Skip to content

fix for continues node restarts after fail #261

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dkim2020 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix for continues node restarts after fail #261

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 10 additions & 12 deletions src/pgsql/bin/functions/do_rewind
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,17 +6,14 @@ echo ">>> Rewinding to the latest state"
TRY_TO_FOLLOW_CLUSTER_MASTER=`PGCONNECT_TIMEOUT=$CHECK_PGCONNECT_TIMEOUT PGPASSWORD=$REPLICATION_PASSWORD psql -h $CURRENT_REPLICATION_PRIMARY_HOST -U $REPLICATION_USER -p $REPLICATION_PRIMARY_PORT $REPLICATION_DB -tAc "SELECT count(*) FROM $(get_repmgr_schema).$REPMGR_NODES_TABLE WHERE (type='primary' OR type='master') AND conninfo LIKE '%host=$CURRENT_REPLICATION_PRIMARY_HOST%'"`

if [[ "$MASTER_SLAVE_SWITCH" == "1" ]] || [ "$TRY_TO_FOLLOW_CLUSTER_MASTER" == "1" ]; then
echo ">>>>>> Archiving configs"
gosu postgres repmgr standby archive-config --config-archive-dir=/tmp/repmgr-archive

echo ">>>>>> Start server to be able to rewind (weird hack to avoid dirty shutdown issue)"
rm -rf $PGDATA/pg_xlog/archive_status/
rm $PGDATA/postmaster.pid
gosu postgres pg_ctl -D "$PGDATA" -o "-c listen_addresses='localhost'" -w start
gosu postgres pg_ctl -D "$PGDATA" -o "-c listen_addresses='localhost'" -w start

echo ">>>>>> Removing unactive replication slots of partners"
close_partners_slots

echo ">>>>>> Stop server"
gosu postgres pg_ctl stop

Expand All @@ -26,20 +23,21 @@ if [[ "$MASTER_SLAVE_SWITCH" == "1" ]] || [ "$TRY_TO_FOLLOW_CLUSTER_MASTER" == "
echo ">>>>>>>>> Creating $REPLICATION_SLOT"
PGCONNECT_TIMEOUT=$CHECK_PGCONNECT_TIMEOUT PGPASSWORD=$REPLICATION_PASSWORD psql -h $CURRENT_REPLICATION_PRIMARY_HOST -U $REPLICATION_USER -p $REPLICATION_PRIMARY_PORT $REPLICATION_DB -c "SELECT * FROM pg_create_physical_replication_slot('$REPLICATION_SLOT')"
fi
echo ">>>>>> Rewind to the host $CURRENT_REPLICATION_PRIMARY_HOST"
gosu postgres pg_rewind --source-server="user=$REPLICATION_USER password=$REPLICATION_PASSWORD host=$CURRENT_REPLICATION_PRIMARY_HOST dbname=$REPLICATION_DB port=$REPLICATION_PRIMARY_PORT connect_timeout=10" --target-pgdata=$PGDATA

echo ">>>>>> Restoring configs"
gosu postgres repmgr standby restore-config -D $PGDATA --config-archive-dir=/tmp/repmgr-archive
echo ">>>>>> Rejoin cluster. new primary: $CURRENT_REPLICATION_PRIMARY_HOST"
gosu postgres repmgr node rejoin -f $REPMGR_CONFIG_FILE --force-rewind --verbose --log-level DEBUG -h $CURRENT_REPLICATION_PRIMARY_HOST -p $REPLICATION_PRIMARY_PORT -d $REPLICATION_DB -U $REPLICATION_USER -D $PGDATA

echo ">>>>>> Starting server to register"
gosu postgres pg_ctl -D "$PGDATA" -o "-c listen_addresses='$CLUSTER_NODE_NETWORK_NAME'" -w start

echo ">>>>>> Register"
gosu postgres repmgr -f $REPMGR_CONFIG_FILE standby register --verbose
fi


if [ "$TRY_TO_FOLLOW_CLUSTER_MASTER" == "0" ]; then
echo ">>>>>> Repmgr can follow only main cluster master"
else
echo ">>>>>> Tell repmgr to follow upstream for the node"
gosu postgres repmgr -h $CURRENT_REPLICATION_PRIMARY_HOST -p $REPLICATION_PRIMARY_PORT -d $REPLICATION_DB -U $REPLICATION_USER -D $PGDATA standby follow -W --log-level DEBUG --verbose

echo ">>>>>> Stop server"
gosu postgres pg_ctl stop
fi
Expand Down