Merge pull request #17736 from taosdata/fix/TD-19624

fix: split vgroup

source/dnode/mnode/impl/src/mndVgroup.c

@@ -1641,35 +1641,81 @@ static int32_t mndSplitVgroup(SMnode *pMnode, SRpcMsg *pReq, SDbObj *pDb, SVgObj
   if (newVg1.replica == 1) {
     if (mndAddVnodeToVgroup(pMnode, &newVg1, pArray) != 0) goto _OVER;
     if (mndAddCreateVnodeAction(pMnode, pTrans, pDb, &newVg1, &newVg1.vnodeGid[1]) != 0) goto _OVER;
-    if (mndAddAlterVnodeReplicaAction(pMnode, pTrans, pDb, &newVg1, -1) != 0) goto _OVER;
+    if (mndAddAlterVnodeReplicaAction(pMnode, pTrans, pDb, &newVg1, newVg1.vnodeGid[0].dnodeId) != 0) goto _OVER;
     if (mndAddAlterVnodeConfirmAction(pMnode, pTrans, pDb, &newVg1) != 0) goto _OVER;
   } else if (newVg1.replica == 3) {
     SVnodeGid del1 = {0};
     if (mndRemoveVnodeFromVgroup(pMnode, &newVg1, pArray, &del1) != 0) goto _OVER;
-    if (mndAddAlterVnodeReplicaAction(pMnode, pTrans, pDb, &newVg1, -1) != 0) goto _OVER;
+    if (mndAddAlterVnodeReplicaAction(pMnode, pTrans, pDb, &newVg1, newVg1.vnodeGid[0].dnodeId) != 0) goto _OVER;
+    if (mndAddAlterVnodeReplicaAction(pMnode, pTrans, pDb, &newVg1, newVg1.vnodeGid[1].dnodeId) != 0) goto _OVER;
     if (mndAddDropVnodeAction(pMnode, pTrans, pDb, &newVg1, &del1, true) != 0) goto _OVER;
     if (mndAddAlterVnodeConfirmAction(pMnode, pTrans, pDb, &newVg1) != 0) goto _OVER;
   } else {
     goto _OVER;
   }
 
+  mInfo("vgId:%d, vgroup info after adjust replica, replica:%d hashBegin:%u hashEnd:%u vnode:0 dnode:%d", newVg1.vgId,
+        newVg1.replica, newVg1.hashBegin, newVg1.hashEnd, newVg1.vnodeGid[0].dnodeId);
+  for (int32_t i = 0; i < newVg1.replica; ++i) {
+    mInfo("vgId:%d, vnode:%d dnode:%d", newVg1.vgId, i, newVg1.vnodeGid[i].dnodeId);
+  }
+
   SVgObj newVg2 = {0};
-  memcpy(&newVg1, &newVg2, sizeof(SVgObj));
+  memcpy(&newVg2, &newVg1, sizeof(SVgObj));
   newVg1.replica = 1;
-  newVg1.hashEnd = (newVg1.hashBegin + newVg1.hashEnd) / 2;
+  newVg1.hashEnd = newVg1.hashBegin / 2 + newVg1.hashEnd / 2;
   memset(&newVg1.vnodeGid[1], 0, sizeof(SVnodeGid));
 
   newVg2.replica = 1;
   newVg2.hashBegin = newVg1.hashEnd + 1;
   memcpy(&newVg2.vnodeGid[0], &newVg2.vnodeGid[1], sizeof(SVnodeGid));
-  memset(&newVg1.vnodeGid[1], 0, sizeof(SVnodeGid));
+  memset(&newVg2.vnodeGid[1], 0, sizeof(SVnodeGid));
+
+  mInfo("vgId:%d, vgroup info after adjust hash, replica:%d hashBegin:%u hashEnd:%u vnode:0 dnode:%d", newVg1.vgId,
+        newVg1.replica, newVg1.hashBegin, newVg1.hashEnd, newVg1.vnodeGid[0].dnodeId);
+  mInfo("vgId:%d, vgroup info after adjust hash, replica:%d hashBegin:%u hashEnd:%u vnode:0 dnode:%d", newVg2.vgId,
+        newVg2.replica, newVg2.hashBegin, newVg2.hashEnd, newVg2.vnodeGid[0].dnodeId);
 
   if (mndAddAlterVnodeHashRangeAction(pMnode, pTrans, pDb, &newVg1) != 0) goto _OVER;
   if (mndAddAlterVnodeHashRangeAction(pMnode, pTrans, pDb, &newVg2) != 0) goto _OVER;
 
