting> 1 | node1 | child_node_reconnect | t | 2019-04-24 12:42:19 | node "node3" (ID: 3) has reconnected after 42 seconds</programlisting>
</para> </para>
</listitem> </listitem>
</varlistentry> </varlistentry>
@@ -597,7 +597,7 @@ $ repmgr cluster event --event=child_node_reconnect
$ repmgr cluster event --event=child_node_new_connect $ repmgr cluster event --event=child_node_new_connect
Node ID | Name | Event | OK | Timestamp | Details Node ID | Name | Event | OK | Timestamp | Details
---------+-------+------------------------+----+---------------------+--------------------------------------------- ---------+-------+------------------------+----+---------------------+---------------------------------------------
1 | node1 | child_node_new_connect | t | 2019-04-24 12:41:30 | new node "node3" (node ID: 3) has connected</programlisting> 1 | node1 | child_node_new_connect | t | 2019-04-24 12:41:30 | new node "node3" (ID: 3) has connected</programlisting>
</para> </para>
</listitem> </listitem>
</varlistentry> </varlistentry>
@@ -725,7 +725,7 @@ Node ID: 2
[2019-03-13 21:01:30] [NOTICE] failover validation command returned a non-zero value: "1" [2019-03-13 21:01:30] [NOTICE] failover validation command returned a non-zero value: "1"
[2019-03-13 21:01:30] [NOTICE] promotion candidate election will be rerun [2019-03-13 21:01:30] [NOTICE] promotion candidate election will be rerun
[2019-03-13 21:01:30] [INFO] 1 followers to notify [2019-03-13 21:01:30] [INFO] 1 followers to notify
[2019-03-13 21:01:30] [NOTICE] notifying node "node3" (node ID: 3) to rerun promotion candidate selection [2019-03-13 21:01:30] [NOTICE] notifying node "node3" (ID: 3) to rerun promotion candidate selection
INFO: node 3 received notification to rerun promotion candidate election INFO: node 3 received notification to rerun promotion candidate election
[2019-03-13 21:01:30] [NOTICE] rerunning election after 15 seconds ("election_rerun_interval")</programlisting> [2019-03-13 21:01:30] [NOTICE] rerunning election after 15 seconds ("election_rerun_interval")</programlisting>
</para> </para>

14
doc/repmgrd-operation.sgml
View File

@@ -117,7 +117,7 @@ NOTICE: node 3 (node3) paused</programlisting>
If the primary (in this example, <literal>node1</literal>) is stopped, <application>repmgrd</application> If the primary (in this example, <literal>node1</literal>) is stopped, <application>repmgrd</application>
running on one of the standbys (here: <literal>node2</literal>) will react like this: running on one of the standbys (here: <literal>node2</literal>) will react like this:
<programlisting> <programlisting>
[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (node ID: 1) [2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (ID: 1)
[2018-09-20 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts [2018-09-20 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts
[2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt [2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
... ...
@@ -125,7 +125,7 @@ NOTICE: node 3 (node3) paused</programlisting>
[2018-09-20 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts [2018-09-20 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts
[2018-09-20 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts [2018-09-20 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
[2018-09-20 12:22:25] [NOTICE] node is paused [2018-09-20 12:22:25] [NOTICE] node is paused
[2018-09-20 12:22:33] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state [2018-09-20 12:22:33] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state
[2018-09-20 12:22:33] [DETAIL] repmgrd paused by administrator [2018-09-20 12:22:33] [DETAIL] repmgrd paused by administrator
[2018-09-20 12:22:33] [HINT] execute "repmgr daemon unpause" to resume normal failover mode</programlisting> [2018-09-20 12:22:33] [HINT] execute "repmgr daemon unpause" to resume normal failover mode</programlisting>
</para> </para>
@@ -268,8 +268,8 @@ NOTICE: node 3 (node3) unpaused</programlisting>
Example output in a situation where there is only one standby with <literal>failover=manual</literal>, Example output in a situation where there is only one standby with <literal>failover=manual</literal>,
and the primary node is unavailable (but is later restarted): and the primary node is unavailable (but is later restarted):
<programlisting> <programlisting>
[2017-08-29 10:59:19] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in normal state (automatic failover disabled) [2017-08-29 10:59:19] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in normal state (automatic failover disabled)
[2017-08-29 10:59:33] [WARNING] unable to connect to upstream node "node1" (node ID: 1) [2017-08-29 10:59:33] [WARNING] unable to connect to upstream node "node1" (ID: 1)
[2017-08-29 10:59:33] [INFO] checking state of node 1, 1 of 5 attempts [2017-08-29 10:59:33] [INFO] checking state of node 1, 1 of 5 attempts
[2017-08-29 10:59:33] [INFO] sleeping 1 seconds until next reconnection attempt [2017-08-29 10:59:33] [INFO] sleeping 1 seconds until next reconnection attempt
(...) (...)
