Postgres WAL 归档实现时间点恢复

#!/bin/sh
set -eu
umask 077
lab=$(mktemp -d /tmp/xbcatm-pitr.XXXXXX)
mkdir "$lab/socket" "$lab/archive"
primary=$lab/primary
restored=$lab/restored
missing=$lab/missing
cleanup() {
    for cluster in "$missing" "$restored" "$primary"; do
        if test -f "$cluster/postmaster.pid"; then
            pg_ctl -D "$cluster" -m fast -w stop >/dev/null
        fi
    done
}
trap cleanup EXIT
initdb -D "$primary" --no-locale --encoding=UTF8 --auth-local=trust --auth-host=reject >/dev/null
cat >> "$primary/postgresql.conf" <<CONF
listen_addresses = ''
unix_socket_directories = '$lab/socket'
port = 56432
wal_level = replica
archive_mode = on
archive_command = '$lab/archive-copy.sh "%p" "%f" "$lab/archive"'
CONF
cat > "$lab/archive-copy.sh" <<'ARCHIVE_HELPER'
#!/bin/sh
set -eu
wal_source=$1
wal_name=$2
archive_directory=$3
archive_target=$archive_directory/$wal_name
if test -e "$archive_target"; then
    cmp -s "$wal_source" "$archive_target"
    sync "$archive_target" "$archive_directory"
    exit 0
fi
archive_temporary=$(mktemp "$archive_directory/.incoming.XXXXXX")
trap 'rm -f "$archive_temporary"' EXIT HUP INT TERM
cp "$wal_source" "$archive_temporary"
sync "$archive_temporary"
ln "$archive_temporary" "$archive_target" || cmp -s "$wal_source" "$archive_target"
sync "$archive_target" "$archive_directory"
ARCHIVE_HELPER
chmod 700 "$lab/archive-copy.sh"
pg_ctl -D "$primary" -l "$lab/primary.log" -w -t 15 start >/dev/null
export PGHOST=$lab/socket PGPORT=56432 PGDATABASE=postgres PGUSER=$(id -un)
export PGCONNECT_TIMEOUT=2
psql -X -v ON_ERROR_STOP=1 -qAt <<'SQL'
CREATE TABLE marker (id integer PRIMARY KEY,value text);
INSERT INTO marker VALUES (1,'base');
SQL
pg_basebackup -D "$lab/base" -X stream -c fast -w
pg_verifybackup -q "$lab/base"
psql -X -v ON_ERROR_STOP=1 -qAt -c 'SELECT pg_switch_wal()' >/dev/null
psql -X -v ON_ERROR_STOP=1 -qAt <<'SQL'
INSERT INTO marker VALUES (2,'keep');
SELECT pg_create_restore_point('before_bad_change');
UPDATE marker SET value='bad' WHERE id=1;
DELETE FROM marker WHERE id=2;
SQL
segment=$(psql -X -v ON_ERROR_STOP=1 -qAt -c 'SELECT pg_walfile_name(pg_current_wal_lsn())')
psql -X -v ON_ERROR_STOP=1 -qAt -c 'SELECT pg_switch_wal()' >/dev/null
attempt=0
while ! test -f "$lab/archive/$segment"; do
    attempt=$((attempt+1))
    test "$attempt" -lt 100 || { echo 'archive segment did not arrive' >&2; exit 1; }
    sleep 0.1
done
printf 'primary_now '
psql -X -v ON_ERROR_STOP=1 -qAt -c "SELECT string_agg(id||':'||value,',' ORDER BY id) FROM marker"
mkdir "$restored"
cp -a "$lab/base/." "$restored/"
cat >> "$restored/postgresql.conf" <<CONF
port = 56433
archive_mode = off
restore_command = 'cp "$lab/archive/%f" "%p"'
recovery_target_name = 'before_bad_change'
recovery_target_action = 'pause'
CONF
touch "$restored/recovery.signal"
pg_ctl -D "$restored" -l "$lab/restored.log" -w -t 15 start >/dev/null
attempt=0
while test "$(PGPORT=56433 psql -X -v ON_ERROR_STOP=1 -qAt -c "SELECT pg_get_wal_replay_pause_state()='paused'")" != t; do
    attempt=$((attempt+1))
    test "$attempt" -lt 100 || { echo 'restore target was not reached' >&2; exit 1; }
    sleep 0.1
done
PGPORT=56433 psql -X -v ON_ERROR_STOP=1 -qAt <<'SQL'
SELECT pg_is_in_recovery(),pg_get_wal_replay_pause_state();
SELECT id,value FROM marker ORDER BY id;
DO $$ BEGIN
  IF (SELECT string_agg(id||':'||value,',' ORDER BY id) FROM marker)
     IS DISTINCT FROM '1:base,2:keep' THEN
    RAISE EXCEPTION 'point-in-time result mismatch';
  END IF;
END $$;
SQL
test ! -e "$lab/base/pg_wal/$segment"
mkdir "$lab/archive-missing" "$missing"
for archived_file in "$lab/archive/"*; do
    if test "${archived_file##*/}" != "$segment"; then
        cp "$archived_file" "$lab/archive-missing/"
    fi
done
cp -a "$lab/base/." "$missing/"
cat >> "$missing/postgresql.conf" <<CONF
port = 56434
archive_mode = off
restore_command = 'cp "$lab/archive-missing/%f" "%p"'
recovery_target_name = 'before_bad_change'
recovery_target_action = 'pause'
CONF
touch "$missing/recovery.signal"
if pg_ctl -D "$missing" -l "$lab/missing.log" -w -t 15 start >/dev/null 2>&1; then
    echo 'missing-segment server was briefly available'
fi
attempt=0
while pg_ctl -D "$missing" status >/dev/null 2>&1; do
    attempt=$((attempt+1))
    test "$attempt" -lt 100 || { echo 'missing-segment server did not stop' >&2; exit 1; }
    sleep 0.1
done
grep -F 'recovery ended before configured recovery target was reached' "$lab/missing.log"
test -f "$lab/archive/$segment"
echo missing_segment_target_unreachable
printf 'lab_directory %s\nrequired_segment %s\n' "$lab" "$segment"