-  // adjust vgroup
-  if (mndBuildAlterVgroupAction(pMnode, pTrans, pDb, pDb, &newVg1, pArray) != 0) goto _OVER;
-  if (mndBuildAlterVgroupAction(pMnode, pTrans, pDb, pDb, &newVg2, pArray) != 0) goto _OVER;
+#if 0
+  // adjust vgroup replica
+  if (pDb->cfg.replications != newVg1.replica) {
+    if (mndBuildAlterVgroupAction(pMnode, pTrans, pDb, pDb, &newVg1, pArray) != 0) goto _OVER;
+  }
+  if (pDb->cfg.replications != newVg2.replica) {
+    if (mndBuildAlterVgroupAction(pMnode, pTrans, pDb, pDb, &newVg2, pArray) != 0) goto _OVER;
+  }
+#endif
+
+  {
+    pRaw = mndVgroupActionEncode(&newVg1);
+    if (pRaw == NULL || mndTransAppendCommitlog(pTrans, pRaw) != 0) goto _OVER;
+    (void)sdbSetRawStatus(pRaw, SDB_STATUS_READY);
+    pRaw = NULL;
+  }
+
+  {
+    pRaw = mndVgroupActionEncode(&newVg2);
+    if (pRaw == NULL || mndTransAppendCommitlog(pTrans, pRaw) != 0) goto _OVER;
+    (void)sdbSetRawStatus(pRaw, SDB_STATUS_READY);
+    pRaw = NULL;
+  }
+
+  mInfo("vgId:%d, vgroup info after adjust hash, replica:%d hashBegin:%u hashEnd:%u vnode:0 dnode:%d", newVg1.vgId,
+        newVg1.replica, newVg1.hashBegin, newVg1.hashEnd, newVg1.vnodeGid[0].dnodeId);
+  for (int32_t i = 0; i < newVg1.replica; ++i) {
+    mInfo("vgId:%d, vnode:%d dnode:%d", newVg1.vgId, i, newVg1.vnodeGid[i].dnodeId);
+  }
+  mInfo("vgId:%d, vgroup info after adjust hash, replica:%d hashBegin:%u hashEnd:%u vnode:0 dnode:%d", newVg2.vgId,
+        newVg2.replica, newVg2.hashBegin, newVg2.hashEnd, newVg2.vnodeGid[0].dnodeId);
+  for (int32_t i = 0; i < newVg1.replica; ++i) {
+    mInfo("vgId:%d, vnode:%d dnode:%d", newVg2.vgId, i, newVg2.vnodeGid[i].dnodeId);
+  }
+
+  if (mndTransPrepare(pMnode, pTrans) != 0) goto _OVER;
+  code = 0;
 
 _OVER:
   mndTransDrop(pTrans);

tests/script/jenkins/basic.txt

@@ -56,6 +56,8 @@
 ./test.sh -f tsim/dnode/redistribute_vgroup_replica3_v3.sim
 ./test.sh -f tsim/dnode/vnode_clean.sim
 ./test.sh -f tsim/dnode/use_dropped_dnode.sim 
+./test.sh -f tsim/dnode/split_vgroup_replica1.sim 
+./test.sh -f tsim/dnode/split_vgroup_replica3.sim 
 