@@ -278,10 +278,10 @@ NOTICE: node 3 (node3) unpaused</programlisting>
[2017-08-29 10:59:37] [NOTICE] this node is not configured for automatic failover so will not be considered as promotion candidate [2017-08-29 10:59:37] [NOTICE] this node is not configured for automatic failover so will not be considered as promotion candidate
[2017-08-29 10:59:37] [NOTICE] no other nodes are available as promotion candidate [2017-08-29 10:59:37] [NOTICE] no other nodes are available as promotion candidate
[2017-08-29 10:59:37] [HINT] use "repmgr standby promote" to manually promote this node [2017-08-29 10:59:37] [HINT] use "repmgr standby promote" to manually promote this node
[2017-08-29 10:59:37] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state (automatic failover disabled) [2017-08-29 10:59:37] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
[2017-08-29 10:59:53] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state (automatic failover disabled) [2017-08-29 10:59:53] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
[2017-08-29 11:00:45] [NOTICE] reconnected to upstream node 1 after 68 seconds, resuming monitoring [2017-08-29 11:00:45] [NOTICE] reconnected to upstream node 1 after 68 seconds, resuming monitoring
[2017-08-29 11:00:57] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in normal state (automatic failover disabled)</programlisting> [2017-08-29 11:00:57] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in normal state (automatic failover disabled)</programlisting>
</para> </para>
<para> <para>

20
doc/repmgrd-overview.sgml
View File

@@ -104,17 +104,17 @@
[2019-03-15 06:32:05] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr connect_timeout=2" [2019-03-15 06:32:05] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr connect_timeout=2"
INFO: set_repmgrd_pid(): provided pidfile is /var/run/repmgr/repmgrd-11.pid INFO: set_repmgrd_pid(): provided pidfile is /var/run/repmgr/repmgrd-11.pid
[2019-03-15 06:32:05] [NOTICE] starting monitoring of node "node2" (ID: 2) [2019-03-15 06:32:05] [NOTICE] starting monitoring of node "node2" (ID: 2)
[2019-03-15 06:32:05] [INFO] monitoring connection to upstream node "node1" (node ID: 1)</programlisting> [2019-03-15 06:32:05] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
</para> </para>
<para> <para>
Each <application>repmgrd</application> should also have recorded its successful startup as an event: Each <application>repmgrd</application> should also have recorded its successful startup as an event:
<programlisting> <programlisting>
$ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
Node ID | Name | Event | OK | Timestamp | Details Node ID | Name | Event | OK | Timestamp | Details
---------+-------+---------------+----+---------------------+------------------------------------------------------------- ---------+-------+---------------+----+---------------------+--------------------------------------------------------
3 | node3 | repmgrd_start | t | 2019-03-14 04:17:30 | monitoring connection to upstream node "node1" (node ID: 1) 3 | node3 | repmgrd_start | t | 2019-03-14 04:17:30 | monitoring connection to upstream node "node1" (ID: 1)
2 | node2 | repmgrd_start | t | 2019-03-14 04:11:47 | monitoring connection to upstream node "node1" (node ID: 1) 2 | node2 | repmgrd_start | t | 2019-03-14 04:11:47 | monitoring connection to upstream node "node1" (ID: 1)
1 | node1 | repmgrd_start | t | 2019-03-14 04:04:31 | monitoring cluster primary "node1" (node ID: 1)</programlisting> 1 | node1 | repmgrd_start | t | 2019-03-14 04:04:31 | monitoring cluster primary "node1" (ID: 1)</programlisting>
</para> </para>
<para> <para>
Now stop the current primary server with e.g.: Now stop the current primary server with e.g.:
