Index: testing/testsuite/testfaults.conf
===================================================================
--- testing/testsuite/testfaults.conf	(.../trunk)	(revision 4440)
+++ testing/testsuite/testfaults.conf	(.../branches/panic-2)	(revision 4440)
@@ -98,23 +98,27 @@
   cmd set_fr, on node1;
   cmd set_md_rd, on node1;
 
-  # attach/detach a few times (want at least one failure!
-  for (my $i = 0; $i < 5; ++$i) {
+  # attach/detach a few times (want at least 10 failures!
+  for (my $i = 0,$errcount=0; $errcount < 10; ++$i) {
+    INFO "   $i. attach";
     cmd '/sbin/drbdadm attach {resource}', on node1;
 
     sleep 2;
 
     if ((get state_ds, on node1) =~ /Diskless/) {
-	VERBOSE ("goodness: meta data read fault fired");
+        $errcount = $errcount + 1;
+	INFO ("      goodness: meta data read fault fired ($errcount)");
     }
     else {
 	# might need to wait for resync here... disable
 	# faults whilst we wait
 	cmd clr_fr, on node1;
 
+        INFO "      device attached - wait for data to be synchronized...";
 	expected 'cs', state 'Connected', timeout 500;
 	expected 'ds', state 'UpToDate', timeout 500;
 
+        INFO "      ... and detach device";
 	cmd '/sbin/drbdadm detach {resource}', on node1;
 
 	cmd set_fr, on node1;
@@ -133,22 +137,26 @@
   cmd set_md_wr, on node1;
 
   # attach/detach a few times (want at least one failure!
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0,$errcount=0; $errcount < 10; ++$i) {
+    INFO "   $i. attach";
     cmd '/sbin/drbdadm attach {resource}', on node1;
 
     sleep 2;
 
     if ((get state_ds, on node1) =~ /Diskless/) {
-	VERBOSE ("goodness: meta data write fault fired");
+	$errcount = $errcount+1;
+	INFO("      goodness: meta data write fault fired ($errcount)");
     }
     else {
 	# might need to wait for resync here... disable
 	# faults whilst we wait
 	cmd clr_fr, on node1;
 
+        INFO "      device attached - wait for data to be synchronized...";
 	expected 'cs', state 'Connected', timeout 500;
 	expected 'ds', state 'UpToDate', timeout 500;
 
+        INFO "      ... and detach device";
 	cmd '/sbin/drbdadm detach {resource}', on node1;
 
 	cmd set_fr, on node1;
@@ -164,36 +172,61 @@
   expected 'cs', state 'Connected', timeout 15;
   expected 'ds', state 'UpToDate', timeout 15;
 
+  # simulate meta data write failures on partner node
+  INFO "3. Simulate remote meta data write failures during attach";
+
   # switch to primary
+  INFO "   First, switch local to primary -- this will cause md write on remote";
   cmd '/sbin/drbdadm primary {resource}', on node1;
 
   # Check node1 went primary...
   expected 'st', state 'Primary', timeout 15, on node1;
 
-  # simulate meta data write failures on partner node
-  INFO "3. Simulate remote meta data write failures during attach";
+  cmd '/sbin/drbdadm detach {resource}', on node1;
+
   cmd set_fr, on node2;
-  cmd set_md_rd, on node2;
+  cmd set_md_wr, on node2;
 
-  cmd '/sbin/drbdadm detach {resource}', on node1;
-
   # attach/detach a few times (want to see at least one failure!
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0,$errcount=0; $errcount < 5; ++$i) {
+    INFO "   $i. attach";
     cmd '/sbin/drbdadm attach {resource}', on node1;
 
     sleep 2;
 
