Bug#30529132 REVIEW OUTDATED LCPSCANFRAGWATCHDOG AND BUG24664 USING ERROR INSERT 10039

This fix replaces the use of the old error code 10039 with
new error code 10055 for stalling local checkpoints in
testcases where that is required.

Error code 10039 was modified in the 7.6 release so that it no
longer stalled LCP and so the testcases were not giving the
coverage they were designed for.

This fix restores the testcase coverage.

Testcases affected :
  testNodeRestart -n LcpScanFragWatchdog
                  -n LcpScanFragWatchdogDisable
                  -n LcpScanFragWatchdogIsolation
  testSystemRestart -n Bug24664

Notes :
  - In 7.6 Partial LCP :
    - The LCP Fragment Scan Watchdog was changed to cover
      more of the LCP process including non scan periods.
    - An undocumented hard coded two minute time limit on
      each actual fragment scan has been implemented.
    This means that the user supplied limit is ignored when
    a fragment scan takes > 2 minutes.
    This behavioural change is left as-is.
    The 2 minute hard limit does not affect
    e.g. testNodeRestart -n LCPScanFragWatchdogDisable as
    the scan stall error injection occurs before that timing
    mechanism starts.

  - testSystemRestart -n Bug24664 was using error insert
    10040 to resume the stalled LCP.
    This is no longer necessary, clearing the error is
    sufficient.
    Additionally, error insert 10040 has been reused for
    a different purpose so the overall effect was incorrect.

Change-Id: I28f6462c101016a50b74bde2375176424428b9fe

Author: frazerclement

storage/ndb/src/kernel/blocks/dblqh/DblqhMain.cpp

@@ -32662,7 +32662,7 @@ Dblqh::handle_check_system_scans(Signal *signal)
         if (i == ZLCP_CHECK_INDEX)
         {
           jam();
-          g_eventLogger->info("LCP Scan have stalled for %u seconds, last"
+          g_eventLogger->info("LCP Scan has stalled for %u seconds, "
                               "last seen on line %u, check_lcp_stop_count: %u",
                               time_stalled,
                               c_check_scanptr_save_line[i],
@@ -32671,7 +32671,7 @@ Dblqh::handle_check_system_scans(Signal *signal)
         else if (i == ZBACKUP_CHECK_INDEX)
         {
           jam();
-          g_eventLogger->info("Backup Scan have stalled for %u seconds, "
+          g_eventLogger->info("Backup Scan has stalled for %u seconds, "
                               "last seen on line %u, check_lcp_stop_count: %u",
                               time_stalled,
                               c_check_scanptr_save_line[i],
@@ -32680,7 +32680,7 @@ Dblqh::handle_check_system_scans(Signal *signal)
         else if (i == ZCOPY_FRAGREQ_CHECK_INDEX)
         {
           jam();
-          g_eventLogger->info("COPY_FRAGREQ Scan have stalled for %u seconds,"
+          g_eventLogger->info("COPY_FRAGREQ Scan has stalled for %u seconds,"
                               "last seen on line %u, check_lcp_stop_count: %u",
                               time_stalled,
                               c_check_scanptr_save_line[i],

storage/ndb/test/ndbapi/testNodeRestart.cpp

@@ -6587,7 +6587,7 @@ runTestScanFragWatchdog(NDBT_Context* ctx, NDBT_Step* step)
       break;
     }
 
-    if (restarter.insertErrorInNode(victim, 10039) != 0) /* Cause LCP/backup frag scan to halt */
+    if (restarter.insertErrorInNode(victim, 10055) != 0) /* Cause LCP/backup frag scan to halt */
     {
       g_err << "Error insert failed." << endl;
       break;
@@ -6798,7 +6798,7 @@ runTestScanFragWatchdogDisable(NDBT_Context* ctx, NDBT_Step* step)
 
     g_err << "Injecting fault in node " << victim;
     g_err << " to suspend LCP frag scan..." << endl;
-    if (restarter.insertErrorInNode(victim, 10039) != 0) 
+    if (restarter.insertErrorInNode(victim, 10055) != 0) 
     {
       g_err << "Error insert failed." << endl;
       break;
@@ -6862,7 +6862,7 @@ runTestScanFragWatchdogDisable(NDBT_Context* ctx, NDBT_Step* step)
   } while (0);
 
   // Insert error code to resume LCP in case node halted
-  if (restarter.insertErrorInNode(victim, 10040) != 0) 
+  if (restarter.insertErrorInNode(victim, 0) != 0) 
   {
     g_err << "Test cleanup failed: failed to resume LCP." << endl;
   }

storage/ndb/test/ndbapi/testSystemRestart.cpp

@@ -1,5 +1,5 @@
 /*
-   Copyright (c) 2003, 2021, Oracle and/or its affiliates.
+   Copyright (c) 2003, 2023, Oracle and/or its affiliates.
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License, version 2.0,
@@ -2153,7 +2153,7 @@ runBug24664(NDBT_Context* ctx, NDBT_Step* step)
       return NDBT_FAILED;
     }
 
-    restarter.insertErrorInAllNodes(10039); // Hang LCP
+    restarter.insertErrorInAllNodes(10055); // Hang LCP
     CHECK(restarter.dumpStateAllNodes(dump, 1) == 0);
     while(ndb_logevent_get_next(handle, &event, 0) >= 0 &&
 	  event.type != NDB_LE_LocalCheckpointStarted);
@@ -2163,7 +2163,7 @@ runBug24664(NDBT_Context* ctx, NDBT_Step* step)
       return NDBT_FAILED;
     }
 
-    restarter.insertErrorInAllNodes(10040); // Resume LCP
+    restarter.insertErrorInAllNodes(0); // Resume LCP
     while(ndb_logevent_get_next(handle, &event, 0) >= 0 &&
 	  event.type != NDB_LE_LocalCheckpointCompleted);