Merge branch '3.0' into feature/TD-14481-3.0

docs-en/14-reference/03-connector/csharp.mdx

@@ -48,7 +48,7 @@ Please refer to [version support list](/reference/connector#version-support)
 
 * Install the [.NET SDK](https://dotnet.microsoft.com/download)
 * [Nuget Client](https://docs.microsoft.com/en-us/nuget/install-nuget-client-tools) (optional installation)
-* Install TDengine client driver, please refer to [Install client driver](/reference/connector#Install client driver) for details
+* Install TDengine client driver, please refer to [Install client driver](/reference/connector/#install-client-driver) for details
 
 ### Install via dotnet CLI
 
@@ -57,7 +57,7 @@ Please refer to [version support list](/reference/connector#version-support)
 
 You can reference the `TDengine.Connector` published in Nuget to the current project via the `dotnet` command under the path of the existing .NET project.
 
-``` bash
+```
 dotnet add package TDengine.Connector
 ```
 
@@ -66,7 +66,7 @@ dotnet add package TDengine.Connector
 
 You can download TDengine's source code and directly reference the latest version of the TDengine.Connector library
 
-```bash
+```
 git clone https://github.com/taosdata/TDengine.git
 cd TDengine/src/connector/C#/src/
 cp -r TDengineDriver/ myProject
@@ -79,7 +79,7 @@ dotnet add TDengineDriver/TDengineDriver.csproj
 
 ## Create a connection
 
-``` C#
+```csharp
 using TDengineDriver;
 
 namespace TDengineExample

docs-en/14-reference/03-connector/go.mdx

@@ -55,25 +55,27 @@ A "REST connection" is a connection between the application and the TDengine ins
 
 ### Pre-installation
 
-* Install Go development environment (Go 1.14 and above, GCC 4.8.5 and above)
-* If you use the native connector, please install the TDengine client driver. Please refer to [Install Client Driver](/reference/connector#Install Client Driver) for specific steps
+- Install Go development environment (Go 1.14 and above, GCC 4.8.5 and above)
+- If you use the native connector, please install the TDengine client driver. Please refer to [Install Client Driver](/reference/connector/#install-client-driver) for specific steps
 
 Configure the environment variables and check the command.
 
-* ```go env``
-* ```gcc -v``
+* `go env`
+* `gcc -v`
 
 ### Use go get to install
 
-``go get -u github.com/taosdata/driver-go/v2@develop``
+```
+go get -u github.com/taosdata/driver-go/v2@develop
+```
 
 ### Manage with go mod
 
 1. Initialize the project with the `go mod` command.
 
-  ``text
+  ```text
   go mod init taos-demo
-  ``` text
+  ``` 
 
 2. Introduce taosSql
 
@@ -88,7 +90,7 @@ Configure the environment variables and check the command.
 
   ```text
   go mod tidy
-  ``` 4.
+  ``` 
 
 4. Run the program with `go run taos-demo` or compile the binary with the `go build` command.
 
@@ -309,6 +311,7 @@ func main() {
 
 :::info
 This API is created successfully without checking permissions, but only when you execute a Query or Exec, and check if user/password/host/port is legal.
+
 :::
 
 * `func (db *DB) Exec(query string, args . .interface{}) (Result, error)`

docs-en/14-reference/03-connector/java.mdx

@@ -69,7 +69,7 @@ Before using Java Connector to connect to the database, the following conditions
 ### Install the connectors
 
 <Tabs defaultValue="maven">
-<TabItem value="maven" label="install via Maven">
+<TabItem value="maven" label="Install via Maven">
 
 - [sonatype](https://search.maven.org/artifact/com.taosdata.jdbc/taos-jdbcdriver)
 - [mvnrepository](https://mvnrepository.com/artifact/com.taosdata.jdbc/taos-jdbcdriver)
@@ -77,7 +77,7 @@ Before using Java Connector to connect to the database, the following conditions
 
 Add following dependency in the `pom.xml` file of your Maven project:
 
-```xml-dtd
+```xml
 <dependency>
  <groupId>com.taosdata.jdbc</groupId>
  <artifactId>taos-jdbcdriver</artifactId>
@@ -90,7 +90,7 @@ Add following dependency in the `pom.xml` file of your Maven project:
 
 You can build Java connector from source code after cloning the TDengine project:
 
-```shell
+```
 git clone https://github.com/taosdata/taos-connector-jdbc.git
 cd taos-connector-jdbc
 mvn clean install -Dmaven.test.skip=true
@@ -140,40 +140,43 @@ When you use a JDBC native connection to connect to a TDengine cluster, you can
 
 1. Do not specify hostname and port in Java applications.
 
-```java
-public Connection getConn() throws Exception{
-  Class.forName("com.taosdata.jdbc.TSDBDriver");
-  String jdbcUrl = "jdbc:TAOS://:/test?user=root&password=taosdata";
-  Properties connProps = new Properties();
-  connProps.setProperty(TSDBDriver.PROPERTY_KEY_CHARSET, "UTF-8");
-  connProps.setProperty(TSDBDriver.PROPERTY_KEY_LOCALE, "en_US.UTF-8");
-  connProps.setProperty(TSDBDriver.PROPERTY_KEY_TIME_ZONE, "UTC-8");
-  Connection conn = DriverManager.getConnection(jdbcUrl, connProps);
-  return conn;
-}
-```
+    ```java
+    public Connection getConn() throws Exception{
+    Class.forName("com.taosdata.jdbc.TSDBDriver");
+    String jdbcUrl = "jdbc:TAOS://:/test?user=root&password=taosdata";
+    Properties connProps = new Properties();
+    connProps.setProperty(TSDBDriver.PROPERTY_KEY_CHARSET, "UTF-8");
+    connProps.setProperty(TSDBDriver.PROPERTY_KEY_LOCALE, "en_US.UTF-8");
+    connProps.setProperty(TSDBDriver.PROPERTY_KEY_TIME_ZONE, "UTC-8");
+    Connection conn = DriverManager.getConnection(jdbcUrl, connProps);
+    return conn;
+    }
+    ```
 
 2. specify the firstEp and the secondEp in the configuration file taos.cfg
 
-```shell
-# first fully qualified domain name (FQDN) for TDengine system
-firstEp               cluster_node1:6030
+    ```shell
+    # first fully qualified domain name (FQDN) for TDengine system
+    firstEp               cluster_node1:6030
 
-# second fully qualified domain name (FQDN) for TDengine system, for cluster only
-secondEp              cluster_node2:6030
+    # second fully qualified domain name (FQDN) for TDengine system, for cluster only
+    secondEp              cluster_node2:6030
 
-# default system charset
-# charset               UTF-8
+    # default system charset
+    # charset               UTF-8
 
-# system locale
-# locale                en_US.UTF-8
-```
+    # system locale
+    # locale                en_US.UTF-8
+    ```
 
 In the above example, JDBC uses the client's configuration file to establish a connection to a hostname `cluster_node1`, port 6030, and a database named `test`. When the firstEp node in the cluster fails, JDBC attempts to connect to the cluster using secondEp.
 
 In TDengine, as long as one node in firstEp and secondEp is valid, the connection to the cluster can be established normally.
 
-> **Note**: The configuration file here refers to the configuration file on the machine where the application that calls the JDBC Connector is located, the default path is `/etc/taos/taos.cfg` on Linux, and the default path is `C://TDengine/cfg/taos.cfg` on Windows.
+:::note
+The configuration file here refers to the configuration file on the machine where the application that calls the JDBC Connector is located, the default path is `/etc/taos/taos.cfg` on Linux, and the default path is `C://TDengine/cfg/taos.cfg` on Windows.
+
+:::
 
 </TabItem>
 <TabItem value="rest" label="REST connection">

docs-en/14-reference/03-connector/rust.mdx

@@ -45,15 +45,15 @@ Add the [libtaos][libtaos] dependency to the [Rust](https://rust-lang.org) proje
 <Tabs defaultValue="native">
 <TabItem value="native" label="native connection">
 
-Add [libtaos][libtaos] to the ``Cargo.toml`'' file.
+Add [libtaos][libtaos] to the `Cargo.toml` file.
 
-``toml
+```toml
 [dependencies]
 # use default feature
 libtaos = "*"
 ```
 
-</TabItem
+</TabItem>
 <TabItem value="rest" label="REST connection">
 
 Add [libtaos][libtaos] to the `Cargo.toml` file and enable the `rest` feature.

include/client/taos.h

@@ -240,7 +240,10 @@ DLL_EXPORT const char *tmq_err2str(tmq_resp_err_t);
 DLL_EXPORT tmq_resp_err_t tmq_subscribe(tmq_t *tmq, const tmq_list_t *topic_list);
 DLL_EXPORT tmq_resp_err_t tmq_unsubscribe(tmq_t *tmq);
 DLL_EXPORT tmq_resp_err_t tmq_subscription(tmq_t *tmq, tmq_list_t **topics);
-DLL_EXPORT TAOS_RES      *tmq_consumer_poll(tmq_t *tmq, int64_t timeout);
+
+// timeout: -1 means infinitely waiting
+DLL_EXPORT TAOS_RES *tmq_consumer_poll(tmq_t *tmq, int64_t timeout);
+
 DLL_EXPORT tmq_resp_err_t tmq_consumer_close(tmq_t *tmq);
 DLL_EXPORT tmq_resp_err_t tmq_commit_sync(tmq_t *tmq, const tmq_topic_vgroup_list_t *offsets);
 DLL_EXPORT void tmq_commit_async(tmq_t *tmq, const tmq_topic_vgroup_list_t *offsets, tmq_commit_cb *cb, void *param);

include/common/tcommon.h

@@ -50,6 +50,7 @@ typedef enum EStreamType {
   STREAM_INVERT,
   STREAM_REPROCESS,
   STREAM_INVALID,
+  STREAM_GET_ALL,
 } EStreamType;
 
 typedef struct {
@@ -116,6 +117,8 @@ typedef struct SQueryTableDataCond {
   int32_t      type;              // data block load type:
   int32_t      numOfTWindows;
   STimeWindow* twindows;
+  int32_t      startVersion;
+  int32_t      endVersion;
 } SQueryTableDataCond;
 
 void*   blockDataDestroy(SSDataBlock* pBlock);

include/common/tmsg.h

@@ -1494,10 +1494,9 @@ typedef struct {
   int32_t code;
 } STaskDropRsp;
 
-#define STREAM_TRIGGER_AT_ONCE_SMA      0
 #define STREAM_TRIGGER_AT_ONCE          1
 #define STREAM_TRIGGER_WINDOW_CLOSE     2
-#define STREAM_TRIGGER_WINDOW_CLOSE_SMA 3
+#define STREAM_TRIGGER_MAX_DELAY        3
 
 typedef struct {
   char    name[TSDB_TABLE_FNAME_LEN];
@@ -2488,7 +2487,7 @@ typedef struct {
   int64_t offset;
   int64_t sliding;
   int64_t dstTbUid;
-  int32_t dstVgId;  // for stream
+  int32_t dstVgId;
   SEpSet  epSet;
   char*   expr;
 } STableIndexInfo;

include/common/tmsgdef.h

@@ -220,7 +220,7 @@ enum {
   TD_DEF_MSG_TYPE(TDMT_MON_QM_LOAD, "monitor-qload", NULL, NULL)
 
   TD_NEW_MSG_SEG(TDMT_SYNC_MSG)
-  TD_DEF_MSG_TYPE(TDMT_SYNC_TIMEOUT, "sync-timeout", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_SYNC_TIMEOUT, "sync-timer", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_SYNC_PING, "sync-ping", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_SYNC_PING_REPLY, "sync-ping-reply", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_SYNC_CLIENT_REQUEST, "sync-client-request", NULL, NULL)

include/libs/catalog/catalog.h

@@ -21,13 +21,13 @@ extern "C" {
 #endif
 
 #include "os.h"
-#include "taosdef.h"
 #include "query.h"
-#include "tname.h"
-#include "tcommon.h"
+#include "taosdef.h"
 #include "tarray.h"
+#include "tcommon.h"
 #include "thash.h"
 #include "tmsg.h"
+#include "tname.h"
 #include "transport.h"
 
 typedef struct SCatalog SCatalog;
@@ -47,8 +47,8 @@ typedef enum {
 } AUTH_TYPE;
 
 typedef struct SUserAuthInfo {
-  char user[TSDB_USER_LEN]; 
-  char dbFName[TSDB_DB_FNAME_LEN]; 
+  char      user[TSDB_USER_LEN];
+  char      dbFName[TSDB_DB_FNAME_LEN];
   AUTH_TYPE type;
 } SUserAuthInfo;
 
@@ -59,17 +59,17 @@ typedef struct SDbInfo {
 } SDbInfo;
 
 typedef struct SCatalogReq {
-  SArray *pDbVgroup;      // element is db full name
-  SArray *pDbCfg;         // element is db full name
-  SArray *pDbInfo;        // element is db full name
-  SArray *pTableMeta;     // element is SNAME
-  SArray *pTableHash;     // element is SNAME
-  SArray *pUdf;           // element is udf name
-  SArray *pIndex;         // element is index name
-  SArray *pUser;          // element is SUserAuthInfo
-  SArray *pTableIndex;    // element is SNAME
+  SArray* pDbVgroup;      // element is db full name
+  SArray* pDbCfg;         // element is db full name
+  SArray* pDbInfo;        // element is db full name
+  SArray* pTableMeta;     // element is SNAME
+  SArray* pTableHash;     // element is SNAME
+  SArray* pUdf;           // element is udf name
+  SArray* pIndex;         // element is index name
+  SArray* pUser;          // element is SUserAuthInfo
+  SArray* pTableIndex;    // element is SNAME
   bool    qNodeRequired;  // valid qnode
-  bool    forceUpdate;    
+  bool    forceUpdate;
 } SCatalogReq;
 
 typedef struct SMetaRes {
@@ -78,16 +78,16 @@ typedef struct SMetaRes {
 } SMetaRes;
 
 typedef struct SMetaData {
-  SArray    *pDbVgroup;   // pRes = SArray<SVgroupInfo>*
-  SArray    *pDbCfg;      // pRes = SDbCfgInfo*
-  SArray    *pDbInfo;     // pRes = SDbInfo*
-  SArray    *pTableMeta;  // pRes = STableMeta*
-  SArray    *pTableHash;  // pRes = SVgroupInfo*
-  SArray    *pTableIndex; // pRes = SArray<STableIndexInfo>*
-  SArray    *pUdfList;    // pRes = SFuncInfo*
-  SArray    *pIndex;      // pRes = SIndexInfo*
-  SArray    *pUser;       // pRes = bool*
-  SArray    *pQnodeList;  // pRes = SQueryNodeAddr*
+  SArray* pDbVgroup;    // pRes = SArray<SVgroupInfo>*
+  SArray* pDbCfg;       // pRes = SDbCfgInfo*
+  SArray* pDbInfo;      // pRes = SDbInfo*
+  SArray* pTableMeta;   // pRes = STableMeta*
+  SArray* pTableHash;   // pRes = SVgroupInfo*
+  SArray* pTableIndex;  // pRes = SArray<STableIndexInfo>*
+  SArray* pUdfList;     // pRes = SFuncInfo*
+  SArray* pIndex;       // pRes = SIndexInfo*
+  SArray* pUser;        // pRes = bool*
+  SArray* pQnodeList;   // pRes = SQueryNodeAddr*
 } SMetaData;
 
 typedef struct SCatalogCfg {
@@ -104,18 +104,18 @@ typedef struct SSTableMetaVersion {
   uint64_t dbId;
   uint64_t suid;
   int16_t  sversion;
-  int16_t  tversion;  
+  int16_t  tversion;
 } SSTableMetaVersion;
 
 typedef struct SDbVgVersion {
   char    dbFName[TSDB_DB_FNAME_LEN];
   int64_t dbId;
   int32_t vgVersion;
-  int32_t numOfTable; // unit is TSDB_TABLE_NUM_UNIT
+  int32_t numOfTable;  // unit is TSDB_TABLE_NUM_UNIT
 } SDbVgVersion;
 
 typedef struct STbSVersion {
-  char* tbFName;
+  char*   tbFName;
   int32_t sver;
   int32_t tver;
 } STbSVersion;
@@ -125,15 +125,15 @@ typedef struct SUserAuthVersion {
   int32_t version;
 } SUserAuthVersion;
 
-typedef SDbCfgRsp SDbCfgInfo;
+typedef SDbCfgRsp     SDbCfgInfo;
 typedef SUserIndexRsp SIndexInfo;
 
 typedef void (*catalogCallback)(SMetaData* pResult, void* param, int32_t code);
 
-int32_t catalogInit(SCatalogCfg *cfg);
+int32_t catalogInit(SCatalogCfg* cfg);
 
 /**
- * Get a cluster's catalog handle for all later operations. 
+ * Get a cluster's catalog handle for all later operations.
  * @param clusterId
  * @param catalogHandle (output, NO need to free it)
  * @return error code
@@ -141,14 +141,14 @@ int32_t catalogInit(SCatalogCfg *cfg);
 int32_t catalogGetHandle(uint64_t clusterId, SCatalog** catalogHandle);
 
