MDEV-24097: galera[_3nodes] suite tests in MTR sporadically failsbb-10.3-julius

This commit contains a fix for instability when testing Galera
and when restarting nodes quickly:

1) Protection against a "stuck" old SST process during the execution
   of the new SST (after restarting the node) is now implemented for
   mariabackup / xtrabackup, which should help to avoid almost all
   conflicts due to the use of the same ports - both during testing
   with mtr, so and when restarting nodes quickly in a production
   environment.
2) Added more protection to scripts against unexpected return of
   the rc != 0 (in the commands for deleting temporary files, etc).
3) Added protection against unexpected crashes during binlog transfer
   (in SST scripts for rsync).
4) Spaces and some special characters in binlog filenames shouldn't
   be a problem now (at the script level).
5) Daemon process termination tracking has been made more robust
   against crashes due to unexpected termination of the previous SST
   process while new scripts are running.
6) Reading ssl encryption parameters has been moved from specific
   SST scripts to a common wsrep_sst_common.sh script, which allows
   unified error handling, unified diagnostics and simplifies script
   revisions in the future.
7) Improved diagnostics of errors related to the use of openssl.
8) Corrections have been made for xtrabackup-v2 (both in tests and in
   the script code) that restore the work of xtrabackup with updated
   versions of innodb.
9) Fixed some tests for galera_3nodes, although the complete solution
   for the problem of starting three nodes at the same time on fast
   machines will be done in a separate commit.

No additional tests are required as this commit fixes problems with
existing tests.

MDEV-24097: Additional test result correction

6 files changed, 214 insertions, 214 deletions

diff --git a/mysql-test/suite/galera/disabled.def b/mysql-test/suite/galera/disabled.def
index 955a2c82ebc..84babda2fa0 100644
--- a/mysql-test/suite/galera/disabled.def
+++ b/mysql-test/suite/galera/disabled.def
@@ -28,5 +28,3 @@ query_cache: MDEV-15805 Test failure on galera.query_cache
 versioning_trx_id: MDEV-18590: galera.versioning_trx_id: Test failure: mysqltest: Result content mismatch
 galera_wsrep_provider_unset_set: wsrep_provider is read-only for security reasons
 pxc-421: wsrep_provider is read-only for security reasons
-galera_sst_xtrabackup-v2: Test fails due to innodb issues
-galera_sst_xtrabackup-v2_data_dir: Test fails due to innodb issues
diff --git a/mysql-test/suite/galera_3nodes/r/galera_ist_gcache_rollover.result b/mysql-test/suite/galera_3nodes/r/galera_ist_gcache_rollover.result
index aa3e349eda7..996363a1ea8 100644
--- a/mysql-test/suite/galera_3nodes/r/galera_ist_gcache_rollover.result
+++ b/mysql-test/suite/galera_3nodes/r/galera_ist_gcache_rollover.result
@@ -6,10 +6,10 @@ CREATE TABLE t1 (f1 INTEGER PRIMARY KEY);
 INSERT INTO t1 VALUES (01), (02), (03), (04), (05);
 connection node_2;
 Unloading wsrep provider ...
-SET GLOBAL wsrep_provider = 'none';
+SET GLOBAL wsrep_cluster_address = '';
 connection node_3;
 Unloading wsrep provider ...
-SET GLOBAL wsrep_provider = 'none';
+SET GLOBAL wsrep_cluster_address = '';
 connection node_1;
 INSERT INTO t1 VALUES (11), (12), (13), (14), (15);
 INSERT INTO t1 VALUES (21), (22), (23), (24), (25);
diff --git a/mysql-test/suite/galera_3nodes/t/galera_ist_gcache_rollover.test b/mysql-test/suite/galera_3nodes/t/galera_ist_gcache_rollover.test
index 0032f8d6ee1..2719316fb84 100644
--- a/mysql-test/suite/galera_3nodes/t/galera_ist_gcache_rollover.test
+++ b/mysql-test/suite/galera_3nodes/t/galera_ist_gcache_rollover.test
@@ -29,9 +29,11 @@ INSERT INTO t1 VALUES (01), (02), (03), (04), (05);
 
 # Disconnect nodes #2 and #3
 --connection node_2
+--let $wsrep_cluster_address_orig2 = `select @@wsrep_cluster_address`
 --source suite/galera/include/galera_stop_replication.inc
 
 --connection node_3
+--let $wsrep_cluster_address_orig3 = `select @@wsrep_cluster_address`
 --source suite/galera/include/galera_stop_replication.inc
 
 --connection node_1
@@ -51,8 +53,8 @@ INSERT INTO t1 VALUES (21), (22), (23), (24), (25);
 # ... and restart providers to force IST
 --connection node_2
 --disable_query_log
---eval SET GLOBAL wsrep_provider = '$wsrep_provider_orig';
---eval SET GLOBAL wsrep_cluster_address = '$wsrep_cluster_address_orig';
+SET GLOBAL wsrep_cluster_address='';
+--eval SET GLOBAL wsrep_cluster_address = '$wsrep_cluster_address_orig2';
 --enable_query_log
 