@@ -128,7 +128,7 @@
decision is made. This is an extract from the log of a standby server (<literal>node2</literal>) decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
which has promoted to new primary after failure of the original primary (<literal>node1</literal>). which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
<programlisting> <programlisting>
[2019-03-15 06:37:50] [WARNING] unable to connect to upstream node "node1" (node ID: 1) [2019-03-15 06:37:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
[2019-03-15 06:37:50] [INFO] checking state of node 1, 1 of 3 attempts [2019-03-15 06:37:50] [INFO] checking state of node 1, 1 of 3 attempts
[2019-03-15 06:37:50] [INFO] sleeping 5 seconds until next reconnection attempt [2019-03-15 06:37:50] [INFO] sleeping 5 seconds until next reconnection attempt
[2019-03-15 06:37:55] [INFO] checking state of node 1, 2 of 3 attempts [2019-03-15 06:37:55] [INFO] checking state of node 1, 2 of 3 attempts
@@ -151,10 +151,10 @@
NOTICE: STANDBY PROMOTE successful NOTICE: STANDBY PROMOTE successful
DETAIL: server "node2" (ID: 2) was successfully promoted to primary DETAIL: server "node2" (ID: 2) was successfully promoted to primary
[2019-03-15 06:38:01] [INFO] 3 followers to notify [2019-03-15 06:38:01] [INFO] 3 followers to notify
[2019-03-15 06:38:01] [NOTICE] notifying node "node3" (node ID: 3) to follow node 2 [2019-03-15 06:38:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
INFO: node 3 received notification to follow node 2 INFO: node 3 received notification to follow node 2
[2019-03-15 06:38:01] [INFO] switching to primary monitoring mode [2019-03-15 06:38:01] [INFO] switching to primary monitoring mode
[2019-03-15 06:38:01] [NOTICE] monitoring cluster primary "node2" (node ID: 2)</programlisting> [2019-03-15 06:38:01] [NOTICE] monitoring cluster primary "node2" (ID: 2)</programlisting>
</para> </para>
<para> <para>
The cluster status will now look like this, with the original primary (<literal>node1</literal>) The cluster status will now look like this, with the original primary (<literal>node1</literal>)
@@ -177,8 +177,8 @@
Node ID | Name | Event | OK | Timestamp | Details Node ID | Name | Event | OK | Timestamp | Details
---------+-------+----------------------------+----+---------------------+------------------------------------------------------------- ---------+-------+----------------------------+----+---------------------+-------------------------------------------------------------
3 | node3 | repmgrd_failover_follow | t | 2019-03-15 06:38:03 | node 3 now following new upstream node 2 3 | node3 | repmgrd_failover_follow | t | 2019-03-15 06:38:03 | node 3 now following new upstream node 2
3 | node3 | standby_follow | t | 2019-03-15 06:38:02 | standby attached to upstream node "node2" (node ID: 2) 3 | node3 | standby_follow | t | 2019-03-15 06:38:02 | standby attached to upstream node "node2" (ID: 2)
2 | node2 | repmgrd_reload | t | 2019-03-15 06:38:01 | monitoring cluster primary "node2" (node ID: 2) 2 | node2 | repmgrd_reload | t | 2019-03-15 06:38:01 | monitoring cluster primary "node2" (ID: 2)
2 | node2 | repmgrd_failover_promote | t | 2019-03-15 06:38:01 | node 2 promoted to primary; old primary 1 marked as failed 2 | node2 | repmgrd_failover_promote | t | 2019-03-15 06:38:01 | node 2 promoted to primary; old primary 1 marked as failed
2 | node2 | standby_promote | t | 2019-03-15 06:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting> 2 | node2 | standby_promote | t | 2019-03-15 06:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
</para> </para>

2
repmgr-action-node.c
View File

@@ -2222,7 +2222,7 @@ do_node_rejoin(void)
{ {