 /**
- * Free a cluster's all catalog info, usually it's not necessary, until the application is closing. 
+ * Free a cluster's all catalog info, usually it's not necessary, until the application is closing.
  * no current or future usage should be guaranteed by application
  * @param pCatalog (input, NO more usage)
  * @return error code
  */
 void catalogFreeHandle(SCatalog* pCatalog);
 
-int32_t catalogGetDBVgVersion(SCatalog* pCtg, const char* dbFName, int32_t* version, int64_t* dbId, int32_t *tableNum);
+int32_t catalogGetDBVgVersion(SCatalog* pCtg, const char* dbFName, int32_t* version, int64_t* dbId, int32_t* tableNum);
 
 /**
  * Get a DB's all vgroup info.
@@ -159,7 +159,8 @@ int32_t catalogGetDBVgVersion(SCatalog* pCtg, const char* dbFName, int32_t* vers
  * @param pVgroupList (output, vgroup info list, element is SVgroupInfo, NEED to simply free the array by caller)
  * @return error code
  */
-int32_t catalogGetDBVgInfo(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, const char* pDBName, SArray** pVgroupList);
+int32_t catalogGetDBVgInfo(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const char* pDBName,
+                           SArray** pVgroupList);
 
 int32_t catalogUpdateDBVgInfo(SCatalog* pCatalog, const char* dbName, uint64_t dbId, SDBVgInfo* dbInfo);
 
@@ -170,7 +171,7 @@ int32_t catalogRemoveTableMeta(SCatalog* pCtg, SName* pTableName);
 int32_t catalogRemoveStbMeta(SCatalog* pCtg, const char* dbFName, uint64_t dbId, const char* stbName, uint64_t suid);
 
 /**
- * Get a table's meta data. 
+ * Get a table's meta data.
  * @param pCatalog (input, got with catalogGetHandle)
  * @param pTransporter (input, rpc object)
  * @param pMgmtEps (input, mnode EPs)
@@ -178,10 +179,11 @@ int32_t catalogRemoveStbMeta(SCatalog* pCtg, const char* dbFName, uint64_t dbId,
  * @param pTableMeta(output, table meta data, NEED to free it by calller)
  * @return error code
  */
-int32_t catalogGetTableMeta(SCatalog* pCatalog, void * pTransporter, const SEpSet* pMgmtEps, const SName* pTableName, STableMeta** pTableMeta);
+int32_t catalogGetTableMeta(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const SName* pTableName,
+                            STableMeta** pTableMeta);
 
 /**
- * Get a super table's meta data. 
+ * Get a super table's meta data.
  * @param pCatalog (input, got with catalogGetHandle)
  * @param pTransporter (input, rpc object)
  * @param pMgmtEps (input, mnode EPs)
@@ -189,47 +191,47 @@ int32_t catalogGetTableMeta(SCatalog* pCatalog, void * pTransporter, const SEpSe
  * @param pTableMeta(output, table meta data, NEED to free it by calller)
  * @return error code
  */
-int32_t catalogGetSTableMeta(SCatalog* pCatalog, void * pTransporter, const SEpSet* pMgmtEps, const SName* pTableName, STableMeta** pTableMeta);
-
-int32_t catalogUpdateTableMeta(SCatalog* pCatalog, STableMetaRsp *rspMsg);
+int32_t catalogGetSTableMeta(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const SName* pTableName,
+                             STableMeta** pTableMeta);
 
+int32_t catalogUpdateTableMeta(SCatalog* pCatalog, STableMetaRsp* rspMsg);
 
 /**
- * Force refresh DB's local cached vgroup info. 
+ * Force refresh DB's local cached vgroup info.
  * @param pCtg (input, got with catalogGetHandle)
  * @param pTrans (input, rpc object)
  * @param pMgmtEps (input, mnode EPs)
  * @param dbFName (input, db full name)
  * @return error code
  */
-int32_t catalogRefreshDBVgInfo(SCatalog* pCtg, void *pTrans, const SEpSet* pMgmtEps, const char* dbFName);
+int32_t catalogRefreshDBVgInfo(SCatalog* pCtg, void* pTrans, const SEpSet* pMgmtEps, const char* dbFName);
 
-int32_t catalogChkTbMetaVersion(SCatalog* pCtg, void *pTrans, const SEpSet* pMgmtEps, SArray* pTables);
+int32_t catalogChkTbMetaVersion(SCatalog* pCtg, void* pTrans, const SEpSet* pMgmtEps, SArray* pTables);
 
 /**
- * Force refresh a table's local cached meta data. 
+ * Force refresh a table's local cached meta data.
  * @param pCatalog (input, got with catalogGetHandle)
  * @param pTransporter (input, rpc object)
  * @param pMgmtEps (input, mnode EPs)
  * @param pTableName (input, table name)
- * @param isSTable (input, is super table or not, 1:supposed to be stable, 0: supposed not to be stable, -1:not sure) 
+ * @param isSTable (input, is super table or not, 1:supposed to be stable, 0: supposed not to be stable, -1:not sure)
  * @return error code
  */
-int32_t catalogRefreshTableMeta(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, const SName* pTableName, int32_t isSTable);
+int32_t catalogRefreshTableMeta(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const SName* pTableName,
+                                int32_t isSTable);
 
 /**
- * Force refresh a table's local cached meta data and get the new one. 
+ * Force refresh a table's local cached meta data and get the new one.
  * @param pCatalog (input, got with catalogGetHandle)
  * @param pTransporter (input, rpc object)
  * @param pMgmtEps (input, mnode EPs)
  * @param pTableName (input, table name)
- * @param pTableMeta(output, table meta data, NEED to free it by calller) 
- * @param isSTable (input, is super table or not, 1:supposed to be stable, 0: supposed not to be stable, -1:not sure) 
+ * @param pTableMeta(output, table meta data, NEED to free it by calller)
+ * @param isSTable (input, is super table or not, 1:supposed to be stable, 0: supposed not to be stable, -1:not sure)
  * @return error code
  */
-int32_t catalogRefreshGetTableMeta(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, const SName* pTableName, STableMeta** pTableMeta, int32_t isSTable);
-
-
+int32_t catalogRefreshGetTableMeta(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps,
+                                   const SName* pTableName, STableMeta** pTableMeta, int32_t isSTable);
 
 /**
  * Get a table's actual vgroup, for stable it's all possible vgroup list.
@@ -240,7 +242,8 @@ int32_t catalogRefreshGetTableMeta(SCatalog* pCatalog, void *pTransporter, const
  * @param pVgroupList (output, vgroup info list, element is SVgroupInfo, NEED to simply free the array by caller)
  * @return error code
  */
-int32_t catalogGetTableDistVgInfo(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, const SName* pTableName, SArray** pVgroupList);
+int32_t catalogGetTableDistVgInfo(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps,
+                                  const SName* pTableName, SArray** pVgroupList);
 
 /**
  * Get a table's vgroup from its name's hash value.
@@ -251,8 +254,8 @@ int32_t catalogGetTableDistVgInfo(SCatalog* pCatalog, void *pTransporter, const
  * @param vgInfo (output, vgroup info)
  * @return error code
  */
-int32_t catalogGetTableHashVgroup(SCatalog* pCatalog, void * pTransporter, const SEpSet* pMgmtEps, const SName* pName, SVgroupInfo* vgInfo);
-
+int32_t catalogGetTableHashVgroup(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const SName* pName,
+                                  SVgroupInfo* vgInfo);
 
 /**
  * Get all meta data required in pReq.
@@ -261,36 +264,40 @@ int32_t catalogGetTableHashVgroup(SCatalog* pCatalog, void * pTransporter, const
  * @param pMgmtEps (input, mnode EPs)
  * @param pReq (input, reqest info)
  * @param pRsp (output, response data)
- * @return error code 
+ * @return error code
  */
-int32_t catalogGetAllMeta(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, const SCatalogReq* pReq, SMetaData* pRsp);
+int32_t catalogGetAllMeta(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, const SCatalogReq* pReq,
+                          SMetaData* pRsp);
 
-int32_t catalogAsyncGetAllMeta(SCatalog* pCtg, void *pTrans, const SEpSet* pMgmtEps, uint64_t reqId, const SCatalogReq* pReq, catalogCallback fp, void* param, int64_t* jobId);
+int32_t catalogAsyncGetAllMeta(SCatalog* pCtg, void* pTrans, const SEpSet* pMgmtEps, uint64_t reqId,
+                               const SCatalogReq* pReq, catalogCallback fp, void* param, int64_t* jobId);
 
-int32_t catalogGetQnodeList(SCatalog* pCatalog, void *pTransporter, const SEpSet* pMgmtEps, SArray* pQnodeList);
+int32_t catalogGetQnodeList(SCatalog* pCatalog, void* pTransporter, const SEpSet* pMgmtEps, SArray* pQnodeList);
 
-int32_t catalogGetExpiredSTables(SCatalog* pCatalog, SSTableMetaVersion **stables, uint32_t *num);
+int32_t catalogGetExpiredSTables(SCatalog* pCatalog, SSTableMetaVersion** stables, uint32_t* num);
 
-int32_t catalogGetExpiredDBs(SCatalog* pCatalog, SDbVgVersion **dbs, uint32_t *num);
+int32_t catalogGetExpiredDBs(SCatalog* pCatalog, SDbVgVersion** dbs, uint32_t* num);
 
-int32_t catalogGetExpiredUsers(SCatalog* pCtg, SUserAuthVersion **users, uint32_t *num);
+int32_t catalogGetExpiredUsers(SCatalog* pCtg, SUserAuthVersion** users, uint32_t* num);
 
-int32_t catalogGetDBCfg(SCatalog* pCtg, void *pRpc, const SEpSet* pMgmtEps, const char* dbFName, SDbCfgInfo* pDbCfg);
+int32_t catalogGetDBCfg(SCatalog* pCtg, void* pRpc, const SEpSet* pMgmtEps, const char* dbFName, SDbCfgInfo* pDbCfg);
 
-int32_t catalogGetIndexMeta(SCatalog* pCtg, void *pRpc, const SEpSet* pMgmtEps, const char* indexName, SIndexInfo* pInfo);
+int32_t catalogGetIndexMeta(SCatalog* pCtg, void* pRpc, const SEpSet* pMgmtEps, const char* indexName,
+                            SIndexInfo* pInfo);
 
-int32_t catalogGetTableIndex(SCatalog* pCtg, void *pTrans, const SEpSet* pMgmtEps, const SName* pTableName, SArray** pRes);
+int32_t catalogGetTableIndex(SCatalog* pCtg, void* pTrans, const SEpSet* pMgmtEps, const SName* pTableName,
+                             SArray** pRes);
 
-int32_t catalogGetUdfInfo(SCatalog* pCtg, void *pRpc, const SEpSet* pMgmtEps, const char* funcName, SFuncInfo* pInfo);
+int32_t catalogGetUdfInfo(SCatalog* pCtg, void* pRpc, const SEpSet* pMgmtEps, const char* funcName, SFuncInfo* pInfo);
 
-int32_t catalogChkAuth(SCatalog* pCtg, void *pRpc, const SEpSet* pMgmtEps, const char* user, const char* dbFName, AUTH_TYPE type, bool *pass);
+int32_t catalogChkAuth(SCatalog* pCtg, void* pRpc, const SEpSet* pMgmtEps, const char* user, const char* dbFName,
+                       AUTH_TYPE type, bool* pass);
 
 int32_t catalogUpdateUserAuthInfo(SCatalog* pCtg, SGetUserAuthRsp* pAuth);
 
-int32_t catalogUpdateVgEpSet(SCatalog* pCtg, const char* dbFName, int32_t vgId, SEpSet *epSet);
-
-int32_t ctgdLaunchAsyncCall(SCatalog* pCtg, void *pTrans, const SEpSet* pMgmtEps, uint64_t reqId, bool forceUpdate);
+int32_t catalogUpdateVgEpSet(SCatalog* pCtg, const char* dbFName, int32_t vgId, SEpSet* epSet);
 
+int32_t ctgdLaunchAsyncCall(SCatalog* pCtg, void* pTrans, const SEpSet* pMgmtEps, uint64_t reqId, bool forceUpdate);
 
 /**
  * Destroy catalog and relase all resources

include/libs/nodes/plannodes.h

@@ -62,6 +62,7 @@ typedef struct SScanLogicNode {
   int64_t       watermark;
   int16_t       tsColId;
   double        filesFactor;
+  SArray*       pSmaIndexes;
 } SScanLogicNode;
 
 typedef struct SJoinLogicNode {
@@ -303,7 +304,7 @@ typedef struct SDownstreamSourceNode {
 
 typedef struct SExchangePhysiNode {
   SPhysiNode node;
-  int32_t    srcGroupId;     // group id of datasource suplans
+  int32_t    srcGroupId;  // group id of datasource suplans
   bool       singleChannel;
   SNodeList* pSrcEndPoints;  // element is SDownstreamSource, scheduler fill by calling qSetSuplanExecutionNode
 } SExchangePhysiNode;
@@ -437,7 +438,6 @@ typedef struct SQueryPlan {
   int32_t      numOfSubplans;
   SNodeList*   pSubplans;  // Element is SNodeListNode. The execution level of subplan, starting from 0.
   SExplainInfo explainInfo;
-  SArray*      pPlaceholderValues;
 } SQueryPlan;
 
 void nodesWalkPhysiPlan(SNode* pNode, FNodeWalker walker, void* pContext);

include/libs/nodes/querynodes.h

@@ -144,6 +144,7 @@ typedef struct SRealTableNode {
   SVgroupsInfo*      pVgroupList;
   char               qualDbName[TSDB_DB_NAME_LEN];  // SHOW qualDbName.TABLES
   double             ratio;
+  SArray*            pSmaIndexes;
 } SRealTableNode;
 
 typedef struct STempTableNode {

include/libs/parser/parser.h

@@ -63,7 +63,7 @@ int32_t qAnalyseSqlSemantic(SParseContext* pCxt, const struct SCatalogReq* pCata
 void qDestroyQuery(SQuery* pQueryNode);
 
 int32_t qExtractResultSchema(const SNode* pRoot, int32_t* numOfCols, SSchema** pSchema);
-int32_t qSetSTableIdForRSma(SNode* pStmt, int64_t uid);
+int32_t qSetSTableIdForRsma(SNode* pStmt, int64_t uid);
 
 int32_t     qBuildStmtOutput(SQuery* pQuery, SHashObj* pVgHash, SHashObj* pBlockHash);
 int32_t     qResetStmtDataBlock(void* block, bool keepBuf);

include/libs/sync/sync.h

@@ -83,8 +83,10 @@ typedef struct SReConfigCbMeta {
   SyncTerm  term;
   SyncTerm  currentTerm;
   SSyncCfg  oldCfg;
+  SSyncCfg  newCfg;
   bool      isDrop;
   uint64_t  flag;
+  uint64_t  seqNum;
 } SReConfigCbMeta;
 
 typedef struct SSnapshot {
@@ -106,7 +108,7 @@ typedef struct SSyncFSM {
   void (*FpRollBackCb)(struct SSyncFSM* pFsm, const SRpcMsg* pMsg, SFsmCbMeta cbMeta);
 
   void (*FpRestoreFinishCb)(struct SSyncFSM* pFsm);
-  void (*FpReConfigCb)(struct SSyncFSM* pFsm, SSyncCfg newCfg, SReConfigCbMeta cbMeta);
+  void (*FpReConfigCb)(struct SSyncFSM* pFsm, const SRpcMsg* pMsg, SReConfigCbMeta cbMeta);
 
   int32_t (*FpGetSnapshot)(struct SSyncFSM* pFsm, SSnapshot* pSnapshot);
 
@@ -184,7 +186,6 @@ int64_t     syncOpen(const SSyncInfo* pSyncInfo);
 void        syncStart(int64_t rid);
 void        syncStop(int64_t rid);
 int32_t     syncSetStandby(int64_t rid);
-int32_t     syncReconfig(int64_t rid, const SSyncCfg* pSyncCfg);
 ESyncState  syncGetMyRole(int64_t rid);
 const char* syncGetMyRoleStr(int64_t rid);
 SyncTerm    syncGetMyTerm(int64_t rid);
@@ -194,8 +195,10 @@ int32_t     syncPropose(int64_t rid, const SRpcMsg* pMsg, bool isWeak);
 bool        syncEnvIsStart();
 const char* syncStr(ESyncState state);
 bool        syncIsRestoreFinish(int64_t rid);
+int32_t     syncGetSnapshotMeta(int64_t rid, struct SSnapshotMeta* sMeta);
 
-int32_t syncGetSnapshotMeta(int64_t rid, struct SSnapshotMeta* sMeta);
+int32_t syncReconfig(int64_t rid, const SSyncCfg* pNewCfg);
+int32_t syncReconfigRaw(int64_t rid, const SSyncCfg* pNewCfg, SRpcMsg* pRpcMsg);
 