 --connection node_1
@@ -60,8 +62,8 @@ INSERT INTO t1 VALUES (31), (32), (33), (34), (35);
 
 --connection node_3
 --disable_query_log
---eval SET GLOBAL wsrep_provider = '$wsrep_provider_orig';
---eval SET GLOBAL wsrep_cluster_address = '$wsrep_cluster_address_orig';
+SET GLOBAL wsrep_cluster_address='';
+--eval SET GLOBAL wsrep_cluster_address = '$wsrep_cluster_address_orig3';
 --enable_query_log
 
 --connection node_1
diff --git a/scripts/wsrep_sst_common.sh b/scripts/wsrep_sst_common.sh
index 040cd31caa9..deebe7cf820 100644
--- a/scripts/wsrep_sst_common.sh
+++ b/scripts/wsrep_sst_common.sh
@@ -17,7 +17,7 @@
 
 # This is a common command line parser to be sourced by other SST scripts
 
-set -u
+set -ue
 
 # Setting the path for some utilities on CentOS
 export PATH="$PATH:/usr/sbin:/usr/bin:/sbin:/bin"
@@ -879,9 +879,9 @@ fi
 
 wsrep_cleanup_progress_file()
 {
-    [ -n "$SST_PROGRESS_FILE" -a \
-      -f "$SST_PROGRESS_FILE" ] && \
-      rm -f "$SST_PROGRESS_FILE" 2>/dev/null || :
+    if [ -n "$SST_PROGRESS_FILE" -a -f "$SST_PROGRESS_FILE" ]; then
+        rm -f "$SST_PROGRESS_FILE" 2>/dev/null || :
+    fi
 }
 
 wsrep_check_program()
@@ -897,13 +897,10 @@ wsrep_check_program()
 wsrep_check_programs()
 {
     local ret=0
-
-    while [ $# -gt 0 ]
-    do
+    while [ $# -gt 0 ]; do
         wsrep_check_program "$1" || ret=$?
         shift
     done
-
     return $ret
 }
 
@@ -1028,11 +1025,11 @@ check_sockets_utils()
 #
 check_port()
 {
-    local pid="$1"
+    local pid="${1:-0}"
     local port="$2"
     local utils="$3"
 
-    [ -z "$pid" ] || [ $pid -eq 0 ] && pid='[0-9]+'
+    [ $pid -le 0 ] && pid='[0-9]+'
 
     local rc=1
 
@@ -1070,14 +1067,20 @@ check_for_dhparams()
     if [ ! -r "$ssl_dhparams" ]; then
         get_openssl
         if [ -n "$OPENSSL_BINARY" ]; then
-            wsrep_log_info "Could not find dhparams file, creating $ssl_dhparams"
-            if ! "$OPENSSL_BINARY" dhparam -out "$ssl_dhparams" 2048 >/dev/null 2>&1
-            then
+            wsrep_log_info \
+                "Could not find dhparams file, creating $ssl_dhparams"
+            local bug=0
+            local errmsg
+            errmsg=$("$OPENSSL_BINARY" \
+                         dhparam -out "$ssl_dhparams" 2048 2>&1) || bug=1
+            if [ $bug -ne 0 ]; then
+                wsrep_log_info "run: \"$OPENSSL_BINARY\" dhparam -out \"$ssl_dhparams\" 2048"
+                wsrep_log_info "output: $errmsg"
                 wsrep_log_error "******** ERROR *****************************************"
                 wsrep_log_error "* Could not create the dhparams.pem file with OpenSSL. *"
                 wsrep_log_error "********************************************************"
                 ssl_dhparams=""
-             fi
+            fi
         else
             # Rollback: if openssl is not installed, then use
             # the default parameters:
@@ -1099,17 +1102,9 @@ verify_ca_matches_cert()
     local ca="$2"
     local cap="$3"
 
-    # If the openssl utility is not installed, then
-    # we will not do this certificate check:
-    get_openssl
-    if [ -z "$OPENSSL_BINARY" ]; then
-        wsrep_log_info "openssl utility not found"
-        return
-    fi
-
     local readable=1; [ ! -r "$cert" ] && readable=0
-    [ -n "$ca"  ] &&  [ ! -r "$ca"   ] && readable=0
-    [ -n "$cap" ] &&  [ ! -r "$cap"  ] && readable=0
+         [ -n "$ca"  -a ! -r "$ca"   ] && readable=0
+         [ -n "$cap" -a ! -r "$cap"  ] && readable=0
 
     if [ $readable -eq 0 ]; then
         wsrep_log_error \
@@ -1117,12 +1112,20 @@ verify_ca_matches_cert()
         exit 22
     fi
 