-    if ((get state_ds, on node1) =~ /Diskless/) {
-	VERBOSE ("goodness: meta data write fault fired");
+    if ((get state_ds, on node2) =~ /Diskless/) {
+	$errcount = $errcount + 1;
+	INFO("      goodness: meta data write fault fired ($errcount)");
+
+	# recover everything...
+	cmd clr_fr, on node2;
+	if ((get state_ds, on node1) =~ /Diskless/) {
+	    INFO("      Reattach on node1");
+	    cmd '/sbin/drbdadm attach {resource}', on node1;
+        }
+        INFO ("      reattach on node2");
+        cmd '/sbin/drbdadm attach {resource}', on node2;
+        INFO "      device attached - wait for data to be synchronized...";
+	expected 'cs', state 'Connected', timeout 500;
+	expected 'ds', state 'UpToDate', timeout 500;
+
+        INFO "      ... and detach device";
+	cmd '/sbin/drbdadm detach {resource}', on node1;
+
+	cmd set_fr, on node2;
+	cmd set_md_rd, on node2;
+
     }
     else {
 	# might need to wait for resync here... disable
 	# faults whilst we wait
 	cmd clr_fr, on node2;
 
+        INFO "      device attached - wait for data to be synchronized...";
 	expected 'cs', state 'Connected', timeout 500;
 	expected 'ds', state 'UpToDate', timeout 500;
 
+        INFO "      ... and detach device";
 	cmd '/sbin/drbdadm detach {resource}', on node1;
 
 	cmd set_fr, on node2;
@@ -203,8 +236,9 @@
 
   cmd clr_fr, on node2;
 
-  # make sure partner is attached...
-  cmd '/sbin/drbdadm attach {resource}', on node2;
+  # make sure disk is attached...
+  INFO "   Finally, ensure all disks attached";
+  cmd '/sbin/drbdadm attach {resource}', on node1;
 
   # everyone should be in connected cstate, uptodate dstate
   expected 'cs', state 'Connected', timeout 500;
@@ -216,8 +250,10 @@
   cmd set_dt_rd, on node1;
 
   # mount file system a few times.
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0; $i < 20; ++$i) {
+      INFO "   $i. mount device";
       cmd 'mount /dev/{device} {mountpoint}', on node1;
+      INFO "      unmount device";
       cmd 'umount /dev/{device}', on node1;
 
       sleep 2;
@@ -235,12 +271,14 @@
   cmd set_dt_wr, on node1;
 
   # mount file system and modify - check for errors!
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0; $i < 20; ++$i) {
+      INFO "   $i. mount device";
       cmd 'mount /dev/{device} {mountpoint}', on node1;
 
       # create some files - should get some errors...
       cmd 'cp -f /boot/* {mountpoint}', on node1;
   
+      INFO "      unmount device";
       cmd 'umount /dev/{device}', on node1;
 
       sleep 2;
@@ -259,8 +297,10 @@
   cmd set_dt_rd, on node2;
 
   # mount file system - check for errors!
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0; $i < 20; ++$i) {
+      INFO "   $i. mount device";
       cmd 'mount /dev/{device} {mountpoint}', on node1;
+      INFO "      unmount device";
       cmd 'umount /dev/{device}', on node1;
 
       sleep 2;
@@ -278,17 +318,19 @@
   expected 'ds', state 'UpToDate', timeout 15;
 
   # simulate write errors remotely
-  INFO "6. Simulate remote user data write failures";
+  INFO "7. Simulate remote user data write failures";
   cmd set_fr, on node2;
   cmd set_dt_wr, on node2;
 
-  for (my $i = 0; $i < 5; ++$i) {
+  for (my $i = 0; $i < 20; ++$i) {
       # mount file system - check for errors!
+      INFO "   $i. mount device";
       cmd 'mount /dev/{device} {mountpoint}', on node1;
 
       # create some files - should get some errors...
       cmd 'cp -f /boot/* {mountpoint}', on node1;
   
+      INFO "      unmount device";
       cmd 'umount /dev/{device}', on node1;
 
       sleep 2;
Index: testing/testsuite/agent.pl
===================================================================
--- testing/testsuite/agent.pl	(.../trunk)	(revision 4440)
+++ testing/testsuite/agent.pl	(.../branches/panic-2)	(revision 4440)
@@ -215,7 +215,7 @@
     do {
       $output = `$command 2>&1`;
       chomp($output);
-    } while (defined($expected) && !($output eq $expected));
+    } while (defined($expected) && !($output eq $expected) && usleep(100000));
     alarm 0;
   };
   if ($@) {