 // to be moved to static
 void syncStartNormal(int64_t rid);

include/util/taoserror.h

@@ -85,7 +85,6 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_RPC_NETWORK_UNAVAIL           TAOS_DEF_ERROR_CODE(0, 0x0102)
 #define TSDB_CODE_RPC_FQDN_ERROR                TAOS_DEF_ERROR_CODE(0, 0x0103)
 #define TSDB_CODE_RPC_PORT_EADDRINUSE           TAOS_DEF_ERROR_CODE(0, 0x0104)
-#define TSDB_CODE_RPC_INDIRECT_NETWORK_UNAVAIL  TAOS_DEF_ERROR_CODE(0, 0x0105)
 
 //client
 #define TSDB_CODE_TSC_INVALID_OPERATION         TAOS_DEF_ERROR_CODE(0, 0x0200)
@@ -220,6 +219,7 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_MND_VGROUP_ALREADY_IN_DNODE   TAOS_DEF_ERROR_CODE(0, 0x0392)
 #define TSDB_CODE_MND_VGROUP_UN_CHANGED         TAOS_DEF_ERROR_CODE(0, 0x0393)
 #define TSDB_CODE_MND_HAS_OFFLINE_DNODE         TAOS_DEF_ERROR_CODE(0, 0x0394)
+#define TSDB_CODE_MND_INVALID_REPLICA           TAOS_DEF_ERROR_CODE(0, 0x0395)
 
 // mnode-stable
 #define TSDB_CODE_MND_STB_ALREADY_EXIST         TAOS_DEF_ERROR_CODE(0, 0x03A0)
@@ -260,6 +260,7 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_MND_TRANS_CONFLICT            TAOS_DEF_ERROR_CODE(0, 0x03D3)
 #define TSDB_CODE_MND_TRANS_UNKNOW_ERROR        TAOS_DEF_ERROR_CODE(0, 0x03D4)
 #define TSDB_CODE_MND_TRANS_CLOG_IS_NULL        TAOS_DEF_ERROR_CODE(0, 0x03D5)
+#define TSDB_CODE_MND_TRANS_NETWORK_UNAVAILL    TAOS_DEF_ERROR_CODE(0, 0x03D6)
 
 // mnode-mq
 #define TSDB_CODE_MND_TOPIC_ALREADY_EXIST       TAOS_DEF_ERROR_CODE(0, 0x03E0)

include/util/tjson.h

@@ -17,16 +17,17 @@
 #define _TD_UTIL_JSON_H_
 
 #include "os.h"
+#include "tarray.h"
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-#define tjsonGetNumberValue(pJson, pName, val, code)  \
-  do {                                                \
-    uint64_t _tmp = 0;                                \
+#define tjsonGetNumberValue(pJson, pName, val, code) \
+  do {                                               \
+    uint64_t _tmp = 0;                               \
     code = tjsonGetBigIntValue(pJson, pName, &_tmp); \
-    val = _tmp;                                       \
+    val = _tmp;                                      \
   } while (0)
 
 typedef void SJson;
@@ -66,18 +67,20 @@ typedef int32_t (*FToJson)(const void* pObj, SJson* pJson);
 int32_t tjsonAddObject(SJson* pJson, const char* pName, FToJson func, const void* pObj);
 int32_t tjsonAddItem(SJson* pJson, FToJson func, const void* pObj);
 int32_t tjsonAddArray(SJson* pJson, const char* pName, FToJson func, const void* pArray, int32_t itemSize, int32_t num);
+int32_t tjsonAddTArray(SJson* pJson, const char* pName, FToJson func, const SArray* pArray);
 
 typedef int32_t (*FToObject)(const SJson* pJson, void* pObj);
 
 int32_t tjsonToObject(const SJson* pJson, const char* pName, FToObject func, void* pObj);
 int32_t tjsonMakeObject(const SJson* pJson, const char* pName, FToObject func, void** pObj, int32_t objSize);
 int32_t tjsonToArray(const SJson* pJson, const char* pName, FToObject func, void* pArray, int32_t itemSize);
+int32_t tjsonToTArray(const SJson* pJson, const char* pName, FToObject func, SArray** pArray, int32_t itemSize);
 
 char* tjsonToString(const SJson* pJson);
 char* tjsonToUnformattedString(const SJson* pJson);
 
-SJson* tjsonParse(const char* pStr);
-bool   tjsonValidateJson(const char* pJson);
+SJson*      tjsonParse(const char* pStr);
+bool        tjsonValidateJson(const char* pJson);
 const char* tjsonGetError();
 
 #ifdef __cplusplus

source/client/src/clientImpl.c

@@ -692,6 +692,7 @@ void launchAsyncQuery(SRequestObj* pRequest, SQuery* pQuery) {
 
       if (TSDB_CODE_SUCCESS == code) {
         code = qCreateQueryPlan(&cxt, &pRequest->body.pDag, pNodeList);
+        tscError("0x%"PRIx64" failed to create query plan, code:%s 0x%"PRIx64, pRequest->self, tstrerror(code), pRequest->requestId);
       }
 
       if (TSDB_CODE_SUCCESS == code) {

source/client/src/clientSml.c

@@ -17,6 +17,9 @@
 #include "tname.h"
 #include "cJSON.h"
 #include "tglobal.h"
+#include "osSemaphore.h"
+#include "osThread.h"
+
 //=================================================================================================
 
 #define SPACE ' '
@@ -67,6 +70,9 @@ for (int i = 1; i < keyLen; ++i) {      \
 
 #define BINARY_ADD_LEN 2        // "binary"   2 means " "
 #define NCHAR_ADD_LEN 3         // L"nchar"   3 means L" "
+
+#define MAX_RETRY_TIMES 5
+#define LINE_BATCH  20
 //=================================================================================================
 typedef TSDB_SML_PROTOCOL_TYPE SMLProtocolType;
 
@@ -153,8 +159,17 @@ typedef struct {
   int64_t endTime;
 } SSmlCostInfo;
 
+typedef struct{
+  SRequestObj*    request;
+  SCatalog*       catalog;
+  tsem_t          sem;
+  TdThreadSpinlock lock;
+} Params;
+
 typedef struct {
   int64_t           id;
+  Params            *params;
+  bool              isLast;
 
   SMLProtocolType   protocol;
   int8_t            precision;
@@ -303,7 +318,7 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
           uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
         }
         taos_free_result(res2);
-        taosMsleep(10);
+        taosMsleep(500);
       }
       break;
     }
@@ -327,7 +342,7 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
           uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
         }
         taos_free_result(res2);
-        taosMsleep(10);
+        taosMsleep(500);
       }
       break;
     }
@@ -350,7 +365,7 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
           uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
         }
         taos_free_result(res2);
-        taosMsleep(10);
+        taosMsleep(500);
       }
       break;
     }
@@ -373,7 +388,7 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
           uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
         }
         taos_free_result(res2);
-        taosMsleep(10);
+        taosMsleep(500);
       }
       break;
     }
@@ -424,7 +439,7 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
           uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
         }
         taos_free_result(res2);
-        taosMsleep(10);
+        taosMsleep(500);
       }
       break;
     }
@@ -541,56 +556,6 @@ end:
   return code;
 }
 
-//=========================================================================
-
-/*        Field                          Escape charaters
-    1: measurement                        Comma,Space
-    2: tag_key, tag_value, field_key  Comma,Equal Sign,Space
-    3: field_value                    Double quote,Backslash
-*/
-//static void escapeSpecialCharacter(uint8_t field, const char **pos) {
-//  const char *cur = *pos;
-//  if (*cur != '\\') {
-//    return;
-//  }
-//  switch (field) {
-//    case 1:
-//      switch (*(cur + 1)) {
-//        case ',':
-//        case ' ':
-//          cur++;
-//          break;
-//        default:
-//          break;
-//      }
-//      break;
-//    case 2:
-//      switch (*(cur + 1)) {
-//        case ',':
-//        case ' ':
-//        case '=':
-//          cur++;
-//          break;
-//        default:
-//          break;
-//      }
-//      break;
-//    case 3:
-//      switch (*(cur + 1)) {
-//        case '"':
-//        case '\\':
-//          cur++;
-//          break;
-//        default:
-//          break;
-//      }
-//      break;
-//    default:
-//      break;
-//  }
-//  *pos = cur;
-//}
-
 static bool smlParseNumber(SSmlKv *kvVal, SSmlMsgBuf *msg){
   const char *pVal = kvVal->value;
   int32_t len = kvVal->length;
@@ -1426,6 +1391,7 @@ static void smlDestroyInfo(SSmlHandle* info){
   if(!info->dataFormat){
     taosArrayDestroy(info->colsContainer);
   }
+  destroyRequest(info->pRequest);
   taosMemoryFreeClear(info);
 }
 
@@ -1453,11 +1419,6 @@ static SSmlHandle* smlBuildSmlInfo(TAOS* taos, SRequestObj* request, SMLProtocol
   ((SVnodeModifOpStmt*)(info->pQuery->pRoot))->payloadType = PAYLOAD_TYPE_KV;
 
   info->taos        = (STscObj *)taos;
-  code = catalogGetHandle(info->taos->pAppInfo->clusterId, &info->pCatalog);
-  if(code != TSDB_CODE_SUCCESS){
-    uError("SML:0x%"PRIx64" get catalog error %d", info->id, code);
-    goto cleanup;
-  }
 
   info->precision   = precision;
   info->protocol    = protocol;
@@ -2206,7 +2167,6 @@ end:
   return ret;
 }
 
-
 static int32_t smlInsertData(SSmlHandle* info) {
   int32_t code = TSDB_CODE_SUCCESS;
 
@@ -2248,10 +2208,12 @@ static int32_t smlInsertData(SSmlHandle* info) {
   }
   info->cost.insertRpcTime = taosGetTimestampUs();
 
-  launchQueryImpl(info->pRequest, info->pQuery, true, NULL);
+  //launchQueryImpl(info->pRequest, info->pQuery, false, NULL);
+//  info->affectedRows = taos_affected_rows(info->pRequest);
+//  return info->pRequest->code;
 
-  info->affectedRows = taos_affected_rows(info->pRequest);
-  return info->pRequest->code;
+  launchAsyncQuery(info->pRequest, info->pQuery);
+  return TSDB_CODE_SUCCESS;
 }
 
 static void smlPrintStatisticInfo(SSmlHandle *info){
@@ -2311,7 +2273,7 @@ static int smlProcess(SSmlHandle *info, char* lines[], int numLines) {
   do{
     code = smlModifyDBSchemas(info);
     if (code == 0) break;
-  } while (retryNum++ < taosHashGetSize(info->superTables));
+  } while (retryNum++ < taosHashGetSize(info->superTables) * MAX_RETRY_TIMES);
 
   if (code != 0) {
     uError("SML:0x%"PRIx64" smlModifyDBSchemas error : %s", info->id, tstrerror(code));
@@ -2332,30 +2294,48 @@ cleanup:
   return code;
 }
 
-static int32_t isSchemalessDb(SSmlHandle* info){
+static int32_t isSchemalessDb(STscObj *taos, SCatalog *catalog){
   SName          name;
-  tNameSetDbName(&name, info->taos->acctId, info->taos->db, strlen(info->taos->db));
+  tNameSetDbName(&name, taos->acctId, taos->db, strlen(taos->db));
   char dbFname[TSDB_DB_FNAME_LEN] = {0};
   tNameGetFullDbName(&name, dbFname);
   SDbCfgInfo pInfo = {0};
-  SEpSet ep = getEpSet_s(&info->taos->pAppInfo->mgmtEp);
+  SEpSet ep = getEpSet_s(&taos->pAppInfo->mgmtEp);
 
-  int32_t code = catalogGetDBCfg(info->pCatalog, info->taos->pAppInfo->pTransporter, &ep, dbFname, &pInfo);
+  int32_t code = catalogGetDBCfg(catalog, taos->pAppInfo->pTransporter, &ep, dbFname, &pInfo);
   if (code != TSDB_CODE_SUCCESS) {
-    info->pRequest->code = code;
-    smlBuildInvalidDataMsg(&info->msgBuf, "catalogGetDBCfg error, code:", tstrerror(code));
     return code;
   }
   taosArrayDestroy(pInfo.pRetensions);
   
   if (!pInfo.schemaless){
-    info->pRequest->code = TSDB_CODE_SML_INVALID_DB_CONF;
-    smlBuildInvalidDataMsg(&info->msgBuf, "can not insert into schemaless db:", dbFname);
     return TSDB_CODE_SML_INVALID_DB_CONF;
   }
   return TSDB_CODE_SUCCESS;
 }
 
+static void smlInsertCallback(void* param, void* res, int32_t code) {
+  SRequestObj *pRequest = (SRequestObj *)res;
+  SSmlHandle* info = (SSmlHandle *)param;
+
+  // lock
+  if(code != TSDB_CODE_SUCCESS){
+    taosThreadSpinLock(&info->params->lock);
+    info->params->request->code = code;
+    taosThreadSpinUnlock(&info->params->lock);
+  }
+  // unlock
+
+  printf("SML:0x%" PRIx64 " insert finished, code: %d, total: %d\n", info->id, code, info->affectedRows);
+  Params *pParam = info->params;
+  bool isLast = info->isLast;
+  smlDestroyInfo(info);
+
+  if(isLast){
+    tsem_post(&pParam->sem);
+  }
+}
+
 /**
  * taos_schemaless_insert() parse and insert data points into database according to
  * different protocol.
@@ -2384,48 +2364,95 @@ TAOS_RES* taos_schemaless_insert(TAOS* taos, char* lines[], int numLines, int pr
     return NULL;
   }
 
-  SSmlHandle* info = smlBuildSmlInfo(taos, request, (SMLProtocolType)protocol, precision);
-  if(!info){
-    return (TAOS_RES*)request;
+  ((STscObj *)taos)->schemalessType = 1;
+  SSmlMsgBuf msg = {ERROR_MSG_BUF_DEFAULT_SIZE, request->msgBuf};
+
+  int cnt = ceil(((double)numLines)/LINE_BATCH);
+  Params params;
+  params.request = request;
+  tsem_init(&params.sem, 0, 0);
+  taosThreadSpinInit(&(params.lock), 0);
+
+  int32_t code = catalogGetHandle(((STscObj *)taos)->pAppInfo->clusterId, &params.catalog);
+  if(code != TSDB_CODE_SUCCESS){
+    uError("SML get catalog error %d", code);
+    request->code = code;
+    goto end;
   }
 
-  info->taos->schemalessType = 1;
   if(request->pDb == NULL){
     request->code = TSDB_CODE_PAR_DB_NOT_SPECIFIED;
-    smlBuildInvalidDataMsg(&info->msgBuf, "Database not specified", NULL);
+    smlBuildInvalidDataMsg(&msg, "Database not specified", NULL);
     goto end;
   }
 
-  if(isSchemalessDb(info) != TSDB_CODE_SUCCESS){
+  if(isSchemalessDb(((STscObj *)taos), params.catalog) != TSDB_CODE_SUCCESS){
     request->code = TSDB_CODE_SML_INVALID_DB_CONF;
-    smlBuildInvalidDataMsg(&info->msgBuf, "Cannot write data to a non schemaless database", NULL);
+    smlBuildInvalidDataMsg(&msg, "Cannot write data to a non schemaless database", NULL);
     goto end;
   }
 
   if (!lines) {
     request->code = TSDB_CODE_SML_INVALID_DATA;
-    smlBuildInvalidDataMsg(&info->msgBuf, "lines is null", NULL);
+    smlBuildInvalidDataMsg(&msg, "lines is null", NULL);
     goto end;
   }
 
   if(protocol < TSDB_SML_LINE_PROTOCOL || protocol > TSDB_SML_JSON_PROTOCOL){
     request->code = TSDB_CODE_SML_INVALID_PROTOCOL_TYPE;
-    smlBuildInvalidDataMsg(&info->msgBuf, "protocol invalidate", NULL);
+    smlBuildInvalidDataMsg(&msg, "protocol invalidate", NULL);
     goto end;
   }
 
   if(protocol == TSDB_SML_LINE_PROTOCOL && (precision < TSDB_SML_TIMESTAMP_NOT_CONFIGURED || precision > TSDB_SML_TIMESTAMP_NANO_SECONDS)){
     request->code = TSDB_CODE_SML_INVALID_PRECISION_TYPE;
-    smlBuildInvalidDataMsg(&info->msgBuf, "precision invalidate for line protocol", NULL);
+    smlBuildInvalidDataMsg(&msg, "precision invalidate for line protocol", NULL);
     goto end;
   }
 