RecoveryType upstream_recovery_type = get_recovery_type(upstream_conn); RecoveryType upstream_recovery_type = get_recovery_type(upstream_conn);
log_error(_("unable to connect to current registered primary \"%s\" (node ID: %i)"), log_error(_("unable to connect to current registered primary \"%s\" (ID: %i)"),
primary_node_record.node_name, primary_node_record.node_name,
primary_node_record.node_id); primary_node_record.node_id);
log_detail(_("registered primary node conninfo is: \"%s\""), log_detail(_("registered primary node conninfo is: \"%s\""),

8
repmgr-action-primary.c
View File

@@ -113,7 +113,7 @@ do_primary_register(void)
{ {
if (get_recovery_type(primary_conn) == RECTYPE_PRIMARY) if (get_recovery_type(primary_conn) == RECTYPE_PRIMARY)
{ {
log_error(_("there is already an active registered primary (node ID: %i) in this cluster"), log_error(_("there is already an active registered primary (ID: %i) in this cluster"),
current_primary_id); current_primary_id);
log_detail(_("a streaming replication cluster can have only one primary node")); log_detail(_("a streaming replication cluster can have only one primary node"));
@@ -223,12 +223,12 @@ do_primary_register(void)
if (record_status == RECORD_FOUND) if (record_status == RECORD_FOUND)
{ {
log_notice(_("primary node record (id: %i) updated"), log_notice(_("primary node record (ID: %i) updated"),
config_file_options.node_id); config_file_options.node_id);
} }
else else
{ {
log_notice(_("primary node record (id: %i) registered"), log_notice(_("primary node record (ID: %i) registered"),
config_file_options.node_id); config_file_options.node_id);
} }
@@ -357,7 +357,7 @@ do_primary_unregister(void)
for (cell = downstream_nodes.head; cell; cell = cell->next) for (cell = downstream_nodes.head; cell; cell = cell->next)
{ {
appendPQExpBuffer(&detail, appendPQExpBuffer(&detail,
" %s (id: %i)\n", " %s (ID: %i)\n",
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
} }

14
repmgr-action-standby.c
View File

@@ -1902,7 +1902,7 @@ do_standby_register(void)
PQfinish(conn); PQfinish(conn);
log_info(_("standby registration complete")); log_info(_("standby registration complete"));
log_notice(_("standby node \"%s\" (id: %i) successfully registered"), log_notice(_("standby node \"%s\" (ID: %i) successfully registered"),
config_file_options.node_name, config_file_options.node_id); config_file_options.node_name, config_file_options.node_id);
return; return;
} }
@@ -2120,7 +2120,7 @@ do_standby_promote(void)
get_node_record(conn, existing_primary_id, &primary_rec); get_node_record(conn, existing_primary_id, &primary_rec);
log_detail(_("current primary is %s (node_id: %i)"), log_detail(_("current primary is \"%s\" (ID: %i)"),
primary_rec.node_name, primary_rec.node_name,
existing_primary_id); existing_primary_id);
} }
@@ -2754,7 +2754,7 @@ do_standby_follow(void)
{ {
log_notice(_("STANDBY FOLLOW successful")); log_notice(_("STANDBY FOLLOW successful"));
appendPQExpBuffer(&follow_output, appendPQExpBuffer(&follow_output,
"standby attached to upstream node \"%s\" (node ID: %i)", "standby attached to upstream node \"%s\" (ID: %i)",
follow_target_node_record.node_name, follow_target_node_record.node_name,
follow_target_node_id); follow_target_node_id);
} }
@@ -2762,7 +2762,7 @@ do_standby_follow(void)
{ {
log_error(_("STANDBY FOLLOW failed")); log_error(_("STANDBY FOLLOW failed"));
appendPQExpBuffer(&follow_output, appendPQExpBuffer(&follow_output,
"standby did not attach to upstream node \"%s\" (node ID: %i) after %i seconds", "standby did not attach to upstream node \"%s\" (ID: %i) after %i seconds",
follow_target_node_record.node_name, follow_target_node_record.node_name,
follow_target_node_id, follow_target_node_id,