+    # If the openssl utility is not installed, then
+    # we will not do this certificate check:
+    get_openssl
+    if [ -z "$OPENSSL_BINARY" ]; then
+        wsrep_log_info "openssl utility not found"
+        return
+    fi
+
     local not_match=0
     local errmsg
     errmsg=$("$OPENSSL_BINARY" verify -verbose \
-                               ${ca:+ -CAfile} ${ca:+ "$ca"} \
-                               ${cap:+ -CApath} ${cap:+ "$cap"} \
-                               "$cert" 2>&1) || not_match=1
+                 ${ca:+ -CAfile} ${ca:+ "$ca"} \
+                 ${cap:+ -CApath} ${cap:+ "$cap"} \
+                 "$cert" 2>&1) || not_match=1
 
     if [ $not_match -eq 1 ]; then
         wsrep_log_info "run: \"$OPENSSL_BINARY\" verify -verbose${ca:+ -CAfile \"$ca\"}${cap:+ -CApath \"$cap\"} \"$cert\""
@@ -1158,6 +1161,7 @@ verify_cert_matches_key()
     # If the diff utility is not installed, then
     # we will not do this certificate check:
     if [ -z "$(commandex diff)" ]; then
+        wsrep_log_info "diff utility not found"
         return
     fi
 
@@ -1165,6 +1169,7 @@ verify_cert_matches_key()
     # we will not do this certificate check:
     get_openssl
     if [ -z "$OPENSSL_BINARY" ]; then
+        wsrep_log_info "openssl utility not found"
         return
     fi
 
@@ -1253,18 +1258,18 @@ check_pid()
 {
     local pid_file="$1"
     if [ -r "$pid_file" ]; then
-        local pid=$(cat "$pid_file" 2>/dev/null)
+        local pid=$(cat "$pid_file" 2>/dev/null || :)
         if [ -n "$pid" ]; then
-            if [ $pid -ne 0 ]; then
-                if ps -p "$pid" >/dev/null 2>&1; then
+            if [ $pid -gt 0 ]; then
+                if ps -p $pid >/dev/null 2>&1; then
                     CHECK_PID=$pid
                     return 0
                 fi
             fi
         fi
         local remove=${2:-0}
-        if [ $remove -eq 1 ]; then
-            rm -f "$pid_file"
+        if [ $remove -ne 0 ]; then
+            rm -f "$pid_file" || :
         fi
     fi
     CHECK_PID=0
@@ -1289,25 +1294,25 @@ cleanup_pid()
     local pid_file="${2:-}"
     local config="${3:-}"
 
-    if [ $pid -ne 0 ]; then
+    if [ $pid -gt 0 ]; then
         if ps -p $pid >/dev/null 2>&1; then
             if kill $pid >/dev/null 2>&1; then
                 sleep 0.5
                 local round=0
                 local force=0
                 while ps -p $pid >/dev/null 2>&1; do
-                   sleep 1
-                   round=$(( round+1 ))
-                   if [ $round -eq 16 ]; then
-                       if [ $force -eq 0 ]; then
-                           round=8
-                           force=1
-                           kill -9 $pid >/dev/null 2>&1
-                           sleep 0.5
-                       else
-                           return 1
-                       fi
-                   fi
+                    sleep 1
+                    round=$(( round+1 ))
+                    if [ $round -eq 16 ]; then
+                        if [ $force -eq 0 ]; then
+                            round=8
+                            force=1
+                            kill -9 $pid >/dev/null 2>&1 || :
+                            sleep 0.5
+                        else
+                            return 1
+                        fi
+                    fi
                 done
             elif ps -p $pid >/dev/null 2>&1; then
                 wsrep_log_warning "Unable to kill PID=$pid ($pid_file)"
@@ -1316,8 +1321,8 @@ cleanup_pid()
         fi
     fi
 
-    [ -n "$pid_file" ] && [ -f "$pid_file" ] && rm -f "$pid_file"
-    [ -n "$config" ]   && [ -f "$config" ]   && rm -f "$config"
+    [ -n "$pid_file" -a -f "$pid_file" ] && rm -f "$pid_file" || :
+    [ -n "$config" -a -f "$config" ] && rm -f "$config" || :
 