-  info->pRequest->code = smlProcess(info, lines, numLines);
+  for (int i = 0; i < cnt; ++i) {
+    SRequestObj* req = (SRequestObj*)createRequest((STscObj *)taos, TSDB_SQL_INSERT);
+    if(!req){
+      request->code = TSDB_CODE_OUT_OF_MEMORY;
+      uError("SML:taos_schemaless_insert error request is null");
+      goto end;
+    }
+    SSmlHandle* info = smlBuildSmlInfo(taos, req, (SMLProtocolType)protocol, precision);
+    if(!info){
+      request->code = TSDB_CODE_OUT_OF_MEMORY;
+      uError("SML:taos_schemaless_insert error SSmlHandle is null");
+      goto end;
+    }
+
+    int32_t perBatch = LINE_BATCH;
+
+    if(numLines > perBatch){
+      numLines -= perBatch;
+      info->isLast = false;
+    }else{
+      perBatch = numLines;
+      numLines = 0;
+      info->isLast = true;
+    }
+
+    info->params = &params;
+    info->pCatalog = params.catalog;
+    info->affectedRows = perBatch;
+    info->pRequest->body.queryFp = smlInsertCallback;
+    info->pRequest->body.param   = info;
+    code = smlProcess(info, lines, perBatch);
+    lines += perBatch;
+    if (code != TSDB_CODE_SUCCESS){
+      info->pRequest->body.queryFp(info, req, code);
+    }
+  }
+  tsem_wait(&params.sem);
 
 end:
-  info->taos->schemalessType = 0;
-  uDebug("result:%s", info->msgBuf.buf);
-  smlDestroyInfo(info);
+  taosThreadSpinDestroy(&params.lock);
+  tsem_destroy(&params.sem);
+  ((STscObj *)taos)->schemalessType = 0;
+  uDebug("result:%s", request->msgBuf);
   return (TAOS_RES*)request;
 }
 

source/client/src/tmq.c

@@ -1281,7 +1281,7 @@ TAOS_RES* tmq_consumer_poll(tmq_t* tmq, int64_t timeout) {
     if (rspObj) {
       return (TAOS_RES*)rspObj;
     }
-    if (timeout != 0) {
+    if (timeout != -1) {
       int64_t endTime = taosGetTimestampMs();
       int64_t leftTime = endTime - startTime;
       if (leftTime > timeout) {

source/client/test/smlTest.cpp

@@ -1325,7 +1325,7 @@ TEST(testCase, sml_oom_Test) {
   pRes = taos_query(taos, "use oom");
   taos_free_result(pRes);
 
-  TAOS_RES* res = taos_schemaless_insert(taos, (char**)sql, 100, TSDB_SML_LINE_PROTOCOL, 0);
+  TAOS_RES* res = taos_schemaless_insert(taos, (char**)sql, sizeof(sql)/sizeof(sql[0]), TSDB_SML_LINE_PROTOCOL, 0);
   ASSERT_EQ(taos_errno(res), 0);
   taos_free_result(pRes);
 }

source/common/src/systable.c

@@ -221,7 +221,7 @@ static const SSysDbTableSchema transSchema[] = {
     {.name = "db", .bytes = SYSTABLE_SCH_DB_NAME_LEN, .type = TSDB_DATA_TYPE_VARCHAR},
     {.name = "failed_times", .bytes = 4, .type = TSDB_DATA_TYPE_INT},
     {.name = "last_exec_time", .bytes = 8, .type = TSDB_DATA_TYPE_TIMESTAMP},
-    {.name = "last_error", .bytes = (TSDB_TRANS_ERROR_LEN - 1) + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
+    {.name = "last_action_info", .bytes = (TSDB_TRANS_ERROR_LEN - 1) + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
 };
 
 static const SSysDbTableSchema configSchema[] = {

source/common/src/tdatablock.c

@@ -294,7 +294,7 @@ int32_t colDataMergeCol(SColumnInfoData* pColumnInfoData, uint32_t numOfRow1, in
 
 int32_t colDataAssign(SColumnInfoData* pColumnInfoData, const SColumnInfoData* pSource, int32_t numOfRows) {
   ASSERT(pColumnInfoData != NULL && pSource != NULL && pColumnInfoData->info.type == pSource->info.type);
-  if (numOfRows == 0) {
+  if (numOfRows <= 0) {
     return numOfRows;
   }
 
@@ -322,6 +322,7 @@ int32_t colDataAssign(SColumnInfoData* pColumnInfoData, const SColumnInfoData* p
     pColumnInfoData->varmeta.length = pSource->varmeta.length;
   } else {
     char* tmp = taosMemoryRealloc(pColumnInfoData->nullbitmap, BitmapLen(numOfRows));
+    printf("----------------%d\n", BitmapLen(numOfRows));
     if (tmp == NULL) {
       return TSDB_CODE_OUT_OF_MEMORY;
     }
@@ -1219,6 +1220,8 @@ SSDataBlock* createOneDataBlock(const SSDataBlock* pDataBlock, bool copyData) {
   pBlock->info.hasVarCol = pDataBlock->info.hasVarCol;
   pBlock->info.rowSize = pDataBlock->info.rowSize;
   pBlock->info.groupId = pDataBlock->info.groupId;
+  pBlock->info.childId = pDataBlock->info.childId;
+  pBlock->info.type = pDataBlock->info.type;
 
   for (int32_t i = 0; i < numOfCols; ++i) {
     SColumnInfoData  colInfo = {0};
@@ -1237,6 +1240,9 @@ SSDataBlock* createOneDataBlock(const SSDataBlock* pDataBlock, bool copyData) {
         return NULL;
       }
 
+      if (pSrc->pData == NULL) {
+        continue;
+      }
       colDataAssign(pDst, pSrc, pDataBlock->info.rows);
     }
 
@@ -1499,6 +1505,7 @@ void blockDebugShowData(const SArray* dataBlocks, const char* flag) {
     SSDataBlock* pDataBlock = taosArrayGet(dataBlocks, i);
     int32_t      colNum = pDataBlock->info.numOfCols;
     int32_t      rows = pDataBlock->info.rows;
+    printf("%s |block type %d |child id %d|\n", flag, (int32_t)pDataBlock->info.type, pDataBlock->info.childId);
     for (int32_t j = 0; j < rows; j++) {
       printf("%s |", flag);
       for (int32_t k = 0; k < colNum; k++) {

source/dnode/mgmt/mgmt_dnode/src/dmHandle.c

@@ -38,9 +38,13 @@ static void dmProcessStatusRsp(SDnodeMgmt *pMgmt, SRpcMsg *pRsp) {
     SStatusRsp statusRsp = {0};
     if (pRsp->pCont != NULL && pRsp->contLen > 0 &&
         tDeserializeSStatusRsp(pRsp->pCont, pRsp->contLen, &statusRsp) == 0) {
-      pMgmt->pData->dnodeVer = statusRsp.dnodeVer;
-      dmUpdateDnodeCfg(pMgmt, &statusRsp.dnodeCfg);
-      dmUpdateEps(pMgmt->pData, statusRsp.pDnodeEps);
+      dTrace("status msg received from mnode, dnodeVer:%" PRId64 " saved:%" PRId64, statusRsp.dnodeVer,
+             pMgmt->pData->dnodeVer);
+      if (pMgmt->pData->dnodeVer != statusRsp.dnodeVer) {
+        pMgmt->pData->dnodeVer = statusRsp.dnodeVer;
+        dmUpdateDnodeCfg(pMgmt, &statusRsp.dnodeCfg);
+        dmUpdateEps(pMgmt->pData, statusRsp.pDnodeEps);
+      }
     }
     rpcFreeCont(pRsp->pCont);
     tFreeSStatusRsp(&statusRsp);
@@ -89,7 +93,7 @@ void dmSendStatusReq(SDnodeMgmt *pMgmt) {
   SRpcMsg rpcMsg = {.pCont = pHead, .contLen = contLen, .msgType = TDMT_MND_STATUS, .info.ahandle = (void *)0x9527};
   SRpcMsg rpcRsp = {0};
 
-  dTrace("send status msg to mnode");
+  dTrace("send status msg to mnode, dnodeVer:%" PRId64, req.dnodeVer);
 
   SEpSet epSet = {0};
   dmGetMnodeEpSet(pMgmt->pData, &epSet);

source/dnode/mgmt/mgmt_mnode/src/mmHandle.c

@@ -170,6 +170,9 @@ SArray *mmGetMsgHandles() {
   if (dmSetMgmtHandle(pArray, TDMT_MND_COMPACT_DB, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_MND_GET_DB_CFG, mmPutNodeMsgToReadQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_MND_VGROUP_LIST, mmPutNodeMsgToReadQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_MND_REDISTRIBUTE_VGROUP, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_MND_MERGE_VGROUP, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_MND_BALANCE_VGROUP, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_MND_CREATE_FUNC, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_MND_RETRIEVE_FUNC, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_MND_DROP_FUNC, mmPutNodeMsgToWriteQueue, 0) == NULL) goto _OVER;

source/dnode/mgmt/node_util/src/dmEps.c

@@ -81,6 +81,13 @@ int32_t dmReadEps(SDnodeData *pData) {
   }
   pData->dnodeId = dnodeId->valueint;
 
+  cJSON *dnodeVer = cJSON_GetObjectItem(root, "dnodeVer");
+  if (!dnodeVer || dnodeVer->type != cJSON_String) {
+    dError("failed to read %s since dnodeVer not found", file);
+    goto _OVER;
+  }
+  pData->dnodeVer = atoll(dnodeVer->valuestring);
+
   cJSON *clusterId = cJSON_GetObjectItem(root, "clusterId");
   if (!clusterId || clusterId->type != cJSON_String) {
     dError("failed to read %s since clusterId not found", file);
@@ -193,6 +200,7 @@ int32_t dmWriteEps(SDnodeData *pData) {
 
   len += snprintf(content + len, maxLen - len, "{\n");
   len += snprintf(content + len, maxLen - len, "  \"dnodeId\": %d,\n", pData->dnodeId);
+  len += snprintf(content + len, maxLen - len, "  \"dnodeVer\": \"%" PRId64 "\",\n", pData->dnodeVer);
   len += snprintf(content + len, maxLen - len, "  \"clusterId\": \"%" PRId64 "\",\n", pData->clusterId);
   len += snprintf(content + len, maxLen - len, "  \"dropped\": %d,\n", pData->dropped);
   len += snprintf(content + len, maxLen - len, "  \"dnodes\": [{\n");
@@ -224,30 +232,15 @@ int32_t dmWriteEps(SDnodeData *pData) {
   }
 
   pData->updateTime = taosGetTimestampMs();
-  dDebug("successed to write %s", realfile);
+  dDebug("successed to write %s, dnodeVer:%" PRId64, realfile, pData->dnodeVer);
   return 0;
 }
 
 void dmUpdateEps(SDnodeData *pData, SArray *eps) {
-  int32_t numOfEps = taosArrayGetSize(eps);
-  if (numOfEps <= 0) return;
-
   taosThreadRwlockWrlock(&pData->lock);
-
-  int32_t numOfEpsOld = (int32_t)taosArrayGetSize(pData->dnodeEps);
-  if (numOfEps != numOfEpsOld) {
-    dDebug("new dnode list get from mnode");
-    dmResetEps(pData, eps);
-    dmWriteEps(pData);
-  } else {
-    int32_t size = numOfEps * sizeof(SDnodeEp);
-    if (memcmp(pData->dnodeEps->pData, eps->pData, size) != 0) {
-      dDebug("new dnode list get from mnode");
-      dmResetEps(pData, eps);
-      dmWriteEps(pData);
-    }
-  }
-
+  dDebug("new dnode list get from mnode, dnodeVer:%" PRId64, pData->dnodeVer);
+  dmResetEps(pData, eps);
+  dmWriteEps(pData);
   taosThreadRwlockUnlock(&pData->lock);
 }
 

source/dnode/mnode/impl/inc/mndDef.h

@@ -120,10 +120,10 @@ typedef struct {
   SArray*        commitActions;
   int64_t        createdTime;
   int64_t        lastExecTime;
-  int32_t        lastErrorAction;
+  int32_t        lastAction;
   int32_t        lastErrorNo;
-  tmsg_t         lastErrorMsgType;
-  SEpSet         lastErrorEpset;
+  tmsg_t         lastMsgType;
+  SEpSet         lastEpset;
   char           dbname[TSDB_DB_FNAME_LEN];
   int32_t        startFunc;
   int32_t        stopFunc;
@@ -485,6 +485,7 @@ typedef struct {
   int64_t   stbUid;
   SHashObj* consumerHash;   // consumerId -> SMqConsumerEp
   SArray*   unassignedVgs;  // SArray<SMqVgEp*>
+  char      dbName[TSDB_DB_FNAME_LEN];
 } SMqSubscribeObj;
 
 SMqSubscribeObj* tNewSubscribeObj(const char key[TSDB_SUBSCRIBE_KEY_LEN]);

source/dnode/mnode/impl/inc/mndScheduler.h

@@ -29,8 +29,8 @@ int32_t mndSchedInitSubEp(SMnode* pMnode, const SMqTopicObj* pTopic, SMqSubscrib
 
 int32_t mndScheduleStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream);
 
-int32_t mndConvertRSmaTask(const char* ast, int64_t uid, int8_t triggerType, int64_t watermark, char** pStr,
-                           int32_t* pLen, double filesFactor);
+int32_t mndConvertRsmaTask(char** pDst, int32_t* pDstLen, const char* ast, int64_t uid, int8_t triggerType,
+                           int64_t watermark, double filesFactor);
 
 #ifdef __cplusplus
 }

source/dnode/mnode/impl/inc/mndVgroup.h

@@ -29,6 +29,7 @@ void     mndReleaseVgroup(SMnode *pMnode, SVgObj *pVgroup);
 SSdbRaw *mndVgroupActionEncode(SVgObj *pVgroup);
 SEpSet   mndGetVgroupEpset(SMnode *pMnode, const SVgObj *pVgroup);
 int32_t  mndGetVnodesNum(SMnode *pMnode, int32_t dnodeId);
+void     mndSortVnodeGid(SVgObj *pVgroup);
 
 SArray *mndBuildDnodesArray(SMnode *, int32_t exceptDnodeId);
 int32_t mndAllocSmaVgroup(SMnode *, SDbObj *pDb, SVgObj *pVgroup);

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

@@ -35,7 +35,7 @@
 
 #define MND_CONSUMER_LOST_HB_CNT 3
 
-static int8_t mqRebLock = 0;
+static int8_t mqRebInExecCnt = 0;
 
 static const char *mndConsumerStatusName(int status);
 
@@ -76,15 +76,15 @@ int32_t mndInitConsumer(SMnode *pMnode) {
 void mndCleanupConsumer(SMnode *pMnode) {}
 
 bool mndRebTryStart() {
-  int8_t old = atomic_val_compare_exchange_8(&mqRebLock, 0, 1);
+  int8_t old = atomic_val_compare_exchange_8(&mqRebInExecCnt, 0, 1);
   return old == 0;
 }
 
-void mndRebEnd() { atomic_sub_fetch_8(&mqRebLock, 1); }
+void mndRebEnd() { atomic_sub_fetch_8(&mqRebInExecCnt, 1); }
 
-void mndRebCntInc() { atomic_add_fetch_8(&mqRebLock, 1); }
+void mndRebCntInc() { atomic_add_fetch_8(&mqRebInExecCnt, 1); }
 
-void mndRebCntDec() { atomic_sub_fetch_8(&mqRebLock, 1); }
+void mndRebCntDec() { atomic_sub_fetch_8(&mqRebInExecCnt, 1); }
 
 static int32_t mndProcessConsumerLostMsg(SRpcMsg *pMsg) {
   SMnode             *pMnode = pMsg->info.node;
@@ -92,7 +92,6 @@ static int32_t mndProcessConsumerLostMsg(SRpcMsg *pMsg) {
   SMqConsumerObj     *pConsumer = mndAcquireConsumer(pMnode, pLostMsg->consumerId);
   ASSERT(pConsumer);
 
-
   mInfo("receive consumer lost msg, consumer id %ld, status %s", pLostMsg->consumerId,
         mndConsumerStatusName(pConsumer->status));
 
@@ -106,7 +105,7 @@ static int32_t mndProcessConsumerLostMsg(SRpcMsg *pMsg) {
 
   mndReleaseConsumer(pMnode, pConsumer);
 
-  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_RETRY, TRN_CONFLICT_NOTHING, pMsg);
+  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_ROLLBACK, TRN_CONFLICT_NOTHING, pMsg);
   if (pTrans == NULL) goto FAIL;
   if (mndSetConsumerCommitLogs(pMnode, pTrans, pConsumerNew) != 0) goto FAIL;
   if (mndTransPrepare(pMnode, pTrans) != 0) goto FAIL;
@@ -125,6 +124,14 @@ static int32_t mndProcessConsumerRecoverMsg(SRpcMsg *pMsg) {
   SMqConsumerObj        *pConsumer = mndAcquireConsumer(pMnode, pRecoverMsg->consumerId);
   ASSERT(pConsumer);
 
+  mInfo("receive consumer recover msg, consumer id %ld, status %s", pRecoverMsg->consumerId,
+        mndConsumerStatusName(pConsumer->status));
+
+  if (pConsumer->status != MQ_CONSUMER_STATUS__READY) {
+    mndReleaseConsumer(pMnode, pConsumer);
+    return -1;
+  }
+
   SMqConsumerObj *pConsumerNew = tNewSMqConsumerObj(pConsumer->consumerId, pConsumer->cgroup);
   pConsumerNew->updateType = CONSUMER_UPDATE__RECOVER;
 