config_file_options.standby_follow_timeout); config_file_options.standby_follow_timeout);
@@ -3608,7 +3608,7 @@ do_standby_switchover(void)
for (cell = sibling_nodes.head; cell; cell = cell->next) for (cell = sibling_nodes.head; cell; cell = cell->next)
{ {
appendPQExpBuffer(&nodes, appendPQExpBuffer(&nodes,
" %s (node ID: %i)", " %s (ID: %i)",
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
if (cell->next) if (cell->next)
@@ -3683,7 +3683,7 @@ do_standby_switchover(void)
{ {
if (cell->node_info->reachable == true) if (cell->node_info->reachable == true)
continue; continue;
log_detail(" %s (ID: %i)", log_detail(" \"%s\" (ID: %i)",
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
} }
@@ -5130,7 +5130,7 @@ check_source_server()
if (record_status == RECORD_FOUND && node_record.node_id != config_file_options.node_id) if (record_status == RECORD_FOUND && node_record.node_id != config_file_options.node_id)
{ {
log_error(_("another node (node_id: %i) already exists with node_name \"%s\""), log_error(_("another node (ID: %i) already exists with node_name \"%s\""),
node_record.node_id, node_record.node_id,
config_file_options.node_name); config_file_options.node_name);
PQfinish(source_conn); PQfinish(source_conn);

66
repmgrd-physical.c
View File

@@ -268,7 +268,7 @@ monitor_streaming_primary(void)
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("monitoring cluster primary \"%s\" (node ID: %i)"), _("monitoring cluster primary \"%s\" (ID: %i)"),
local_node_info.node_name, local_node_info.node_name,
local_node_info.node_id); local_node_info.node_id);
@@ -335,13 +335,13 @@ monitor_streaming_primary(void)
if (cell->node_info->attached == NODE_ATTACHED) if (cell->node_info->attached == NODE_ATTACHED)
{ {
log_info(_("child node \"%s\" (node ID: %i) is attached"), log_info(_("child node \"%s\" (ID: %i) is attached"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
} }
else else
{ {
log_info(_("child node \"%s\" (node ID: %i) is not yet attached"), log_info(_("child node \"%s\" (ID: %i) is not yet attached"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
} }
@@ -536,7 +536,7 @@ loop:
if (log_status_interval_elapsed >= config_file_options.log_status_interval) if (log_status_interval_elapsed >= config_file_options.log_status_interval)
{ {
log_info(_("monitoring primary node \"%s\" (node ID: %i) in %s state"), log_info(_("monitoring primary node \"%s\" (ID: %i) in %s state"),
local_node_info.node_name, local_node_info.node_name,
local_node_info.node_id, local_node_info.node_id,
print_monitoring_state(monitoring_state)); print_monitoring_state(monitoring_state));
@@ -660,7 +660,7 @@ check_primary_status(int degraded_monitoring_elapsed)
return true; return true;
} }
log_debug("primary node id is now %i", primary_node_id); log_debug("primary node ID is now %i", primary_node_id);
record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info); record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info);
@@ -907,7 +907,7 @@ check_primary_child_nodes(t_child_node_info_list *local_child_nodes)
if (db_node_rec_found == false) if (db_node_rec_found == false)
{ {
log_notice(_("child node \"%s\" (node id %i) is no longer connected or registered"), log_notice(_("child node \"%s\" (ID: %i) is no longer connected or registered"),
local_child_node_rec->node_name, local_child_node_rec->node_name,
local_child_node_rec->node_id); local_child_node_rec->node_id);
remove_child_node_record(local_child_nodes, local_child_node_rec->node_id); remove_child_node_record(local_child_nodes, local_child_node_rec->node_id);
@@ -924,7 +924,7 @@ check_primary_child_nodes(t_child_node_info_list *local_child_nodes)
PQExpBufferData event_details; PQExpBufferData event_details;