     return 0
 }
@@ -1339,3 +1344,46 @@ get_proc()
         fi
     fi
 }
+
+check_server_ssl_config()
+{
+    # backward-compatible behavior:
+    tcert=$(parse_cnf 'sst' 'tca')
+    tcap=$(parse_cnf 'sst' 'tcapath')
+    tpem=$(parse_cnf 'sst' 'tcert')
+    tkey=$(parse_cnf 'sst' 'tkey')
+    # reading new ssl configuration options:
+    local tcert2=$(parse_cnf "$encgroups" 'ssl-ca')
+    local tcap2=$(parse_cnf "$encgroups" 'ssl-capath')
+    local tpem2=$(parse_cnf "$encgroups" 'ssl-cert')
+    local tkey2=$(parse_cnf "$encgroups" 'ssl-key')
+    # if there are no old options, then we take new ones:
+    if [ -z "$tcert" -a -z "$tcap" -a -z "$tpem" -a -z "$tkey" ]; then
+        tcert="$tcert2"
+        tcap="$tcap2"
+        tpem="$tpem2"
+        tkey="$tkey2"
+    # checking for presence of the new-style SSL configuration:
+    elif [ -n "$tcert2" -o -n "$tcap2" -o -n "$tpem2" -o -n "$tkey2" ]; then
+        if [ "$tcert" != "$tcert2" -o \
+             "$tcap"  != "$tcap2"  -o \
+             "$tpem"  != "$tpem2"  -o \
+             "$tkey"  != "$tkey2" ]
+        then
+            wsrep_log_info \
+               "new ssl configuration options (ssl-ca[path], ssl-cert" \
+               "and ssl-key) are ignored by SST due to presence" \
+               "of the tca[path], tcert and/or tkey in the [sst] section"
+        fi
+    fi
+    if [ -n "$tcert" ]; then
+        tcert=$(trim_string "$tcert")
+        if [ "${tcert%/}" != "$tcert" -o -d "$tcert" ]; then
+            tcap="$tcert"
+            tcert=""
+        fi
+    fi
+    if [ -n "$tcap" ]; then
+        tcap=$(trim_string "$tcap")
+    fi
+}
diff --git a/scripts/wsrep_sst_mariabackup.sh b/scripts/wsrep_sst_mariabackup.sh
index 4bca785fcad..aa9442b0601 100644
--- a/scripts/wsrep_sst_mariabackup.sh
+++ b/scripts/wsrep_sst_mariabackup.sh
@@ -30,7 +30,6 @@ eformat=""
 ekey=""
 ekeyfile=""
 encrypt=0
-ecode=0
 ssyslog=""
 ssystag=""
 BACKUP_PID=""
@@ -465,49 +464,6 @@ adjust_progress()
 
 encgroups='--mysqld|sst|xtrabackup'
 
-check_server_ssl_config()
-{
-    # backward-compatible behavior:
-    tcert=$(parse_cnf 'sst' 'tca')
-    tcap=$(parse_cnf 'sst' 'tcapath')
-    tpem=$(parse_cnf 'sst' 'tcert')
-    tkey=$(parse_cnf 'sst' 'tkey')
-    # reading new ssl configuration options:
-    local tcert2=$(parse_cnf "$encgroups" 'ssl-ca')
-    local tcap2=$(parse_cnf "$encgroups" 'ssl-capath')
-    local tpem2=$(parse_cnf "$encgroups" 'ssl-cert')
-    local tkey2=$(parse_cnf "$encgroups" 'ssl-key')
-    # if there are no old options, then we take new ones:
-    if [ -z "$tcert" -a -z "$tcap" -a -z "$tpem" -a -z "$tkey" ]; then
-        tcert="$tcert2"
-        tcap="$tcap2"
-        tpem="$tpem2"
-        tkey="$tkey2"
-    # checking for presence of the new-style SSL configuration:
-    elif [ -n "$tcert2" -o -n "$tcap2" -o -n "$tpem2" -o -n "$tkey2" ]; then
-        if [ "$tcert" != "$tcert2" -o \
-             "$tcap"  != "$tcap2"  -o \
-             "$tpem"  != "$tpem2"  -o \
-             "$tkey"  != "$tkey2" ]
-        then
-            wsrep_log_info \
-               "new ssl configuration options (ssl-ca[path], ssl-cert" \
-               "and ssl-key) are ignored by SST due to presence" \
-               "of the tca[path], tcert and/or tkey in the [sst] section"
-        fi
-    fi
-    if [ -n "$tcert" ]; then
-        tcert=$(trim_string "$tcert")
-        if [ "${tcert%/}" != "$tcert" ] || [ -d "$tcert" ]; then
-            tcap="$tcert"
-            tcert=""
-        fi
-    fi
-    if [ -n "$tcap" ]; then
-        tcap=$(trim_string "$tcap")
-    fi
-}
-
 read_cnf()
 {
     sfmt=$(parse_cnf sst streamfmt 'mbstream')
@@ -647,7 +603,7 @@ cleanup_at_exit()
                 cleanup_pid $CHECK_PID "$BACKUP_PID"
             fi
         fi
-        [ -f "$DATA/$IST_FILE" ] && rm -f "$DATA/$IST_FILE"
+        [ -f "$DATA/$IST_FILE" ] && rm -f "$DATA/$IST_FILE" || :
     fi
 
     if [ -n "$progress" -a -p "$progress" ]; then
@@ -658,27 +614,31 @@ cleanup_at_exit()
     wsrep_log_info "Cleaning up temporary directories"
 
     if [ "$WSREP_SST_OPT_ROLE" = 'joiner' ]; then
-        if [ -n "$STATDIR" ]; then
-           [ -d "$STATDIR" ] && rm -rf "$STATDIR"
-        fi
+        [ -n "$STATDIR" -a -d "$STATDIR" ] && rm -rf "$STATDIR" || :
     else
         [ -n "$xtmpdir" -a -d "$xtmpdir" ] && rm -rf "$xtmpdir" || :
         [ -n "$itmpdir" -a -d "$itmpdir" ] && rm -rf "$itmpdir" || :
     fi
 