@@ -440,6 +447,8 @@ static int32_t mndProcessSubscribeReq(SRpcMsg *pMsg) {
 
   pConsumerOld = mndAcquireConsumer(pMnode, consumerId);
   if (pConsumerOld == NULL) {
+    mInfo("receive subscribe request from new consumer: %ld", consumerId);
+
     pConsumerNew = tNewSMqConsumerObj(consumerId, cgroup);
     tstrncpy(pConsumerNew->clientId, subscribe.clientId, 256);
     pConsumerNew->updateType = CONSUMER_UPDATE__MODIFY;
@@ -456,7 +465,12 @@ static int32_t mndProcessSubscribeReq(SRpcMsg *pMsg) {
 
   } else {
     /*taosRLockLatch(&pConsumerOld->lock);*/
+
     int32_t status = atomic_load_32(&pConsumerOld->status);
+
+    mInfo("receive subscribe request from old consumer: %ld, current status: %s", consumerId,
+          mndConsumerStatusName(status));
+
     if (status != MQ_CONSUMER_STATUS__READY) {
       terrno = TSDB_CODE_MND_CONSUMER_NOT_READY;
       goto SUBSCRIBE_OVER;
@@ -844,10 +858,11 @@ static int32_t mndRetrieveConsumer(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *
       topicSz = 1;
     }
 
+    if (numOfRows + topicSz > rowsCapacity) {
+      blockDataEnsureCapacity(pBlock, numOfRows + topicSz);
+    }
+
     for (int32_t i = 0; i < topicSz; i++) {
-      if (numOfRows + topicSz > rowsCapacity) {
-        blockDataEnsureCapacity(pBlock, numOfRows + topicSz);
-      }
       SColumnInfoData *pColInfo;
       int32_t          cols = 0;
 

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

@@ -415,6 +415,7 @@ SMqSubscribeObj *tCloneSubscribeObj(const SMqSubscribeObj *pSub) {
     taosHashPut(pSubNew->consumerHash, &newEp.consumerId, sizeof(int64_t), &newEp, sizeof(SMqConsumerEp));
   }
   pSubNew->unassignedVgs = taosArrayDeepCopy(pSub->unassignedVgs, (FCopy)tCloneSMqVgEp);
+  memcpy(pSubNew->dbName, pSub->dbName, TSDB_DB_FNAME_LEN);
   return pSubNew;
 }
 
@@ -445,6 +446,7 @@ int32_t tEncodeSubscribeObj(void **buf, const SMqSubscribeObj *pSub) {
   }
   ASSERT(cnt == sz);
   tlen += taosEncodeArray(buf, pSub->unassignedVgs, (FEncode)tEncodeSMqVgEp);
+  tlen += taosEncodeString(buf, pSub->dbName);
   return tlen;
 }
 
@@ -467,6 +469,7 @@ void *tDecodeSubscribeObj(const void *buf, SMqSubscribeObj *pSub) {
   }
 
   buf = taosDecodeArray(buf, &pSub->unassignedVgs, (FDecode)tDecodeSMqVgEp, sizeof(SMqVgEp));
+  buf = taosDecodeStringTo(buf, pSub->dbName);
   return (void *)buf;
 }
 

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

@@ -385,7 +385,7 @@ static int32_t mndProcessStatusReq(SRpcMsg *pReq) {
   int64_t dnodeVer = sdbGetTableVer(pMnode->pSdb, SDB_DNODE) + sdbGetTableVer(pMnode->pSdb, SDB_MNODE);
   int64_t curMs = taosGetTimestampMs();
   bool    online = mndIsDnodeOnline(pDnode, curMs);
-  bool    dnodeChanged = (statusReq.dnodeVer != dnodeVer);
+  bool    dnodeChanged = (statusReq.dnodeVer == 0) || (statusReq.dnodeVer != dnodeVer);
   bool    reboot = (pDnode->rebootTime != statusReq.rebootTime);
   bool    needCheck = !online || dnodeChanged || reboot;
 
@@ -427,7 +427,7 @@ static int32_t mndProcessStatusReq(SRpcMsg *pReq) {
     if (!online) {
       mInfo("dnode:%d, from offline to online", pDnode->id);
     } else {
-      mDebug("dnode:%d, send dnode epset, online:%d dnode_ver:%" PRId64 ":%" PRId64 " reboot:%d", pDnode->id, online,
+      mDebug("dnode:%d, send dnode epset, online:%d dnodeVer:%" PRId64 ":%" PRId64 " reboot:%d", pDnode->id, online,
              statusReq.dnodeVer, dnodeVer, reboot);
     }
 

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

@@ -217,8 +217,8 @@ static int32_t mndInitSteps(SMnode *pMnode) {
   if (mndAllocStep(pMnode, "mnode-cluster", mndInitCluster, mndCleanupCluster) != 0) return -1;
   if (mndAllocStep(pMnode, "mnode-mnode", mndInitMnode, mndCleanupMnode) != 0) return -1;
   if (mndAllocStep(pMnode, "mnode-qnode", mndInitQnode, mndCleanupQnode) != 0) return -1;
-  if (mndAllocStep(pMnode, "mnode-qnode", mndInitSnode, mndCleanupSnode) != 0) return -1;
-  if (mndAllocStep(pMnode, "mnode-qnode", mndInitBnode, mndCleanupBnode) != 0) return -1;
+  if (mndAllocStep(pMnode, "mnode-snode", mndInitSnode, mndCleanupSnode) != 0) return -1;
+  if (mndAllocStep(pMnode, "mnode-bnode", mndInitBnode, mndCleanupBnode) != 0) return -1;
   if (mndAllocStep(pMnode, "mnode-dnode", mndInitDnode, mndCleanupDnode) != 0) return -1;
   if (mndAllocStep(pMnode, "mnode-user", mndInitUser, mndCleanupUser) != 0) return -1;
   if (mndAllocStep(pMnode, "mnode-grant", mndInitGrant, mndCleanupGrant) != 0) return -1;
@@ -403,6 +403,10 @@ int32_t mndProcessSyncMsg(SRpcMsg *pMsg) {
   char  logBuf[512] = {0};
   char *syncNodeStr = sync2SimpleStr(pMgmt->sync);
   snprintf(logBuf, sizeof(logBuf), "==vnodeProcessSyncReq== msgType:%d, syncNode: %s", pMsg->msgType, syncNodeStr);
+  static int64_t mndTick = 0;
+  if (++mndTick % 10 == 1) {
+    mTrace("sync trace msg:%s, %s", TMSG_INFO(pMsg->msgType), syncNodeStr);
+  }
   syncRpcMsgLog2(logBuf, pMsg);
   taosMemoryFree(syncNodeStr);
 

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

@@ -183,7 +183,10 @@ static int32_t mndProcessCommitOffsetReq(SRpcMsg *pMsg) {
 
   for (int32_t i = 0; i < commitOffsetReq.num; i++) {
     SMqOffset *pOffset = &commitOffsetReq.offsets[i];
+    mInfo("commit offset %ld to vg %d of consumer group %s on topic %s", pOffset->offset, pOffset->vgId,
+          pOffset->cgroup, pOffset->topicName);
     if (mndMakePartitionKey(key, pOffset->cgroup, pOffset->topicName, pOffset->vgId) < 0) {
+      mError("submit offset to topic %s failed", pOffset->topicName);
       return -1;
     }
     bool          create = false;
@@ -192,7 +195,7 @@ static int32_t mndProcessCommitOffsetReq(SRpcMsg *pMsg) {
       SMqTopicObj *pTopic = mndAcquireTopic(pMnode, pOffset->topicName);
       if (pTopic == NULL) {
         terrno = TSDB_CODE_MND_TOPIC_NOT_EXIST;
-        mError("submit offset to topic %s failed since  %s", pOffset->topicName, terrstr());
+        mError("submit offset to topic %s failed since %s", pOffset->topicName, terrstr());
         continue;
       }
       pOffsetObj = taosMemoryMalloc(sizeof(SMqOffsetObj));

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

@@ -42,8 +42,8 @@ static int32_t mndAddTaskToTaskSet(SArray* pArray, SStreamTask* pTask) {
   return 0;
 }
 
-int32_t mndConvertRSmaTask(const char* ast, int64_t uid, int8_t triggerType, int64_t watermark, char** pStr,
-                           int32_t* pLen, double filesFactor) {
+int32_t mndConvertRsmaTask(char** pDst, int32_t* pDstLen, const char* ast, int64_t uid, int8_t triggerType,
+                           int64_t watermark, double filesFactor) {
   SNode*      pAst = NULL;
   SQueryPlan* pPlan = NULL;
   terrno = TSDB_CODE_SUCCESS;
@@ -53,7 +53,7 @@ int32_t mndConvertRSmaTask(const char* ast, int64_t uid, int8_t triggerType, int
     goto END;
   }
 
-  if (qSetSTableIdForRSma(pAst, uid) < 0) {
+  if (qSetSTableIdForRsma(pAst, uid) < 0) {
     terrno = TSDB_CODE_QRY_INVALID_INPUT;
     goto END;
   }
@@ -86,7 +86,7 @@ int32_t mndConvertRSmaTask(const char* ast, int64_t uid, int8_t triggerType, int
   }
 
   SSubplan* plan = nodesListGetNode(inner->pNodeList, 0);
-  if (qSubPlanToString(plan, pStr, pLen) < 0) {
+  if (qSubPlanToString(plan, pDst, pDstLen) < 0) {
     terrno = TSDB_CODE_QRY_INVALID_INPUT;
     goto END;
   }
@@ -127,6 +127,61 @@ int32_t mndPersistTaskDeployReq(STrans* pTrans, SStreamTask* pTask, const SEpSet
   return 0;
 }
 
+int32_t mndAddSinkToTask(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream, SStreamTask* pTask) {
+  pTask->dispatchType = TASK_DISPATCH__NONE;
+  // sink
+  if (pStream->createdBy == STREAM_CREATED_BY__SMA) {
+    pTask->sinkType = TASK_SINK__SMA;
+    pTask->smaSink.smaId = pStream->smaId;
+  } else {
+    pTask->sinkType = TASK_SINK__TABLE;
+    pTask->tbSink.stbUid = pStream->targetStbUid;
+    memcpy(pTask->tbSink.stbFullName, pStream->targetSTbName, TSDB_TABLE_FNAME_LEN);
+    pTask->tbSink.pSchemaWrapper = tCloneSSchemaWrapper(&pStream->outputSchema);
+  }
+  return 0;
+}
+
+int32_t mndAddDispatcherToInnerTask(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream, SStreamTask* pTask) {
+  pTask->sinkType = TASK_SINK__NONE;
+  if (pStream->fixedSinkVgId == 0) {
+    pTask->dispatchType = TASK_DISPATCH__SHUFFLE;
+    pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
+    SDbObj* pDb = mndAcquireDb(pMnode, pStream->targetDb);
+    ASSERT(pDb);
+
+    if (mndExtractDbInfo(pMnode, pDb, &pTask->shuffleDispatcher.dbInfo, NULL) < 0) {
+      sdbRelease(pMnode->pSdb, pDb);
+
+      SArray* pVgs = pTask->shuffleDispatcher.dbInfo.pVgroupInfos;
+      int32_t sz = taosArrayGetSize(pVgs);
+      SArray* sinkLv = taosArrayGetP(pStream->tasks, 0);
+      int32_t sinkLvSize = taosArrayGetSize(sinkLv);
+      for (int32_t i = 0; i < sz; i++) {
+        SVgroupInfo* pVgInfo = taosArrayGet(pVgs, i);
+        for (int32_t j = 0; j < sinkLvSize; j++) {
+          SStreamTask* pLastLevelTask = taosArrayGetP(sinkLv, j);
+          if (pLastLevelTask->nodeId == pVgInfo->vgId) {
+            pVgInfo->taskId = pLastLevelTask->taskId;
+            break;
+          }
+        }
+      }
+    }
+  } else {
+    pTask->dispatchType = TASK_DISPATCH__FIXED;
+    pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
+    SArray* pArray = taosArrayGetP(pStream->tasks, 0);
+    // one sink only
+    ASSERT(taosArrayGetSize(pArray) == 1);
+    SStreamTask* lastLevelTask = taosArrayGetP(pArray, 0);
+    pTask->fixedEpDispatcher.taskId = lastLevelTask->taskId;
+    pTask->fixedEpDispatcher.nodeId = lastLevelTask->nodeId;
+    pTask->fixedEpDispatcher.epSet = lastLevelTask->epSet;
+  }
+  return 0;
+}
+
 int32_t mndAssignTaskToVg(SMnode* pMnode, STrans* pTrans, SStreamTask* pTask, SSubplan* plan, const SVgObj* pVgroup) {
   int32_t msgLen;
   pTask->nodeId = pVgroup->vgId;
@@ -139,6 +194,7 @@ int32_t mndAssignTaskToVg(SMnode* pMnode, STrans* pTrans, SStreamTask* pTask, SS
     terrno = TSDB_CODE_QRY_INVALID_INPUT;
     return -1;
   }
+  ASSERT(pTask->dispatchType != TASK_DISPATCH__NONE || pTask->sinkType != TASK_SINK__NONE);
   mndPersistTaskDeployReq(pTrans, pTask, &plan->execNode.epSet, TDMT_STREAM_TASK_DEPLOY, pVgroup->vgId);
   return 0;
 }
@@ -182,7 +238,7 @@ SVgObj* mndSchedFetchOneVg(SMnode* pMnode, int64_t dbUid) {
   return pVgroup;
 }
 
-int32_t mndAddShuffledSinkToStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
+int32_t mndAddShuffleSinkTasksToStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
   SSdb*   pSdb = pMnode->pSdb;
   void*   pIter = NULL;
   SArray* tasks = taosArrayGetP(pStream->tasks, 0);
@@ -234,7 +290,7 @@ int32_t mndAddShuffledSinkToStream(SMnode* pMnode, STrans* pTrans, SStreamObj* p
   return 0;
 }
 
-int32_t mndAddFixedSinkToStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
+int32_t mndAddFixedSinkTaskToStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
   ASSERT(pStream->fixedSinkVgId != 0);
   SArray*      tasks = taosArrayGetP(pStream->tasks, 0);
   SStreamTask* pTask = tNewSStreamTask(pStream->uid);
@@ -300,177 +356,92 @@ int32_t mndScheduleStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
     // add extra sink
     hasExtraSink = true;
     if (pStream->fixedSinkVgId == 0) {
-      mndAddShuffledSinkToStream(pMnode, pTrans, pStream);
+      mndAddShuffleSinkTasksToStream(pMnode, pTrans, pStream);
     } else {
-      mndAddFixedSinkToStream(pMnode, pTrans, pStream);
+      mndAddFixedSinkTaskToStream(pMnode, pTrans, pStream);
     }
   }
 
-  for (int32_t level = 0; level < totLevel; level++) {
-    SArray*        taskOneLevel = taosArrayInit(0, sizeof(void*));
-    SNodeListNode* inner = nodesListGetNode(pPlan->pSubplans, level);
-    ASSERT(LIST_LENGTH(inner->pNodeList) == 1);
+  if (totLevel > 1) {
+    SStreamTask* pFinalTask;
+    // inner plan
+    {
+      SArray* taskInnerLevel = taosArrayInit(0, sizeof(void*));
+      taosArrayPush(pStream->tasks, &taskInnerLevel);
 
-    SSubplan* plan = nodesListGetNode(inner->pNodeList, 0);
+      SNodeListNode* inner = nodesListGetNode(pPlan->pSubplans, 0);
+      SSubplan*      plan = nodesListGetNode(inner->pNodeList, 0);
+      ASSERT(plan->subplanType == SUBPLAN_TYPE_MERGE);
 
-    // if (level == totLevel - 1 /* or no snode */) {
-    if (level == totLevel - 1) {
-      // last level, source, must assign to vnode
-      // must be scan type
-      ASSERT(plan->subplanType == SUBPLAN_TYPE_SCAN);
-
-      // replicate task to each vnode
-      void* pIter = NULL;
-      while (1) {
-        SVgObj* pVgroup;
-        pIter = sdbFetch(pSdb, SDB_VGROUP, pIter, (void**)&pVgroup);
-        if (pIter == NULL) break;
-        if (pVgroup->dbUid != pStream->dbUid) {
-          sdbRelease(pSdb, pVgroup);
-          continue;
-        }
-        SStreamTask* pTask = tNewSStreamTask(pStream->uid);
-        mndAddTaskToTaskSet(taskOneLevel, pTask);
-        // source part
-        pTask->sourceType = TASK_SOURCE__SCAN;
-        pTask->inputType = TASK_INPUT_TYPE__SUMBIT_BLOCK;
-
-        // sink part
-        if (level == 0) {
-          // only for inplace
-          pTask->sinkType = TASK_SINK__NONE;
-          if (!hasExtraSink) {
-#if 1
-            if (pStream->createdBy == STREAM_CREATED_BY__SMA) {
-              pTask->sinkType = TASK_SINK__SMA;
-              pTask->smaSink.smaId = pStream->smaId;
-            } else {
-              pTask->sinkType = TASK_SINK__TABLE;
-              pTask->tbSink.stbUid = pStream->targetStbUid;
-              memcpy(pTask->tbSink.stbFullName, pStream->targetSTbName, TSDB_TABLE_FNAME_LEN);
-              pTask->tbSink.pSchemaWrapper = tCloneSSchemaWrapper(&pStream->outputSchema);
-            }
-#endif
-          }
-        } else {
-          pTask->sinkType = TASK_SINK__NONE;
-        }
+      pFinalTask = tNewSStreamTask(pStream->uid);
+      mndAddTaskToTaskSet(taskInnerLevel, pFinalTask);
+      // input
+      pFinalTask->inputType = TASK_INPUT_TYPE__DATA_BLOCK;
 