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("node \"%s\" (node ID: %i) has disconnected"), _("node \"%s\" (ID: %i) has disconnected"),
child_node_rec->node_name, child_node_rec->node_name,
child_node_rec->node_id); child_node_rec->node_id);
log_notice("%s", event_details.data); log_notice("%s", event_details.data);
@@ -949,7 +949,7 @@ check_primary_child_nodes(t_child_node_info_list *local_child_nodes)
PQExpBufferData event_details; PQExpBufferData event_details;
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("node \"%s\" (node ID: %i) has reconnected after %i seconds"), _("node \"%s\" (ID: %i) has reconnected after %i seconds"),
child_node_rec->node_name, child_node_rec->node_name,
child_node_rec->node_id, child_node_rec->node_id,
calculate_elapsed( child_node_rec->detached_time )); calculate_elapsed( child_node_rec->detached_time ));
@@ -975,7 +975,7 @@ check_primary_child_nodes(t_child_node_info_list *local_child_nodes)
PQExpBufferData event_details; PQExpBufferData event_details;
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("new node \"%s\" (node ID: %i) has connected"), _("new node \"%s\" (ID: %i) has connected"),
child_node_rec->node_name, child_node_rec->node_name,
child_node_rec->node_id); child_node_rec->node_id);
log_notice("%s", event_details.data); log_notice("%s", event_details.data);
@@ -1356,7 +1356,7 @@ monitor_streaming_standby(void)
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("monitoring connection to upstream node \"%s\" (node ID: %i)"), _("monitoring connection to upstream node \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_name,
upstream_node_info.node_id); upstream_node_info.node_id);
@@ -1402,7 +1402,7 @@ monitor_streaming_standby(void)
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("unable to connect to upstream node \"%s\" (node ID: %i)"), _("unable to connect to upstream node \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
/* TODO: possibly add pre-action event here */ /* TODO: possibly add pre-action event here */
@@ -1469,7 +1469,7 @@ monitor_streaming_standby(void)
*/ */
termPQExpBuffer(&event_details); termPQExpBuffer(&event_details);
log_notice(_("current upstream node \"%s\" (node ID: %i) is not primary, restarting monitoring"), log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
PQfinish(upstream_conn); PQfinish(upstream_conn);
upstream_conn = NULL; upstream_conn = NULL;
@@ -1803,7 +1803,7 @@ loop:
initPQExpBuffer(&monitoring_summary); initPQExpBuffer(&monitoring_summary);
appendPQExpBuffer(&monitoring_summary, appendPQExpBuffer(&monitoring_summary,
_("node \"%s\" (node ID: %i) monitoring upstream node \"%s\" (node ID: %i) in %s state"), _("node \"%s\" (ID: %i) monitoring upstream node \"%s\" (ID: %i) in %s state"),
local_node_info.node_name, local_node_info.node_name,
local_node_info.node_id, local_node_info.node_id,
upstream_node_info.node_name, upstream_node_info.node_name,
@@ -1984,7 +1984,7 @@ loop:
{ {
if (get_recovery_type(primary_conn) == RECTYPE_STANDBY) if (get_recovery_type(primary_conn) == RECTYPE_STANDBY)
{ {
log_notice(_("current upstream node \"%s\" (node ID: %i) is not primary, restarting monitoring"), log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
PQfinish(primary_conn); PQfinish(primary_conn);
primary_conn = NULL; primary_conn = NULL;
@@ -2113,7 +2113,7 @@ monitor_streaming_witness(void)
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("witness monitoring connection to primary node \"%s\" (node ID: %i)"), _("witness monitoring connection to primary node \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_name,
upstream_node_info.node_id); upstream_node_info.node_id);
@@ -2194,7 +2194,7 @@ monitor_streaming_witness(void)