     # Final cleanup
-    pgid=$(ps -o pgid= $$ | grep -o '[0-9]*')
+    pgid=$(ps -o pgid= $$ 2>/dev/null | grep -o '[0-9]*' || :)
 
     # This means no setsid done in mysqld.
     # We don't want to kill mysqld here otherwise.
-    if [ $$ -eq $pgid ]; then
-        # This means a signal was delivered to the process.
-        # So, more cleanup.
-        if [ $estatus -ge 128 ]; then
-            kill -KILL -- -$$ || :
+    if [ -n "$pgid" ]; then
+        if [ $$ -eq $pgid ]; then
+            # This means a signal was delivered to the process.
+            # So, more cleanup.
+            if [ $estatus -ge 128 ]; then
+                kill -KILL -- -$$ || :
+            fi
         fi
     fi
 
+    if [ -n "${SST_PID:-}" ]; then
+        [ -f "$SST_PID" ] && rm -f "$SST_PID" || :
+    fi
+
     exit $estatus
 }
 
@@ -967,7 +927,7 @@ setup_commands()
     fi
     INNOAPPLY="$BACKUP_BIN --prepare$disver$recovery${iapts:+ }$iapts$INNOEXTRA --target-dir='$DATA' --datadir='$DATA'$mysqld_args $INNOAPPLY"
     INNOMOVE="$BACKUP_BIN$WSREP_SST_OPT_CONF --move-back$disver${impts:+ }$impts --force-non-empty-directories --target-dir='$DATA' --datadir='${TDATA:-$DATA}' $INNOMOVE"
-    INNOBACKUP="$BACKUP_BIN$WSREP_SST_OPT_CONF --backup$disver${iopts:+ }$iopts $tmpopts$INNOEXTRA --galera-info --stream=$sfmt --target-dir='$itmpdir' --datadir='$DATA'$mysqld_args $INNOBACKUP"
+    INNOBACKUP="$BACKUP_BIN$WSREP_SST_OPT_CONF --backup$disver${iopts:+ }$iopts$tmpopts$INNOEXTRA --galera-info --stream=$sfmt --target-dir='$itmpdir' --datadir='$DATA'$mysqld_args $INNOBACKUP"
 }
 
 get_stream
@@ -995,7 +955,7 @@ then
         fi
 
         wsrep_log_info "Using '$xtmpdir' as mariabackup temporary directory"
-        tmpopts="--tmpdir='$xtmpdir'"
+        tmpopts=" --tmpdir='$xtmpdir'"
 
         itmpdir="$(mktemp -d)"
         wsrep_log_info "Using '$itmpdir' as mariabackup working directory"
@@ -1161,10 +1121,23 @@ then
         impts="--parallel=$backup_threads${impts:+ }$impts"
     fi
 
-    stagemsg='Joiner-Recv'
+    SST_PID="$WSREP_SST_OPT_DATA/wsrep_sst.pid"
+
+    # give some time for previous SST to complete:
+    check_round=0
+    while check_pid "$SST_PID" 0; do
+        wsrep_log_info "previous SST is not completed, waiting for it to exit"
+        check_round=$(( check_round + 1 ))
+        if [ $check_round -eq 10 ]; then
+            wsrep_log_error "previous SST script still running."
+            exit 114 # EALREADY
+        fi
+        sleep 1
+    done
+
+    echo $$ > "$SST_PID"
 
-    sencrypted=1
-    nthreads=1
+    stagemsg='Joiner-Recv'
 
     MODULE="xtrabackup_sst"
 
@@ -1208,7 +1181,7 @@ then
     fi
 
     get_keys
-    if [ $encrypt -eq 1 -a $sencrypted -eq 1 ]; then
+    if [ $encrypt -eq 1 ]; then
         strmcmd="$ecmd | $strmcmd"
     fi
 
@@ -1263,12 +1236,14 @@ then
 
         if [ -n "$WSREP_SST_OPT_BINLOG" ]; then
             binlog_dir=$(dirname "$WSREP_SST_OPT_BINLOG")
-            cd "$binlog_dir"
-            wsrep_log_info "Cleaning the binlog directory $binlog_dir as well"
-            rm -fv "$WSREP_SST_OPT_BINLOG".[0-9]* 1>&2 \+ || :
-            [ -f "$WSREP_SST_OPT_BINLOG_INDEX" ] && \
-                rm -fv "$WSREP_SST_OPT_BINLOG_INDEX" 1>&2 \+ || :
-            cd "$OLD_PWD"
+            if [ -d "$binlog_dir" ]; then
+                cd "$binlog_dir"
+                wsrep_log_info "Cleaning the binlog directory $binlog_dir as well"
+                rm -fv "$WSREP_SST_OPT_BINLOG".[0-9]* 1>&2 \+ || :
+                [ -f "$WSREP_SST_OPT_BINLOG_INDEX" ] && \
+                    rm -fv "$WSREP_SST_OPT_BINLOG_INDEX" 1>&2 \+
+                cd "$OLD_PWD"
+            fi
         fi
 
         TDATA="$DATA"
@@ -1285,7 +1260,7 @@ then
         fi
 
         # Compact backups are not supported by mariabackup
-        if grep -q -F 'compact = 1' "$DATA/xtrabackup_checkpoints"; then
+        if grep -qw -F 'compact = 1' "$DATA/xtrabackup_checkpoints"; then
             wsrep_log_info "Index compaction detected"
             wsrel_log_error "Compact backups are not supported by mariabackup"
             exit 2
diff --git a/scripts/wsrep_sst_rsync.sh b/scripts/wsrep_sst_rsync.sh
index b0cc8cb3066..28dfed18218 100644
--- a/scripts/wsrep_sst_rsync.sh
+++ b/scripts/wsrep_sst_rsync.sh
@@ -17,7 +17,7 @@
 # Free Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston
 # MA  02110-1335  USA.
 