-        // dispatch part
-        if (level == 0) {
-          pTask->dispatchType = TASK_DISPATCH__NONE;
-        } else {
-          // add fixed ep dispatcher
-          int32_t lastLevel = level - 1;
-          ASSERT(lastLevel == 0);
-          if (hasExtraSink) lastLevel++;
-          SArray* pArray = taosArrayGetP(pStream->tasks, lastLevel);
-          // one merge only
-          ASSERT(taosArrayGetSize(pArray) == 1);
-          SStreamTask* lastLevelTask = taosArrayGetP(pArray, 0);
-          /*pTask->dispatchMsgType = TDMT_VND_TASK_MERGE_EXEC;*/
-          pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
-          pTask->dispatchType = TASK_DISPATCH__FIXED;
-
-          pTask->fixedEpDispatcher.taskId = lastLevelTask->taskId;
-          pTask->fixedEpDispatcher.nodeId = lastLevelTask->nodeId;
-          pTask->fixedEpDispatcher.epSet = lastLevelTask->epSet;
-        }
+      // dispatch
+      mndAddDispatcherToInnerTask(pMnode, pTrans, pStream, pFinalTask);
 
-        // exec part
-        pTask->execType = TASK_EXEC__PIPE;
-        if (mndAssignTaskToVg(pMnode, pTrans, pTask, plan, pVgroup) < 0) {
-          sdbRelease(pSdb, pVgroup);
-          qDestroyQueryPlan(pPlan);
-          return -1;
-        }
+      // exec
+      pFinalTask->execType = TASK_EXEC__PIPE;
+      SVgObj* pVgroup = mndSchedFetchOneVg(pMnode, pStream->dbUid);
+      if (mndAssignTaskToVg(pMnode, pTrans, pFinalTask, plan, pVgroup) < 0) {
         sdbRelease(pSdb, pVgroup);
+        qDestroyQueryPlan(pPlan);
+        return -1;
       }
-    } else {
-      // merge plan
+    }
 
-      // TODO if has snode, assign to snode
+    // source plan
+    SArray* taskSourceLevel = taosArrayInit(0, sizeof(void*));
+    taosArrayPush(pStream->tasks, &taskSourceLevel);
 
-      // else, assign to vnode
-      ASSERT(plan->subplanType == SUBPLAN_TYPE_MERGE);
+    SNodeListNode* inner = nodesListGetNode(pPlan->pSubplans, 1);
+    SSubplan*      plan = nodesListGetNode(inner->pNodeList, 0);
+    ASSERT(plan->subplanType == SUBPLAN_TYPE_SCAN);
+
+    void* pIter = NULL;
+    while (1) {
+      SVgObj* pVgroup;
+      pIter = sdbFetch(pSdb, SDB_VGROUP, pIter, (void**)&pVgroup);
+      if (pIter == NULL) break;
+      if (pVgroup->dbUid != pStream->dbUid) {
+        sdbRelease(pSdb, pVgroup);
+        continue;
+      }
       SStreamTask* pTask = tNewSStreamTask(pStream->uid);
-      mndAddTaskToTaskSet(taskOneLevel, pTask);
+      mndAddTaskToTaskSet(taskSourceLevel, pTask);
 
-      // source part, currently only support multi source
-      pTask->sourceType = TASK_SOURCE__PIPE;
-      pTask->inputType = TASK_INPUT_TYPE__DATA_BLOCK;
+      // input
+      pTask->inputType = TASK_INPUT_TYPE__SUMBIT_BLOCK;
 
-      // sink part
+      // add fixed vg dispatch
       pTask->sinkType = TASK_SINK__NONE;
+      pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
+      pTask->dispatchType = TASK_DISPATCH__FIXED;
 
-      // dispatch part
-      ASSERT(hasExtraSink);
-      /*pTask->dispatchType = TASK_DISPATCH__NONE;*/
-#if 1
-
-      if (hasExtraSink) {
-        // add dispatcher
-        if (pStream->fixedSinkVgId == 0) {
-          pTask->dispatchType = TASK_DISPATCH__SHUFFLE;
-
-          pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
-          SDbObj* pDb = mndAcquireDb(pMnode, pStream->targetDb);
-          ASSERT(pDb);
-          if (mndExtractDbInfo(pMnode, pDb, &pTask->shuffleDispatcher.dbInfo, NULL) < 0) {
-            sdbRelease(pSdb, pDb);
-            qDestroyQueryPlan(pPlan);
-            return -1;
-          }
-          sdbRelease(pSdb, pDb);
-
-          // put taskId to useDbRsp
-          // TODO: optimize
-          SArray* pVgs = pTask->shuffleDispatcher.dbInfo.pVgroupInfos;
-          int32_t sz = taosArrayGetSize(pVgs);
-          SArray* sinkLv = taosArrayGetP(pStream->tasks, 0);
-          int32_t sinkLvSize = taosArrayGetSize(sinkLv);
-          for (int32_t i = 0; i < sz; i++) {
-            SVgroupInfo* pVgInfo = taosArrayGet(pVgs, i);
-            for (int32_t j = 0; j < sinkLvSize; j++) {
-              SStreamTask* pLastLevelTask = taosArrayGetP(sinkLv, j);
-              if (pLastLevelTask->nodeId == pVgInfo->vgId) {
-                pVgInfo->taskId = pLastLevelTask->taskId;
-                break;
-              }
-            }
-          }
-        } else {
-          pTask->dispatchType = TASK_DISPATCH__FIXED;
-          /*pTask->dispatchMsgType = TDMT_VND_TASK_WRITE_EXEC;*/
-          pTask->dispatchMsgType = TDMT_STREAM_TASK_DISPATCH;
-          SArray* pArray = taosArrayGetP(pStream->tasks, 0);
-          // one sink only
-          ASSERT(taosArrayGetSize(pArray) == 1);
-          SStreamTask* lastLevelTask = taosArrayGetP(pArray, 0);
-          pTask->fixedEpDispatcher.taskId = lastLevelTask->taskId;
-          pTask->fixedEpDispatcher.nodeId = lastLevelTask->nodeId;
-          pTask->fixedEpDispatcher.epSet = lastLevelTask->epSet;
-        }
-      }
-#endif
+      pTask->fixedEpDispatcher.taskId = pFinalTask->taskId;
+      pTask->fixedEpDispatcher.nodeId = pFinalTask->nodeId;
+      pTask->fixedEpDispatcher.epSet = pFinalTask->epSet;
 
-      // exec part
-      pTask->execType = TASK_EXEC__MERGE;
-      SVgObj* pVgroup = mndSchedFetchOneVg(pMnode, pStream->dbUid);
-      ASSERT(pVgroup);
+      // exec
+      pTask->execType = TASK_EXEC__PIPE;
       if (mndAssignTaskToVg(pMnode, pTrans, pTask, plan, pVgroup) < 0) {
         sdbRelease(pSdb, pVgroup);
         qDestroyQueryPlan(pPlan);
         return -1;
       }
-      sdbRelease(pSdb, pVgroup);
     }
+  }
 
+  if (totLevel == 1) {
+    SArray* taskOneLevel = taosArrayInit(0, sizeof(void*));
     taosArrayPush(pStream->tasks, &taskOneLevel);
-  }
 
-#if 0
-  if (totLevel == 2) {
+    SNodeListNode* inner = nodesListGetNode(pPlan->pSubplans, 0);
+    ASSERT(LIST_LENGTH(inner->pNodeList) == 1);
+    SSubplan* plan = nodesListGetNode(inner->pNodeList, 0);
+    ASSERT(plan->subplanType == SUBPLAN_TYPE_SCAN);
+
     void* pIter = NULL;
     while (1) {
       SVgObj* pVgroup;
@@ -481,26 +452,28 @@ int32_t mndScheduleStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
         continue;
       }
       SStreamTask* pTask = tNewSStreamTask(pStream->uid);
+      mndAddTaskToTaskSet(taskOneLevel, pTask);
 
-      // source part
-      pTask->sourceType = TASK_SOURCE__MERGE;
-      pTask->inputType = TASK_INPUT_TYPE__DATA_BLOCK;
+      // input
+      pTask->inputType = TASK_INPUT_TYPE__SUMBIT_BLOCK;
 
-      // sink part
-      pTask->sinkType = TASK_SINK__NONE;
-
-      // dispatch part
-      pTask->dispatchType = TASK_DISPATCH__NONE;
+      // sink or dispatch
+      if (hasExtraSink) {
+        mndAddDispatcherToInnerTask(pMnode, pTrans, pStream, pTask);
+      } else {
+        mndAddSinkToTask(pMnode, pTrans, pStream, pTask);
+      }
 
-      // exec part
-      pTask->execType = TASK_EXEC__NONE;
+      // exec
+      pTask->execType = TASK_EXEC__PIPE;
+      if (mndAssignTaskToVg(pMnode, pTrans, pTask, plan, pVgroup) < 0) {
+        sdbRelease(pSdb, pVgroup);
+        qDestroyQueryPlan(pPlan);
+        return -1;
+      }
     }
   }
-#endif
-
-  // free memory
   qDestroyQueryPlan(pPlan);
-
   return 0;
 }
 

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

@@ -395,13 +395,13 @@ static void *mndBuildVCreateStbReq(SMnode *pMnode, SVgObj *pVgroup, SStbObj *pSt
     req.pRSmaParam.xFilesFactor = pStb->xFilesFactor;
     req.pRSmaParam.delay = pStb->delay;
     if (pStb->ast1Len > 0) {
-      if (mndConvertRSmaTask(pStb->pAst1, pStb->uid, 0, 0, &req.pRSmaParam.qmsg1, &req.pRSmaParam.qmsg1Len,
+      if (mndConvertRsmaTask(&req.pRSmaParam.qmsg1, &req.pRSmaParam.qmsg1Len, pStb->pAst1, pStb->uid, STREAM_TRIGGER_AT_ONCE, 0,
                              req.pRSmaParam.xFilesFactor) != TSDB_CODE_SUCCESS) {
         return NULL;
       }
     }
     if (pStb->ast2Len > 0) {
-      if (mndConvertRSmaTask(pStb->pAst2, pStb->uid, 0, 0, &req.pRSmaParam.qmsg2, &req.pRSmaParam.qmsg2Len,
+      if (mndConvertRsmaTask(&req.pRSmaParam.qmsg2, &req.pRSmaParam.qmsg2Len, pStb->pAst2, pStb->uid, STREAM_TRIGGER_AT_ONCE, 0,
                              req.pRSmaParam.xFilesFactor) != TSDB_CODE_SUCCESS) {
         return NULL;
       }

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

@@ -402,7 +402,8 @@ static int32_t mndDoRebalance(SMnode *pMnode, const SMqRebInputObj *pInput, SMqR
 }
 
 static int32_t mndPersistRebResult(SMnode *pMnode, SRpcMsg *pMsg, const SMqRebOutputObj *pOutput) {
-  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_ROLLBACK, TRN_CONFLICT_NOTHING, pMsg);
+  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_ROLLBACK, TRN_CONFLICT_DB_INSIDE, pMsg);
+  mndTransSetDbName(pTrans, pOutput->pSub->dbName);
   if (pTrans == NULL) return -1;
 
   // make txn:
@@ -547,6 +548,7 @@ static int32_t mndProcessRebalanceReq(SRpcMsg *pMsg) {
       taosRLockLatch(&pTopic->lock);
 
       rebOutput.pSub = mndCreateSub(pMnode, pTopic, pRebInfo->key);
+      memcpy(rebOutput.pSub->dbName, pTopic->db, TSDB_DB_FNAME_LEN);
       ASSERT(taosHashGetSize(rebOutput.pSub->consumerHash) == 0);
 
       taosRUnLockLatch(&pTopic->lock);

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

@@ -96,10 +96,18 @@ void mndRestoreFinish(struct SSyncFSM *pFsm) {
   }
 }
 
-void mndReConfig(struct SSyncFSM *pFsm, SSyncCfg newCfg, SReConfigCbMeta cbMeta) {
+void mndReConfig(struct SSyncFSM *pFsm, const SRpcMsg *pMsg, SReConfigCbMeta cbMeta) {
   SMnode    *pMnode = pFsm->data;
   SSyncMgmt *pMgmt = &pMnode->syncMgmt;
 
+#if 0
+// send response
+  SRpcMsg rpcMsg = {.msgType = pMsg->msgType, .contLen = pMsg->contLen, .conn.applyIndex = cbMeta.index};
+  rpcMsg.pCont = rpcMallocCont(rpcMsg.contLen);
+  memcpy(rpcMsg.pCont, pMsg->pCont, pMsg->contLen);
+  syncGetAndDelRespRpc(pMnode->syncMgmt.sync, cbMeta.seqNum, &rpcMsg.info);
+#endif
+
   pMgmt->errCode = cbMeta.code;
   mInfo("trans:-1, sync reconfig is proposed, saved:%d code:0x%x, index:%" PRId64 " term:%" PRId64, pMgmt->transId,
         cbMeta.code, cbMeta.index, cbMeta.term);
@@ -192,14 +200,14 @@ int32_t mndInitSync(SMnode *pMnode) {
     return -1;
   }
 
-  mDebug("mnode sync is opened, id:%" PRId64, pMgmt->sync);
+  mDebug("mnode-sync is opened, id:%" PRId64, pMgmt->sync);
   return 0;
 }
 
 void mndCleanupSync(SMnode *pMnode) {
   SSyncMgmt *pMgmt = &pMnode->syncMgmt;
   syncStop(pMgmt->sync);
-  mDebug("mnode sync is stopped, id:%" PRId64, pMgmt->sync);
+  mDebug("mnode-sync is stopped, id:%" PRId64, pMgmt->sync);
 
   tsem_destroy(&pMgmt->syncSem);
   memset(pMgmt, 0, sizeof(SSyncMgmt));

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

@@ -87,30 +87,22 @@ int32_t mndCheckColAndTagModifiable(SMnode *pMnode, int64_t suid, col_id_t colId
     SNode *pAst = NULL;
     if (nodesStringToNode(pTopic->ast, &pAst) != 0) {
       ASSERT(0);
-      return false;
+      return -1;
     }
 
-    SHashObj  *pColHash = NULL;
     SNodeList *pNodeList = NULL;
     nodesCollectColumns((SSelectStmt *)pAst, SQL_CLAUSE_FROM, NULL, COLLECT_COL_TYPE_ALL, &pNodeList);
     SNode *pNode = NULL;
     FOREACH(pNode, pNodeList) {
       SColumnNode *pCol = (SColumnNode *)pNode;
       if (pCol->tableId != suid) goto NEXT;
-      if (pColHash == NULL) {
-        pColHash = taosHashInit(0, taosGetDefaultHashFunction(TSDB_DATA_TYPE_SMALLINT), false, HASH_NO_LOCK);
-      }
-      if (pCol->colId > 0) {
-        taosHashPut(pColHash, &pCol->colId, sizeof(int16_t), NULL, 0);
+      if (pCol->colId > 0 && pCol->colId == colId) {
+        found = true;
+        goto NEXT;
       }
       mTrace("topic:%s, colId:%d is used", pTopic->name, pCol->colId);
     }
 
-    if (taosHashGet(pColHash, &colId, sizeof(int16_t)) != NULL) {
-      found = true;
-      goto NEXT;
-    }
-
   NEXT:
     sdbRelease(pSdb, pTopic);
     nodesDestroyNode(pAst);
@@ -563,7 +555,7 @@ static int32_t mndProcessDropTopicReq(SRpcMsg *pReq) {
         mndReleaseConsumer(pMnode, pConsumer);
         mndReleaseTopic(pMnode, pTopic);
         terrno = TSDB_CODE_MND_TOPIC_SUBSCRIBED;
-        mError("topic:%s, failed to drop since subscribed by consumer %ld from cgroup %s", dropReq.name,
+        mError("topic:%s, failed to drop since subscribed by consumer %ld in consumer group %s", dropReq.name,
                pConsumer->consumerId, pConsumer->cgroup);
         return -1;
       }
@@ -580,7 +572,8 @@ static int32_t mndProcessDropTopicReq(SRpcMsg *pReq) {
   }
 #endif
 
-  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_ROLLBACK, TRN_CONFLICT_NOTHING, pReq);
+  STrans *pTrans = mndTransCreate(pMnode, TRN_POLICY_ROLLBACK, TRN_CONFLICT_DB_INSIDE, pReq);
+  mndTransSetDbName(pTrans, pTopic->db);
   if (pTrans == NULL) {
     mError("topic:%s, failed to drop since %s", pTopic->name, terrstr());
     return -1;