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("unable to connect to primary node \"%s\" (node ID: %i)"), _("unable to connect to primary node \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
create_event_record(NULL, create_event_record(NULL,
@@ -2224,7 +2224,7 @@ monitor_streaming_witness(void)
/* check upstream is still primary */ /* check upstream is still primary */
if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY) if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY)
{ {
log_notice(_("current upstream node \"%s\" (node ID: %i) is not primary, restarting monitoring"), log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
PQfinish(primary_conn); PQfinish(primary_conn);
primary_conn = NULL; primary_conn = NULL;
@@ -2297,7 +2297,7 @@ monitor_streaming_witness(void)
/* check upstream is still primary */ /* check upstream is still primary */
if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY) if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY)
{ {
log_notice(_("current upstream node \"%s\" (node ID: %i) is not primary, restarting monitoring"), log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
PQfinish(primary_conn); PQfinish(primary_conn);
primary_conn = NULL; primary_conn = NULL;
@@ -2489,7 +2489,7 @@ loop:
{ {
if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY) if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY)
{ {
log_notice(_("current upstream node \"%s\" (node ID: %i) is not primary, restarting monitoring"), log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
PQfinish(primary_conn); PQfinish(primary_conn);
primary_conn = NULL; primary_conn = NULL;
@@ -2515,7 +2515,7 @@ loop:
initPQExpBuffer(&monitoring_summary); initPQExpBuffer(&monitoring_summary);
appendPQExpBuffer(&monitoring_summary, appendPQExpBuffer(&monitoring_summary,
_("witness node \"%s\" (node ID: %i) monitoring primary node \"%s\" (node ID: %i) in %s state"), _("witness node \"%s\" (ID: %i) monitoring primary node \"%s\" (ID: %i) in %s state"),
local_node_info.node_name, local_node_info.node_name,
local_node_info.node_id, local_node_info.node_id,
upstream_node_info.node_name, upstream_node_info.node_name,
@@ -2862,7 +2862,7 @@ do_primary_failover(void)
/* pass control back down to start_monitoring() */ /* pass control back down to start_monitoring() */
log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type));
log_detail(_("original primary \"%s\" (node ID: %i) reappeared"), log_detail(_("original primary \"%s\" (ID: %i) reappeared"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;
@@ -2872,7 +2872,7 @@ do_primary_failover(void)
case FAILOVER_STATE_FOLLOWED_NEW_PRIMARY: case FAILOVER_STATE_FOLLOWED_NEW_PRIMARY:
log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type));
log_detail(_("following new primary \"%s\" (node id: %i)"), log_detail(_("following new primary \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;
@@ -2881,7 +2881,7 @@ do_primary_failover(void)
case FAILOVER_STATE_FOLLOWING_ORIGINAL_PRIMARY: case FAILOVER_STATE_FOLLOWING_ORIGINAL_PRIMARY:
log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"), get_node_type_string(local_node_info.type));
log_detail(_("following original primary \"%s\" (node id: %i)"), log_detail(_("following original primary \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;
@@ -3355,12 +3355,12 @@ promote_self(void)
{ {
PQExpBufferData event_details; PQExpBufferData event_details;
log_notice(_("original primary (id: %i) reappeared before this standby was promoted - no action taken"), log_notice(_("original primary (ID: %i) reappeared before this standby was promoted - no action taken"),
failed_primary.node_id); failed_primary.node_id);