-# This is a reference script for rsync-based state snapshot tansfer
+# This is a reference script for rsync-based state snapshot transfer
 
 RSYNC_REAL_PID=0   # rsync process id
 STUNNEL_REAL_PID=0 # stunnel process id
@@ -41,7 +41,7 @@ cleanup_joiner()
         if cleanup_pid $STUNNEL_REAL_PID "$STUNNEL_PID" "$STUNNEL_CONF"; then
             if [ $RSYNC_REAL_PID -eq 0 ]; then
                 if [ -r "$RSYNC_PID" ]; then
-                    RSYNC_REAL_PID=$(cat "$RSYNC_PID" 2>/dev/null)
+                    RSYNC_REAL_PID=$(cat "$RSYNC_PID" 2>/dev/null || :)
                     if [ -z "$RSYNC_REAL_PID" ]; then
                         RSYNC_REAL_PID=0
                     fi
@@ -79,7 +79,7 @@ check_pid_and_port()
 
     local utils='rsync|stunnel'
 
-    if ! check_port "$pid" "$port" "$utils"; then
+    if ! check_port $pid "$port" "$utils"; then
         local port_info
         local busy=0
 
@@ -90,7 +90,7 @@ check_pid_and_port()
             grep -q -E "[[:space:]](\\*|\\[?::\\]?):$port[[:space:]]" && busy=1
         else
             local filter='([^[:space:]]+[[:space:]]+){4}[^[:space:]]+'
-            if [ $sockstat_available -eq 1 ]; then
+            if [ $sockstat_available -ne 0 ]; then
                 local opts='-p'
                 if [ "$OS" = 'FreeBSD' ]; then
                     # sockstat on FreeBSD requires the "-s" option
@@ -110,18 +110,20 @@ check_pid_and_port()
         fi
 
         if [ $busy -eq 0 ]; then
-            if echo "$port_info" | grep -qw -F "[$addr]:$port" || \
-               echo "$port_info" | grep -qw -F -- "$addr:$port"
+            if ! echo "$port_info" | grep -qw -F "[$addr]:$port" && \
+               ! echo "$port_info" | grep -qw -F -- "$addr:$port"
             then
-                busy=1
+                if ! ps -p $pid >/dev/null 2>&1; then
+                    wsrep_log_error \
+                        "rsync or stunnel daemon (PID: $pid)" \
+                        "terminated unexpectedly."
+                    exit 16 # EBUSY
+                fi
+                return 1
             fi
         fi
 
-        if [ $busy -eq 0 ]; then
-            return 1
-        fi
-
-        if ! check_port "$pid" "$port" "$utils"; then
+        if ! check_port $pid "$port" "$utils"; then
             wsrep_log_error "rsync or stunnel daemon port '$port'" \
                             "has been taken by another program"
             exit 16 # EBUSY
@@ -197,60 +199,16 @@ INNODB_UNDO_DIR=$(pwd -P)
 
 cd "$OLD_PWD"
 
-# Old filter - include everything except selected
-# FILTER=(--exclude '*.err' --exclude '*.pid' --exclude '*.sock' \
-#         --exclude '*.conf' --exclude core --exclude 'galera.*' \
-#         --exclude grastate.txt --exclude '*.pem' \
-#         --exclude '*.[0-9][0-9][0-9][0-9][0-9][0-9]' --exclude '*.index')
-
-# New filter - exclude everything except dirs (schemas) and innodb files
-FILTER="-f '- /lost+found'
-        -f '- /.zfs'
-        -f '- /.fseventsd'
-        -f '- /.Trashes'
-        -f '- /.pid'
-        -f '- /.conf'
-        -f '+ /wsrep_sst_binlog.tar'
-        -f '- $INNODB_DATA_HOME_DIR/ib_lru_dump'
-        -f '- $INNODB_DATA_HOME_DIR/ibdata*'
-        -f '+ $INNODB_UNDO_DIR/undo*'
-        -f '+ /*/'
-        -f '- /*'"
-
-# old-style SSL config
-SSTKEY=$(parse_cnf 'sst' 'tkey')
-SSTCERT=$(parse_cnf 'sst' 'tcert')
-SSTCA=$(parse_cnf 'sst' 'tca')
-SSTCAP=$(parse_cnf 'sst' 'tcapath')
+encgroups='--mysqld|sst'
 