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

@@ -297,7 +297,7 @@ static SSdbRow *mndTransActionDecode(SSdbRaw *pRaw) {
       SDB_GET_INT32(pRaw, dataPos, &dataLen, _OVER)
       action.pRaw = taosMemoryMalloc(dataLen);
       if (action.pRaw == NULL) goto _OVER;
-      mTrace("raw:%p, is created", pData);
+      // mTrace("raw:%p, is created", pData);
       SDB_GET_BINARY(pRaw, dataPos, (void *)action.pRaw, dataLen, _OVER);
       if (taosArrayPush(pTrans->redoActions, &action) == NULL) goto _OVER;
       action.pRaw = NULL;
@@ -330,7 +330,7 @@ static SSdbRow *mndTransActionDecode(SSdbRaw *pRaw) {
       SDB_GET_INT32(pRaw, dataPos, &dataLen, _OVER)
       action.pRaw = taosMemoryMalloc(dataLen);
       if (action.pRaw == NULL) goto _OVER;
-      mTrace("raw:%p, is created", pData);
+      // mTrace("raw:%p, is created", action.pRaw);
       SDB_GET_BINARY(pRaw, dataPos, (void *)action.pRaw, dataLen, _OVER);
       if (taosArrayPush(pTrans->undoActions, &action) == NULL) goto _OVER;
       action.pRaw = NULL;
@@ -363,7 +363,7 @@ static SSdbRow *mndTransActionDecode(SSdbRaw *pRaw) {
       SDB_GET_INT32(pRaw, dataPos, &dataLen, _OVER)
       action.pRaw = taosMemoryMalloc(dataLen);
       if (action.pRaw == NULL) goto _OVER;
-      mTrace("raw:%p, is created", action.pRaw);
+      // mTrace("raw:%p, is created", action.pRaw);
       SDB_GET_BINARY(pRaw, dataPos, (void *)action.pRaw, dataLen, _OVER);
       if (taosArrayPush(pTrans->commitActions, &action) == NULL) goto _OVER;
       action.pRaw = NULL;
@@ -781,7 +781,7 @@ static void mndTransSendRpcRsp(SMnode *pMnode, STrans *pTrans) {
       sendRsp = true;
     }
   } else {
-    if (pTrans->stage == TRN_STAGE_REDO_ACTION && pTrans->failedTimes > 3) {
+    if (pTrans->stage == TRN_STAGE_REDO_ACTION && pTrans->failedTimes > 2) {
       if (code == 0) code = TSDB_CODE_MND_TRANS_UNKNOW_ERROR;
       sendRsp = true;
     }
@@ -791,7 +791,7 @@ static void mndTransSendRpcRsp(SMnode *pMnode, STrans *pTrans) {
     mDebug("trans:%d, send rsp, code:0x%x stage:%s app:%p", pTrans->id, code, mndTransStr(pTrans->stage),
            pTrans->rpcInfo.ahandle);
     if (code == TSDB_CODE_RPC_NETWORK_UNAVAIL) {
-      code = TSDB_CODE_RPC_INDIRECT_NETWORK_UNAVAIL;
+      code = TSDB_CODE_MND_TRANS_NETWORK_UNAVAILL;
     }
     SRpcMsg rspMsg = {.code = code, .info = pTrans->rpcInfo};
 
@@ -894,10 +894,19 @@ static int32_t mndTransWriteSingleLog(SMnode *pMnode, STrans *pTrans, STransActi
     code = 0;
     mDebug("trans:%d, %s:%d write to sdb, type:%s status:%s", pTrans->id, mndTransStr(pAction->stage), pAction->id,
            sdbTableName(pAction->pRaw->type), sdbStatusName(pAction->pRaw->status));
+
+    pTrans->lastAction = pAction->id;
+    pTrans->lastMsgType = pAction->msgType;
+    pTrans->lastEpset = pAction->epSet;
+    pTrans->lastErrorNo = 0;
   } else {
     pAction->errCode = (terrno != 0) ? terrno : code;
     mError("trans:%d, %s:%d failed to write sdb since %s, type:%s status:%s", pTrans->id, mndTransStr(pAction->stage),
            pAction->id, terrstr(), sdbTableName(pAction->pRaw->type), sdbStatusName(pAction->pRaw->status));
+    pTrans->lastAction = pAction->id;
+    pTrans->lastMsgType = pAction->msgType;
+    pTrans->lastEpset = pAction->epSet;
+    pTrans->lastErrorNo = pAction->errCode;
   }
 
   return code;
@@ -933,27 +942,48 @@ static int32_t mndTransSendSingleMsg(SMnode *pMnode, STrans *pTrans, STransActio
     pAction->msgReceived = 0;
     pAction->errCode = 0;
     mDebug("trans:%d, %s:%d is sent, %s", pTrans->id, mndTransStr(pAction->stage), pAction->id, detail);
+
+    pTrans->lastAction = pAction->id;
+    pTrans->lastMsgType = pAction->msgType;
+    pTrans->lastEpset = pAction->epSet;
+    if (pTrans->lastErrorNo == 0) {
+      pTrans->lastErrorNo = TSDB_CODE_ACTION_IN_PROGRESS;
+    }
   } else {
     pAction->msgSent = 0;
     pAction->msgReceived = 0;
     pAction->errCode = (terrno != 0) ? terrno : code;
     mError("trans:%d, %s:%d not send since %s, %s", pTrans->id, mndTransStr(pAction->stage), pAction->id, terrstr(),
            detail);
+
+    pTrans->lastAction = pAction->id;
+    pTrans->lastMsgType = pAction->msgType;
+    pTrans->lastEpset = pAction->epSet;
+    pTrans->lastErrorNo = pAction->errCode;
   }
 
   return code;
 }
 
+static int32_t mndTransExecNullMsg(SMnode *pMnode, STrans *pTrans, STransAction *pAction) {
+  pAction->rawWritten = 0;
+  pAction->errCode = 0;
+  mDebug("trans:%d, %s:%d null action executed", pTrans->id, mndTransStr(pAction->stage), pAction->id);
+
+  pTrans->lastAction = pAction->id;
+  pTrans->lastMsgType = pAction->msgType;
+  pTrans->lastEpset = pAction->epSet;
+  pTrans->lastErrorNo == 0;
+  return 0;
+}
+
 static int32_t mndTransExecSingleAction(SMnode *pMnode, STrans *pTrans, STransAction *pAction) {
   if (pAction->actionType == TRANS_ACTION_RAW) {
     return mndTransWriteSingleLog(pMnode, pTrans, pAction);
   } else if (pAction->actionType == TRANS_ACTION_MSG) {
     return mndTransSendSingleMsg(pMnode, pTrans, pAction);
   } else {
-    pAction->rawWritten = 0;
-    pAction->errCode = 0;
-    mDebug("trans:%d, %s:%d null action executed", pTrans->id, mndTransStr(pAction->stage), pAction->id);
-    return 0;
+    return mndTransExecNullMsg(pMnode, pTrans, pAction);
   }
 }
 
@@ -994,19 +1024,19 @@ static int32_t mndTransExecuteActions(SMnode *pMnode, STrans *pTrans, SArray *pA
 
   if (numOfExecuted == numOfActions) {
     if (errCode == 0) {
-      pTrans->lastErrorAction = 0;
+      pTrans->lastAction = 0;
       pTrans->lastErrorNo = 0;
-      pTrans->lastErrorMsgType = 0;
-      memset(&pTrans->lastErrorEpset, 0, sizeof(pTrans->lastErrorEpset));
+      pTrans->lastMsgType = 0;
+      memset(&pTrans->lastEpset, 0, sizeof(pTrans->lastEpset));
       mDebug("trans:%d, all %d actions execute successfully", pTrans->id, numOfActions);
       return 0;
     } else {
       mError("trans:%d, all %d actions executed, code:0x%x", pTrans->id, numOfActions, errCode & 0XFFFF);
       if (pErrAction != NULL) {
-        pTrans->lastErrorMsgType = pErrAction->msgType;
-        pTrans->lastErrorAction = pErrAction->id;
+        pTrans->lastMsgType = pErrAction->msgType;
+        pTrans->lastAction = pErrAction->id;
         pTrans->lastErrorNo = pErrAction->errCode;
-        pTrans->lastErrorEpset = pErrAction->epSet;
+        pTrans->lastEpset = pErrAction->epSet;
       }
       mndTransResetActions(pMnode, pTrans, pArray);
       terrno = errCode;
@@ -1073,15 +1103,15 @@ static int32_t mndTransExecuteRedoActionsSerial(SMnode *pMnode, STrans *pTrans)
     }
 
     if (code == 0) {
-      pTrans->lastErrorAction = 0;
+      pTrans->lastAction = 0;
       pTrans->lastErrorNo = 0;
-      pTrans->lastErrorMsgType = 0;
-      memset(&pTrans->lastErrorEpset, 0, sizeof(pTrans->lastErrorEpset));
+      pTrans->lastMsgType = 0;
+      memset(&pTrans->lastEpset, 0, sizeof(pTrans->lastEpset));
     } else {
-      pTrans->lastErrorMsgType = pAction->msgType;
-      pTrans->lastErrorAction = action;
-      pTrans->lastErrorNo = pAction->errCode;
-      pTrans->lastErrorEpset = pAction->epSet;
+      pTrans->lastMsgType = pAction->msgType;
+      pTrans->lastAction = action;
+      pTrans->lastErrorNo = code;
+      pTrans->lastEpset = pAction->epSet;
     }
 
     if (code == 0) {
@@ -1432,23 +1462,21 @@ static int32_t mndRetrieveTrans(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *pBl
     pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
     colDataAppend(pColInfo, numOfRows, (const char *)&pTrans->lastExecTime, false);
 
-    char lastError[TSDB_TRANS_ERROR_LEN + VARSTR_HEADER_SIZE] = {0};
-    char detail[TSDB_TRANS_ERROR_LEN] = {0};
-    if (pTrans->lastErrorNo != 0) {
-      int32_t len = snprintf(detail, sizeof(detail), "action:%d errno:0x%x(%s) ", pTrans->lastErrorAction,
-                             pTrans->lastErrorNo & 0xFFFF, tstrerror(pTrans->lastErrorNo));
-      SEpSet  epset = pTrans->lastErrorEpset;
-      if (epset.numOfEps > 0) {
-        len += snprintf(detail + len, sizeof(detail) - len, "msgType:%s numOfEps:%d inUse:%d ",
-                        TMSG_INFO(pTrans->lastErrorMsgType), epset.numOfEps, epset.inUse);
-        for (int32_t i = 0; i < pTrans->lastErrorEpset.numOfEps; ++i) {
-          len += snprintf(detail + len, sizeof(detail) - len, "ep:%d-%s:%u ", i, epset.eps[i].fqdn, epset.eps[i].port);
-        }
+    char    lastInfo[TSDB_TRANS_ERROR_LEN + VARSTR_HEADER_SIZE] = {0};
+    char    detail[TSDB_TRANS_ERROR_LEN] = {0};
+    int32_t len = snprintf(detail, sizeof(detail), "action:%d code:0x%x(%s) ", pTrans->lastAction,
+                           pTrans->lastErrorNo & 0xFFFF, tstrerror(pTrans->lastErrorNo));
+    SEpSet  epset = pTrans->lastEpset;
+    if (epset.numOfEps > 0) {
+      len += snprintf(detail + len, sizeof(detail) - len, "msgType:%s numOfEps:%d inUse:%d ",
+                      TMSG_INFO(pTrans->lastMsgType), epset.numOfEps, epset.inUse);
+      for (int32_t i = 0; i < pTrans->lastEpset.numOfEps; ++i) {
+        len += snprintf(detail + len, sizeof(detail) - len, "ep:%d-%s:%u ", i, epset.eps[i].fqdn, epset.eps[i].port);
       }
     }
-    STR_WITH_MAXSIZE_TO_VARSTR(lastError, detail, pShow->pMeta->pSchemas[cols].bytes);
+    STR_WITH_MAXSIZE_TO_VARSTR(lastInfo, detail, pShow->pMeta->pSchemas[cols].bytes);
     pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
-    colDataAppend(pColInfo, numOfRows, (const char *)lastError, false);
+    colDataAppend(pColInfo, numOfRows, (const char *)lastInfo, false);
 
     numOfRows++;
     sdbRelease(pSdb, pTrans);

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

@@ -59,6 +59,10 @@ int32_t mndInitVgroup(SMnode *pMnode) {
   mndSetMsgHandle(pMnode, TDMT_DND_DROP_VNODE_RSP, mndTransProcessRsp);
   mndSetMsgHandle(pMnode, TDMT_VND_COMPACT_RSP, mndTransProcessRsp);
 
+  mndSetMsgHandle(pMnode, TDMT_MND_REDISTRIBUTE_VGROUP, mndProcessRedistributeVgroupMsg);
+  mndSetMsgHandle(pMnode, TDMT_MND_MERGE_VGROUP, mndProcessSplitVgroupMsg);
+  mndSetMsgHandle(pMnode, TDMT_MND_BALANCE_VGROUP, mndProcessBalanceVgroupMsg);
+
   mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_VGROUP, mndRetrieveVgroups);
   mndAddShowFreeIterHandle(pMnode, TSDB_MGMT_TABLE_VGROUP, mndCancelGetNextVgroup);
   mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_VNODES, mndRetrieveVnodes);
@@ -390,12 +394,24 @@ SArray *mndBuildDnodesArray(SMnode *pMnode, int32_t exceptDnodeId) {
   return pArray;
 }
 
+static int32_t mndCompareDnodeId(int32_t *dnode1Id, int32_t *dnode2Id) { return *dnode1Id >= *dnode2Id ? 1 : 0; }
+
 static int32_t mndCompareDnodeVnodes(SDnodeObj *pDnode1, SDnodeObj *pDnode2) {
   float d1Score = (float)pDnode1->numOfVnodes / pDnode1->numOfSupportVnodes;
   float d2Score = (float)pDnode2->numOfVnodes / pDnode2->numOfSupportVnodes;
   return d1Score >= d2Score ? 1 : 0;
 }
 
+void mndSortVnodeGid(SVgObj *pVgroup) {
+  for (int32_t i = 0; i < pVgroup->replica; ++i) {
+    for (int32_t j = 0; j < pVgroup->replica - 1 - i; ++j) {
+      if (pVgroup->vnodeGid[j].dnodeId > pVgroup->vnodeGid[j + 1].dnodeId) {
+        TSWAP(pVgroup->vnodeGid[j], pVgroup->vnodeGid[j + 1]);
+      }
+    }
+  }
+}
+
 static int32_t mndGetAvailableDnode(SMnode *pMnode, SVgObj *pVgroup, SArray *pArray) {
   SSdb   *pSdb = pMnode->pSdb;
   int32_t allocedVnodes = 0;
@@ -430,6 +446,7 @@ static int32_t mndGetAvailableDnode(SMnode *pMnode, SVgObj *pVgroup, SArray *pAr
     pDnode->numOfVnodes++;
   }
 
+  mndSortVnodeGid(pVgroup);
   return 0;
 }
 
@@ -1009,10 +1026,10 @@ static int32_t mndAddDecVgroupReplicaFromTrans(SMnode *pMnode, STrans *pTrans, S
 
   if (pGid == NULL) return 0;
 
+  pVgroup->replica--;
   memcpy(&delGid, pGid, sizeof(SVnodeGid));
   memcpy(pGid, &pVgroup->vnodeGid[pVgroup->replica], sizeof(SVnodeGid));
   memset(&pVgroup->vnodeGid[pVgroup->replica], 0, sizeof(SVnodeGid));
-  pVgroup->replica--;
 
   if (mndAddAlterVnodeAction(pMnode, pTrans, pDb, pVgroup, TDMT_VND_ALTER_REPLICA) != 0) return -1;
   if (mndAddDropVnodeAction(pMnode, pTrans, pDb, pVgroup, &delGid, true) != 0) return -1;
@@ -1031,7 +1048,7 @@ static int32_t mndRedistributeVgroup(SMnode *pMnode, SRpcMsg *pReq, SDbObj *pDb,
   pTrans = mndTransCreate(pMnode, TRN_POLICY_RETRY, TRN_CONFLICT_GLOBAL, pReq);
   if (pTrans == NULL) goto _OVER;
   mndTransSetSerial(pTrans);
-  mDebug("trans:%d, used to drop redistribute vgId:%d", pTrans->id, pVgroup->vgId);
+  mDebug("trans:%d, used to redistribute vgroup, vgId:%d", pTrans->id, pVgroup->vgId);
 
   SVgObj newVg = {0};
   memcpy(&newVg, pVgroup, sizeof(SVgObj));
@@ -1040,11 +1057,38 @@ static int32_t mndRedistributeVgroup(SMnode *pMnode, SRpcMsg *pReq, SDbObj *pDb,
     mInfo("vgId:%d, vnode:%d dnode:%d", newVg.vgId, i, newVg.vnodeGid[i].dnodeId);
   }
 