initPQExpBuffer(&event_details); initPQExpBuffer(&event_details);
appendPQExpBuffer(&event_details, appendPQExpBuffer(&event_details,
_("original primary \"%s\" (node ID: %i) reappeared"), _("original primary \"%s\" (ID: %i) reappeared"),
failed_primary.node_name, failed_primary.node_name,
failed_primary.node_id); failed_primary.node_id);
@@ -3449,7 +3449,7 @@ notify_followers(NodeInfoList *standby_nodes, int follow_node_id)
if (PQstatus(cell->node_info->conn) != CONNECTION_OK) if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
{ {
log_info(_("reconnecting to node \"%s\" (node ID: %i)..."), log_info(_("reconnecting to node \"%s\" (ID: %i)..."),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
@@ -3458,7 +3458,7 @@ notify_followers(NodeInfoList *standby_nodes, int follow_node_id)
if (PQstatus(cell->node_info->conn) != CONNECTION_OK) if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
{ {
log_warning(_("unable to reconnect to \"%s\" (node ID: %i)"), log_warning(_("unable to reconnect to \"%s\" (ID: %i)"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
log_detail("\n%s", PQerrorMessage(cell->node_info->conn)); log_detail("\n%s", PQerrorMessage(cell->node_info->conn));
@@ -3468,13 +3468,13 @@ notify_followers(NodeInfoList *standby_nodes, int follow_node_id)
if (follow_node_id == ELECTION_RERUN_NOTIFICATION) if (follow_node_id == ELECTION_RERUN_NOTIFICATION)
{ {
log_notice(_("notifying node \"%s\" (node ID: %i) to rerun promotion candidate selection"), log_notice(_("notifying node \"%s\" (ID: %i) to rerun promotion candidate selection"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
} }
else else
{ {
log_notice(_("notifying node \"%s\" (node ID: %i) to follow node %i"), log_notice(_("notifying node \"%s\" (ID: %i) to follow node %i"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id, cell->node_info->node_id,
follow_node_id); follow_node_id);
@@ -4031,7 +4031,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
{ {
ReplInfo sibling_replication_info; ReplInfo sibling_replication_info;
log_info(_("checking state of sibling node \"%s\" (node ID: %i)"), log_info(_("checking state of sibling node \"%s\" (ID: %i)"),
cell->node_info->node_name, cell->node_info->node_name,
cell->node_info->node_id); cell->node_info->node_id);
@@ -4401,7 +4401,7 @@ bool do_witness_failover(void)
case FAILOVER_STATE_PRIMARY_REAPPEARED: case FAILOVER_STATE_PRIMARY_REAPPEARED:
/* pass control back down to start_monitoring() */ /* pass control back down to start_monitoring() */
log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type));
log_detail(_("original primary \"%s\" (node ID: %i) reappeared"), log_detail(_("original primary \"%s\" (ID: %i) reappeared"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;
@@ -4410,7 +4410,7 @@ bool do_witness_failover(void)
case FAILOVER_STATE_FOLLOWED_NEW_PRIMARY: case FAILOVER_STATE_FOLLOWED_NEW_PRIMARY:
log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type));
log_detail(_("following new primary \"%s\" (node id: %i)"), log_detail(_("following new primary \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;
@@ -4418,7 +4418,7 @@ bool do_witness_failover(void)
case FAILOVER_STATE_FOLLOWING_ORIGINAL_PRIMARY: case FAILOVER_STATE_FOLLOWING_ORIGINAL_PRIMARY:
log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type)); log_info(_("resuming %s monitoring mode"),get_node_type_string(local_node_info.type));
log_detail(_("following original primary \"%s\" (node id: %i)"), log_detail(_("following original primary \"%s\" (ID: %i)"),
upstream_node_info.node_name, upstream_node_info.node_id); upstream_node_info.node_name, upstream_node_info.node_id);
failover_state = FAILOVER_STATE_NONE; failover_state = FAILOVER_STATE_NONE;