-SST_SECTIONS="--mysqld|sst"
+check_server_ssl_config
 
-check_server_ssl_config()
-{
-    SSTKEY=$(parse_cnf "$SST_SECTIONS" 'ssl-key')
-    SSTCERT=$(parse_cnf "$SST_SECTIONS" 'ssl-cert')
-    SSTCA=$(parse_cnf "$SST_SECTIONS" 'ssl-ca')
-    SSTCAP=$(parse_cnf "$SST_SECTIONS" 'ssl-capath')
-}
+SSTKEY="$tkey"
+SSTCERT="$tpem"
+SSTCA="$tcert"
+SSTCAP="$tcap"
 
-SSLMODE=$(parse_cnf "$SST_SECTIONS" 'ssl-mode' | tr [:lower:] [:upper:])
-
-# no old-style SSL config in [sst], check for new one:
-if [ -z "$SSTKEY" -a -z "$SSTCERT" -a -z "$SSTCA" -a -z "$SSTCAP" ]; then
-    check_server_ssl_config
-fi
-
-if [ -n "$SSTCA" ]; then
-    SSTCA=$(trim_string "$SSTCA")
-    if [ "${SSTCA%/}" != "$SSTCA" ] || [ -d "$SSTCA" ]; then
-        SSTCAP="$SSTCA"
-        SSTCA=""
-    fi
-fi
-
-if [ -n "$SSTCAP" ]; then
-    SSTCAP=$(trim_string "$SSTCAP")
-fi
+SSLMODE=$(parse_cnf "$encgroups" 'ssl-mode' | tr [:lower:] [:upper:])
 
 if [ -z "$SSLMODE" ]; then
     # Implicit verification if CA is set and the SSL mode
@@ -266,7 +224,7 @@ if [ -z "$SSLMODE" ]; then
     fi
 fi
 
-if [ -n "$SSTCERT" -a -n "$SSTKEY" ]; then
+if [ -n "$SSTKEY" -a -n "$SSTCERT" ]; then
     verify_cert_matches_key "$SSTCERT" "$SSTKEY"
 fi
 
@@ -287,8 +245,7 @@ fi
 VERIFY_OPT=""
 CHECK_OPT=""
 CHECK_OPT_LOCAL=""
-if [ "${SSLMODE#VERIFY}" != "$SSLMODE" ]
-then
+if [ "${SSLMODE#VERIFY}" != "$SSLMODE" ]; then
     case "$SSLMODE" in
     'VERIFY_IDENTITY')
         VERIFY_OPT='verifyPeer = yes'
@@ -364,8 +321,9 @@ EOF
         [ -f "$STUNNEL_CONF" ] && rm -f "$STUNNEL_CONF"
     fi
 
-    if [ $WSREP_SST_OPT_BYPASS -eq 0 ]
-    then
+    RC=0
+
+    if [ $WSREP_SST_OPT_BYPASS -eq 0 ]; then
 
         FLUSHED="$WSREP_SST_OPT_DATA/tables_flushed"
         ERROR="$WSREP_SST_OPT_DATA/sst_error"
@@ -380,11 +338,11 @@ EOF
         # (b) Cluster state ID & wsrep_gtid_domain_id to be written to the file, OR
         # (c) ERROR file, in case flush tables operation failed.
 
-        while [ ! -r "$FLUSHED" ] && ! grep -q -F ':' "$FLUSHED" >/dev/null 2>&1
+        while [ ! -r "$FLUSHED" ] && \
+                ! grep -q -F ':' '--' "$FLUSHED" >/dev/null 2>&1
         do
             # Check whether ERROR file exists.
-            if [ -f "$ERROR" ]
-            then
+            if [ -f "$ERROR" ]; then
                 # Flush tables operation failed.
                 rm -f "$ERROR"
                 exit 255
@@ -397,7 +355,7 @@ EOF
 
         sync
 
-        if [ -n "$WSREP_SST_OPT_BINLOG" ]
+        if [ -n "$WSREP_SST_OPT_BINLOG" -a -d "${BINLOG_DIRNAME:-}" ]
         then
             # Prepare binlog files
             cd "$BINLOG_DIRNAME"
@@ -405,16 +363,14 @@ EOF
             binlog_files_full=$(tail -n $BINLOG_N_FILES \
                                 "$WSREP_SST_OPT_BINLOG_INDEX")
             binlog_files=""
-            for ii in $binlog_files_full
-            do
-                binlog_file=$(basename "$ii")
-                binlog_files="$binlog_files $binlog_file"
+            for file in $binlog_files_full; do
+                binlog_file=$(basename "$file")
+                binlog_files="$binlog_files${binlog_files:+ }'$binlog_file'"
             done
 
-            if [ -n "$binlog_files" ]
-            then
+            if [ -n "$binlog_files" ]; then
                 wsrep_log_info "Preparing binlog files for transfer:"
-                tar -cvf "$BINLOG_TAR_FILE" $binlog_files >&2
+                eval tar -cvf "'$BINLOG_TAR_FILE'" $binlog_files >&2
             fi
 
             cd "$OLD_PWD"
@@ -427,9 +383,28 @@ EOF
             WHOLE_FILE_OPT="--whole-file"
         fi
 
