ctdb-scripts: Fix stack dumping when debugging hung scripts

There are parentheses missing that stop the default pattern from
matching commands with trailing garbage (e.g. "exportfs.orig").

A careful check of POSIX (and running GNU sed with --posix) suggests
that "\|" isn't a supported way of specifying alternation in a regular
expression.  Therefore, it is clearer to switch to extended regular
expressions so that this has a chance of being portable (even though
the point is to print /proc/<pid>/stack, which only works on Linux).

Signed-off-by: Martin Schwenke <martin@meltin.net>
Reviewed-by: Amitay Isaacs <amitay@gmail.com>

Autobuild-User(master): Amitay Isaacs <amitay@samba.org>
Autobuild-Date(master): Tue Nov 18 06:37:45 CET 2014 on sn-devel-104

3 files changed, 12 insertions, 7 deletions

diff --git a/ctdb/config/debug-hung-script.sh b/ctdb/config/debug-hung-script.sh
index 34e957c3cf0..3f800fc5559 100755
--- a/ctdb/config/debug-hung-script.sh
+++ b/ctdb/config/debug-hung-script.sh
@@ -1,5 +1,8 @@
 #!/bin/sh
 
+# This script only works on Linux.  Please modify (and submit patches)
+# for other operating systems.
+
 [ -n "$CTDB_BASE" ] || \
     export CTDB_BASE=$(cd -P $(dirname "$0") ; echo "$PWD")
 
@@ -28,12 +31,12 @@ fi
     # Check for processes matching a regular expression and print
     # stack staces.  This could help confirm that certain processes
     # are stuck in certain places such as the cluster filesystem.  The
-    # regexp should separate items with "\|" and should not contain
+    # regexp must separate items with "|" and must not contain
     # parentheses.  The default pattern can be replaced for testing.
-    default_pat='exportfs\|rpcinfo'
+    default_pat='exportfs|rpcinfo'
     pat="${CTDB_DEBUG_HUNG_SCRIPT_STACKPAT:-${default_pat}}"
     echo "$out" |
-    sed -n "s@.*-\(.*${pat}.*\),\([0-9]*\).*@\2 \1@p" |
+    sed -r -n "s@.*-(.*(${pat}).*),([0-9]*).*@\3 \1@p" |
     while read pid name ; do
 	trace=$(cat "/proc/${pid}/stack" 2>/dev/null)
 	if [ $? -eq 0 ] ; then
diff --git a/ctdb/doc/ctdbd.conf.5.xml b/ctdb/doc/ctdbd.conf.5.xml
index cb48d721d06..cf71a3509bd 100644
--- a/ctdb/doc/ctdbd.conf.5.xml
+++ b/ctdb/doc/ctdbd.conf.5.xml
@@ -1521,11 +1521,13 @@ CTDB_SET_MonitorInterval=20
 	  <para>
 	    REGEXP specifies interesting processes for which stack
 	    traces should be logged when debugging hung eventscripts
-	    and those processes are matched in pstree output.  See
-	    also <citetitle>CTDB_DEBUG_HUNG_SCRIPT</citetitle>.
+	    and those processes are matched in pstree output.  REGEXP
+	    is an extended regexp so choices are separated by pipes
+	    ('|').  However, REGEXP should not contain parentheses.
+	    See also <citetitle>CTDB_DEBUG_HUNG_SCRIPT</citetitle>.
 	  </para>
 	  <para>
-	    Default is "exportfs\|rpcinfo".
+	    Default is "exportfs|rpcinfo".
 	  </para>
 	</listitem>
       </varlistentry>
diff --git a/ctdb/tests/complex/90_debug_hung_script.sh b/ctdb/tests/complex/90_debug_hung_script.sh
index 543844970ba..09718c4f721 100755
--- a/ctdb/tests/complex/90_debug_hung_script.sh
+++ b/ctdb/tests/complex/90_debug_hung_script.sh
@@ -58,7 +58,7 @@ ctdb_test_exit_hook_add "onnode $test_node rm -f $debug_output"
 try_command_on_node -i $test_node tee "$rc_local_f" <<<"\
 CTDB_RUN_TIMEOUT_MONITOR=yes
 CTDB_DEBUG_HUNG_SCRIPT_LOGFILE=\"$debug_output\"
-CTDB_DEBUG_HUNG_SCRIPT_STACKPAT='exportfs\|rpcinfo\|sleep'"
+CTDB_DEBUG_HUNG_SCRIPT_STACKPAT='exportfs|rpcinfo|sleep'"
 
 try_command_on_node $test_node chmod +x "$rc_local_f"