 # ---- import ----
 ./test.sh -f tsim/import/basic.sim

tests/script/tsim/dnode/split_vgroup_replica1.sim

+system sh/stop_dnodes.sh
+system sh/deploy.sh -n dnode1 -i 1
+system sh/deploy.sh -n dnode2 -i 2
+system sh/deploy.sh -n dnode3 -i 3
+system sh/deploy.sh -n dnode4 -i 4
+system sh/cfg.sh -n dnode1 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode2 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode3 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode4 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode1 -c supportVnodes -v 0
+system sh/exec.sh -n dnode1 -s start
+system sh/exec.sh -n dnode2 -s start
+sql connect
+sql create user u1 pass 'taosdata'
+
+print =============== step1 create dnode2
+sql create dnode $hostname port 7200
+sql create dnode $hostname port 7300
+
+$x = 0
+step1:
+	$x = $x + 1
+	sleep 1000
+	if $x == 10 then
+	  print ====> dnode not ready!
+		return -1
+	endi
+sql select * from information_schema.ins_dnodes
+print ===> $data00 $data01 $data02 $data03 $data04 $data05
+print ===> $data10 $data11 $data12 $data13 $data14 $data15
+print ===> $data20 $data21 $data22 $data23 $data24 $data25
+print ===> $data30 $data31 $data32 $data33 $data34 $data35
+if $rows != 3 then
+  return -1
+endi
+if $data(1)[4] != ready then
+  goto step1
+endi
+if $data(2)[4] != ready then
+  goto step1
+endi
+
+print =============== step2: create db
+sql create database d1 vgroups 1 replica 1
+
+system sh/exec.sh -n dnode3 -s start
+$x = 0
+step2:
+	$x = $x + 1
+	sleep 1000
+	if $x == 10 then
+	  print ====> dnode not ready!
+		return -1
+	endi
+sql select * from information_schema.ins_dnodes
+print ===> $data00 $data01 $data02 $data03 $data04 $data05
+print ===> $data10 $data11 $data12 $data13 $data14 $data15
+print ===> $data20 $data21 $data22 $data23 $data24 $data25
+if $rows != 3 then
+  return -1
+endi
+if $data(1)[4] != ready then
+  goto step2
+endi
+if $data(2)[4] != ready then
+  goto step2
+endi
+if $data(3)[4] != ready then
+  goto step2
+endi
+
+print =============== step3: create database
+sql use d1
+sql create table d1.st (ts timestamp, i int) tags (j int)
+sql create table d1.c1 using st tags(1)
+sql show d1.tables
+if $rows != 1 then
+  return -1
+endi
+
+print =============== step4: split 
+print split vgroup 2
+sql split vgroup 2
+
+system sh/exec.sh -n dnode1 -s stop -x SIGINT
+system sh/exec.sh -n dnode2 -s stop -x SIGINT
+system sh/exec.sh -n dnode3 -s stop -x SIGINT

tests/script/tsim/dnode/split_vgroup_replica3.sim

+system sh/stop_dnodes.sh
+system sh/deploy.sh -n dnode1 -i 1
+system sh/deploy.sh -n dnode2 -i 2
+system sh/deploy.sh -n dnode3 -i 3
+system sh/deploy.sh -n dnode4 -i 4
+system sh/deploy.sh -n dnode5 -i 5
+system sh/cfg.sh -n dnode1 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode2 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode3 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode4 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode5 -c transPullupInterval -v 1
+system sh/cfg.sh -n dnode1 -c supportVnodes -v 0
+system sh/exec.sh -n dnode1 -s start
+system sh/exec.sh -n dnode2 -s start
+system sh/exec.sh -n dnode3 -s start
+system sh/exec.sh -n dnode4 -s start
+#system sh/exec.sh -n dnode5 -s start
+sql connect
+sql create user u1 pass 'taosdata'
+
+print =============== step1 create dnode2
+sql create dnode $hostname port 7200
+sql create dnode $hostname port 7300
+sql create dnode $hostname port 7400
+
+$x = 0
+step1:
+	$x = $x + 1
+	sleep 1000
+	if $x == 10 then
+	  print ====> dnode not ready!
+		return -1
+	endi
+sql select * from information_schema.ins_dnodes
+print ===> $data00 $data01 $data02 $data03 $data04 $data05
+print ===> $data10 $data11 $data12 $data13 $data14 $data15
+print ===> $data20 $data21 $data22 $data23 $data24 $data25
+print ===> $data30 $data31 $data32 $data33 $data34 $data35
+print ===> $data40 $data41 $data42 $data43 $data44 $data45
+if $rows != 4 then
+  return -1
+endi
+if $data(1)[4] != ready then
+  goto step1
+endi
+if $data(2)[4] != ready then
+  goto step1
+endi
+if $data(3)[4] != ready then
+  goto step1
+endi
+if $data(4)[4] != ready then
+  goto step1
+endi
+
+print =============== step2: create db
+sql create database d1 vgroups 1 replica 3
+
+print =============== step3: split
+print split vgroup 2
+sql split vgroup 2
+
+system sh/exec.sh -n dnode1 -s stop -x SIGINT
+system sh/exec.sh -n dnode2 -s stop -x SIGINT
+system sh/exec.sh -n dnode3 -s stop -x SIGINT
+system sh/exec.sh -n dnode4 -s stop -x SIGINT
+system sh/exec.sh -n dnode5 -s stop -x SIGINT