+# Old filter - include everything except selected
+# FILTER=(--exclude '*.err' --exclude '*.pid' --exclude '*.sock' \
+#         --exclude '*.conf' --exclude core --exclude 'galera.*' \
+#         --exclude grastate.txt --exclude '*.pem' \
+#         --exclude '*.[0-9][0-9][0-9][0-9][0-9][0-9]' --exclude '*.index')
+
+# New filter - exclude everything except dirs (schemas) and innodb files
+FILTER="-f '- /lost+found'
+        -f '- /.zfs'
+        -f '- /.fseventsd'
+        -f '- /.Trashes'
+        -f '- /.pid'
+        -f '- /.conf'
+        -f '+ /wsrep_sst_binlog.tar'
+        -f '- $INNODB_DATA_HOME_DIR/ib_lru_dump'
+        -f '- $INNODB_DATA_HOME_DIR/ibdata*'
+        -f '+ $INNODB_UNDO_DIR/undo*'
+        -f '+ /*/'
+        -f '- /*'"
+
         # first, the normal directories, so that we can detect
         # incompatible protocol:
-        RC=0
         eval rsync ${STUNNEL:+"--rsh='$STUNNEL'"} \
               --owner --group --perms --links --specials \
               --ignore-times --inplace --dirs --delete --quiet \
@@ -484,7 +459,7 @@ EOF
 
         cd "$WSREP_SST_OPT_DATA"
 
-        backup_threads=$(parse_cnf "--mysqld|sst" 'backup-threads')
+        backup_threads=$(parse_cnf '--mysqld|sst' 'backup-threads')
         if [ -z "$backup_threads" ]; then
             get_proc
             backup_threads=$nproc
@@ -527,7 +502,12 @@ EOF
 
     rsync ${STUNNEL:+--rsh="$STUNNEL"} \
           --archive --quiet --checksum "$MAGIC_FILE" \
-          "rsync://$WSREP_SST_OPT_ADDR"
+          "rsync://$WSREP_SST_OPT_ADDR" >&2 || RC=$?
+
+    if [ $RC -ne 0 ]; then
+        wsrep_log_error "rsync $MAGIC_FILE returned code $RC:"
+        exit 255 # unknown error
+    fi
 
     echo "done $STATE"
 
@@ -540,12 +520,11 @@ elif [ "$WSREP_SST_OPT_ROLE" = 'joiner' ]
 then
     check_sockets_utils
 
-    SST_PID="$WSREP_SST_OPT_DATA/wsrep_rsync_sst.pid"
+    SST_PID="$WSREP_SST_OPT_DATA/wsrep_sst.pid"
 
     # give some time for previous SST to complete:
     check_round=0
-    while check_pid "$SST_PID" 0
-    do
+    while check_pid "$SST_PID" 0 'wsrep_sst_'; do
         wsrep_log_info "previous SST is not completed, waiting for it to exit"
         check_round=$(( check_round + 1 ))
         if [ $check_round -eq 10 ]; then
@@ -555,10 +534,11 @@ then
         sleep 1
     done
 
+    echo $$ > "$SST_PID"
+
     # give some time for stunnel from the previous SST to complete:
     check_round=0
-    while check_pid "$STUNNEL_PID" 1
-    do
+    while check_pid "$STUNNEL_PID" 1; do
         wsrep_log_info "Lingering stunnel daemon found at startup," \
                        "waiting for it to exit"
         check_round=$(( check_round + 1 ))
@@ -575,8 +555,7 @@ then
 
     # give some time for rsync from the previous SST to complete:
     check_round=0
-    while check_pid "$RSYNC_PID" 1
-    do
+    while check_pid "$RSYNC_PID" 1; do
         wsrep_log_info "Lingering rsync daemon found at startup," \
                        "waiting for it to exit"
         check_round=$(( check_round + 1 ))
@@ -590,7 +569,7 @@ then
     [ -f "$MAGIC_FILE"      ] && rm -f "$MAGIC_FILE"
     [ -f "$BINLOG_TAR_FILE" ] && rm -f "$BINLOG_TAR_FILE"
 
-    [ -z "$STUNNEL" ] && [ -f "$STUNNEL_CONF" ] && rm -f "$STUNNEL_CONF"
+    [ -z "$STUNNEL" -a -f "$STUNNEL_CONF" ] && rm -f "$STUNNEL_CONF"
 
     ADDR="$WSREP_SST_OPT_ADDR"
     RSYNC_PORT="$WSREP_SST_OPT_PORT"
@@ -639,8 +618,6 @@ EOF
         RSYNC_ADDR="*"
     fi
 
-    echo $$ > "$SST_PID"
-
     if [ -z "$STUNNEL" ]; then
         rsync --daemon --no-detach --port "$RSYNC_PORT" \
               --config "$RSYNC_CONF" $RSYNC_EXTRA_ARGS &