-  if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew1->id) != 0) goto _OVER;
-  if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld1->id) != 0) goto _OVER;
-  if (pNew2 != NULL) {
+  if (pNew1 != NULL && pOld1 != NULL) {
+    int32_t numOfVnodes = mndGetVnodesNum(pMnode, pNew1->id);
+    if (numOfVnodes >= pNew1->numOfSupportVnodes) {
+      mError("vgId:%d, no enough vnodes in dnode:%d, numOfVnodes:%d support:%d", newVg.vgId, pNew1->id, numOfVnodes,
+             pNew1->numOfSupportVnodes);
+      terrno = TSDB_CODE_MND_NO_ENOUGH_DNODES;
+      goto _OVER;
+    }
+    if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew1->id) != 0) goto _OVER;
+    if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld1->id) != 0) goto _OVER;
+  }
+
+  if (pNew2 != NULL && pOld2 != NULL) {
+    int32_t numOfVnodes = mndGetVnodesNum(pMnode, pNew2->id);
+    if (numOfVnodes >= pNew2->numOfSupportVnodes) {
+      mError("vgId:%d, no enough vnodes in dnode:%d, numOfVnodes:%d support:%d", newVg.vgId, pNew2->id, numOfVnodes,
+             pNew2->numOfSupportVnodes);
+      terrno = TSDB_CODE_MND_NO_ENOUGH_DNODES;
+      goto _OVER;
+    }
     if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew2->id) != 0) goto _OVER;
     if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld2->id) != 0) goto _OVER;
+  }
+
+  if (pNew3 != NULL && pOld3 != NULL) {
+    int32_t numOfVnodes = mndGetVnodesNum(pMnode, pNew3->id);
+    if (numOfVnodes >= pNew3->numOfSupportVnodes) {
+      mError("vgId:%d, no enough vnodes in dnode:%d, numOfVnodes:%d support:%d", newVg.vgId, pNew3->id, numOfVnodes,
+             pNew3->numOfSupportVnodes);
+      terrno = TSDB_CODE_MND_NO_ENOUGH_DNODES;
+      goto _OVER;
+    }
     if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew3->id) != 0) goto _OVER;
     if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld3->id) != 0) goto _OVER;
   }
@@ -1070,88 +1114,190 @@ _OVER:
 }
 
 static int32_t mndProcessRedistributeVgroupMsg(SRpcMsg *pReq) {
-  SMnode        *pMnode = pReq->info.node;
-  SUserObj      *pUser = NULL;
-  SDnodeObj     *pNew1 = NULL;
-  SDnodeObj     *pNew2 = NULL;
-  SDnodeObj     *pNew3 = NULL;
-  SDnodeObj     *pOld1 = NULL;
-  SDnodeObj     *pOld2 = NULL;
-  SDnodeObj     *pOld3 = NULL;
-  SVgObj        *pVgroup = NULL;
-  SDbObj        *pDb = NULL;
-  int32_t        code = -1;
-  int64_t        curMs = taosGetTimestampMs();
-  SMDropMnodeReq redReq = {0};
-
-#if 0
-  if (tDeserializeSCreateDropMQSBNodeReq(pReq->pCont, pReq->contLen, &dropReq) != 0) {
+  SMnode    *pMnode = pReq->info.node;
+  SUserObj  *pUser = NULL;
+  SDnodeObj *pNew1 = NULL;
+  SDnodeObj *pNew2 = NULL;
+  SDnodeObj *pNew3 = NULL;
+  SDnodeObj *pOld1 = NULL;
+  SDnodeObj *pOld2 = NULL;
+  SDnodeObj *pOld3 = NULL;
+  SVgObj    *pVgroup = NULL;
+  SDbObj    *pDb = NULL;
+  int32_t    code = -1;
+  int64_t    curMs = taosGetTimestampMs();
+  int32_t    newDnodeId[3] = {0};
+  int32_t    oldDnodeId[3] = {0};
+  int32_t    newIndex = -1;
+  int32_t    oldIndex = -1;
+
+  SRedistributeVgroupReq req = {0};
+  if (tDeserializeSRedistributeVgroupReq(pReq->pCont, pReq->contLen, &req) != 0) {
     terrno = TSDB_CODE_INVALID_MSG;
     goto _OVER;
   }
-#endif
 
-  mDebug("vgId:%d, start to redistribute", 2);
+  mInfo("vgId:%d, start to redistribute to dnode %d:%d:%d", req.vgId, req.dnodeId1, req.dnodeId2, req.dnodeId3);
   pUser = mndAcquireUser(pMnode, pReq->conn.user);
   if (pUser == NULL) {
     terrno = TSDB_CODE_MND_NO_USER_FROM_CONN;
     goto _OVER;
   }
 
-  if (mndCheckNodeAuth(pUser) != 0) {
-    goto _OVER;
-  }
+  if (mndCheckNodeAuth(pUser) != 0) goto _OVER;
 
-  pVgroup = mndAcquireVgroup(pMnode, 2);
+  pVgroup = mndAcquireVgroup(pMnode, req.vgId);
   if (pVgroup == NULL) goto _OVER;
 
   pDb = mndAcquireDb(pMnode, pVgroup->dbName);
   if (pDb == NULL) goto _OVER;
 
   if (pVgroup->replica == 1) {
-    pNew1 = mndAcquireDnode(pMnode, 1);
-    pOld1 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[0].dnodeId);
-    if (pNew1 == NULL || pOld1 == NULL) goto _OVER;
-    if (!mndIsDnodeOnline(pNew1, curMs) || !mndIsDnodeOnline(pOld1, curMs)) {
-      terrno = TSDB_CODE_NODE_OFFLINE;
+    if (req.dnodeId1 <= 0 || req.dnodeId2 > 0 || req.dnodeId3 > 0) {
+      terrno = TSDB_CODE_MND_INVALID_REPLICA;
       goto _OVER;
     }
-    if (pNew1 == pOld1) {
+
+    if (req.dnodeId1 == pVgroup->vnodeGid[0].dnodeId) {
       terrno = TSDB_CODE_MND_VGROUP_UN_CHANGED;
       goto _OVER;
     }
-    if (mndRedistributeVgroup(pMnode, pReq, pDb, pVgroup, pNew1, pOld1, NULL, NULL, NULL, NULL) != 0) goto _OVER;
-  }
 
-  if (pVgroup->replica == 3) {
-    pNew1 = mndAcquireDnode(pMnode, 1);
-    pNew2 = mndAcquireDnode(pMnode, 2);
-    pNew3 = mndAcquireDnode(pMnode, 3);
+    pNew1 = mndAcquireDnode(pMnode, req.dnodeId1);
+    if (pNew1 == NULL) goto _OVER;
+    if (!mndIsDnodeOnline(pNew1, curMs)) {
+      terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+      goto _OVER;
+    }
+
     pOld1 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[0].dnodeId);
-    pOld2 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[1].dnodeId);
-    pOld3 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[2].dnodeId);
-    if (pNew1 == NULL || pOld1 == NULL || pNew2 == NULL || pOld2 == NULL || pNew3 == NULL || pOld3 == NULL) goto _OVER;
-    if (!mndIsDnodeOnline(pNew1, curMs) || !mndIsDnodeOnline(pOld1, curMs) || !mndIsDnodeOnline(pNew2, curMs) ||
-        !mndIsDnodeOnline(pOld2, curMs) || !mndIsDnodeOnline(pNew3, curMs) || !mndIsDnodeOnline(pOld3, curMs)) {
-      terrno = TSDB_CODE_NODE_OFFLINE;
+    if (pOld1 == NULL) goto _OVER;
+    if (!mndIsDnodeOnline(pOld1, curMs)) {
+      terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+      goto _OVER;
+    }
+
+    code = mndRedistributeVgroup(pMnode, pReq, pDb, pVgroup, pNew1, pOld1, NULL, NULL, NULL, NULL);
+
+  } else if (pVgroup->replica == 3) {
+    if (req.dnodeId1 <= 0 || req.dnodeId2 <= 0 || req.dnodeId3 <= 0) {
+      terrno = TSDB_CODE_MND_INVALID_REPLICA;
       goto _OVER;
     }
-    bool changed = true;
-    if (pNew1 != pOld1 || pNew1 != pOld2 || pNew1 != pOld3) changed = true;
-    if (pNew2 != pOld1 || pNew2 != pOld2 || pNew2 != pOld3) changed = true;
-    if (pNew3 != pOld1 || pNew3 != pOld2 || pNew3 != pOld3) changed = true;
-    if (!changed) {
+
+    if (req.dnodeId1 == req.dnodeId2 || req.dnodeId1 == req.dnodeId3 || req.dnodeId2 == req.dnodeId3) {
+      terrno = TSDB_CODE_MND_INVALID_REPLICA;
+      goto _OVER;
+    }
+
+    if (req.dnodeId1 != pVgroup->vnodeGid[0].dnodeId && req.dnodeId1 != pVgroup->vnodeGid[1].dnodeId &&
+        req.dnodeId1 != pVgroup->vnodeGid[2].dnodeId) {
+      newDnodeId[++newIndex] = req.dnodeId1;
+      mInfo("vgId:2, dnode:%d will be added", newDnodeId[newIndex]);
+    }
+
+    if (req.dnodeId2 != pVgroup->vnodeGid[0].dnodeId && req.dnodeId2 != pVgroup->vnodeGid[1].dnodeId &&
+        req.dnodeId2 != pVgroup->vnodeGid[2].dnodeId) {
+      newDnodeId[++newIndex] = req.dnodeId2;
+      mInfo("vgId:2, dnode:%d will be added", newDnodeId[newIndex]);
+    }
+
+    if (req.dnodeId3 != pVgroup->vnodeGid[0].dnodeId && req.dnodeId3 != pVgroup->vnodeGid[1].dnodeId &&
+        req.dnodeId3 != pVgroup->vnodeGid[2].dnodeId) {
+      newDnodeId[++newIndex] = req.dnodeId3;
+      mInfo("vgId:2, dnode:%d will be added", newDnodeId[newIndex]);
+    }
+
+    if (req.dnodeId1 != pVgroup->vnodeGid[0].dnodeId && req.dnodeId2 != pVgroup->vnodeGid[0].dnodeId &&
+        req.dnodeId3 != pVgroup->vnodeGid[0].dnodeId) {
+      oldDnodeId[++oldIndex] = pVgroup->vnodeGid[0].dnodeId;
+      mInfo("vgId:2, dnode:%d will be removed", oldDnodeId[oldIndex]);
+    }
+
+    if (req.dnodeId1 != pVgroup->vnodeGid[1].dnodeId && req.dnodeId2 != pVgroup->vnodeGid[1].dnodeId &&
+        req.dnodeId3 != pVgroup->vnodeGid[1].dnodeId) {
+      oldDnodeId[++oldIndex] = pVgroup->vnodeGid[1].dnodeId;
+      mInfo("vgId:2, dnode:%d will be removed", oldDnodeId[oldIndex]);
+    }
+
+    if (req.dnodeId1 != pVgroup->vnodeGid[2].dnodeId && req.dnodeId2 != pVgroup->vnodeGid[2].dnodeId &&
+        req.dnodeId3 != pVgroup->vnodeGid[2].dnodeId) {
+      oldDnodeId[++oldIndex] = pVgroup->vnodeGid[2].dnodeId;
+      mInfo("vgId:2, dnode:%d will be removed", oldDnodeId[oldIndex]);
+    }
+
+    if (newDnodeId[0] != 0) {
+      pNew1 = mndAcquireDnode(pMnode, newDnodeId[0]);
+      if (pNew1 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pNew1, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (newDnodeId[1] != 0) {
+      pNew2 = mndAcquireDnode(pMnode, newDnodeId[1]);
+      if (pNew2 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pNew2, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (newDnodeId[2] != 0) {
+      pNew3 = mndAcquireDnode(pMnode, newDnodeId[2]);
+      if (pNew3 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pNew3, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (oldDnodeId[0] != 0) {
+      pOld1 = mndAcquireDnode(pMnode, oldDnodeId[0]);
+      if (pOld1 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pOld1, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (oldDnodeId[1] != 0) {
+      pOld2 = mndAcquireDnode(pMnode, oldDnodeId[1]);
+      if (pOld2 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pOld2, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (oldDnodeId[2] != 0) {
+      pOld3 = mndAcquireDnode(pMnode, oldDnodeId[2]);
+      if (pOld3 == NULL) goto _OVER;
+      if (!mndIsDnodeOnline(pOld3, curMs)) {
+        terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+        goto _OVER;
+      }
+    }
+
+    if (pNew1 == NULL && pOld1 == NULL && pNew2 == NULL && pOld2 == NULL && pNew3 == NULL && pOld3 == NULL) {
       terrno = TSDB_CODE_MND_VGROUP_UN_CHANGED;
       goto _OVER;
     }
-    if (mndRedistributeVgroup(pMnode, pReq, pDb, pVgroup, pNew1, pOld1, pNew2, pOld2, pNew3, pOld3) != 0) goto _OVER;
+
+    code = mndRedistributeVgroup(pMnode, pReq, pDb, pVgroup, pNew1, pOld1, pNew2, pOld2, pNew3, pOld3);
+
+  } else {
+    terrno = TSDB_CODE_MND_INVALID_REPLICA;
+    goto _OVER;
   }
 
   if (code == 0) code = TSDB_CODE_ACTION_IN_PROGRESS;
 
 _OVER:
   if (code != 0 && code != TSDB_CODE_ACTION_IN_PROGRESS) {
-    mDebug("vgId:%d, failed to redistribute since %s", 1, terrstr());
+    mError("vgId:%d, failed to redistribute to dnode %d:%d:%d since %s", req.vgId, req.dnodeId1, req.dnodeId2,
+           req.dnodeId3, terrstr());
   }
 
   mndReleaseDnode(pMnode, pNew1);
@@ -1303,9 +1449,7 @@ static int32_t mndProcessSplitVgroupMsg(SRpcMsg *pReq) {
     goto _OVER;
   }
 
-  if (mndCheckNodeAuth(pUser) != 0) {
-    goto _OVER;
-  }
+  if (mndCheckNodeAuth(pUser) != 0) goto _OVER;
 
   code = mndSplitVgroup(pMnode, pReq, pDb, pVgroup);
   if (code == 0) code = TSDB_CODE_ACTION_IN_PROGRESS;

source/dnode/mnode/sdb/src/sdb.c

@@ -163,7 +163,12 @@ void sdbSetApplyIndex(SSdb *pSdb, int64_t index) { pSdb->curVer = index; }
 
 void sdbSetApplyTerm(SSdb *pSdb, int64_t term) { pSdb->curTerm = term; }
 
-void sdbSetCurConfig(SSdb *pSdb, int64_t config) { pSdb->curConfig = config; }
+void sdbSetCurConfig(SSdb *pSdb, int64_t config) {
+  if (pSdb->curConfig != config) {
+    mDebug("mnode sync config set from %" PRId64 " to %" PRId64, pSdb->curConfig, config);
+    pSdb->curConfig = config;
+  }
+}
 
 int64_t sdbGetApplyIndex(SSdb *pSdb) { return pSdb->curVer; }
 

source/dnode/mnode/sdb/src/sdbFile.c

@@ -357,7 +357,7 @@ static int32_t sdbWriteFileImp(SSdb *pSdb) {
     SdbEncodeFp encodeFp = pSdb->encodeFps[i];
     if (encodeFp == NULL) continue;
 
-    mTrace("write %s to sdb file, total %d rows", sdbTableName(i), sdbGetSize(pSdb, i));
+    mDebug("write %s to sdb file, total %d rows", sdbTableName(i), sdbGetSize(pSdb, i));
 
     SHashObj       *hash = pSdb->hashObjs[i];
     TdThreadRwlock *pLock = &pSdb->locks[i];
@@ -432,8 +432,8 @@ static int32_t sdbWriteFileImp(SSdb *pSdb) {
   } else {
     pSdb->lastCommitVer = pSdb->curVer;
     pSdb->lastCommitTerm = pSdb->curTerm;
-    mDebug("write sdb file successfully, ver:%" PRId64 " term:%" PRId64 " file:%s", pSdb->lastCommitVer,
-           pSdb->lastCommitTerm, curfile);
+    mDebug("write sdb file successfully, index:%" PRId64 " term:%" PRId64 " config:%" PRId64 " file:%s",
+           pSdb->lastCommitVer, pSdb->lastCommitTerm, pSdb->curConfig, curfile);
   }
 
   terrno = code;

source/dnode/mnode/sdb/src/sdbHash.c

@@ -83,6 +83,7 @@ const char *sdbStatusName(ESdbStatus status) {
 }
 
 void sdbPrintOper(SSdb *pSdb, SSdbRow *pRow, const char *oper) {
+#if 0
   EKeyType keyType = pSdb->keyTypes[pRow->type];
 
   if (keyType == SDB_KEY_BINARY) {
@@ -96,6 +97,7 @@ void sdbPrintOper(SSdb *pSdb, SSdbRow *pRow, const char *oper) {
            pRow->refCount, oper, pRow->pObj, sdbStatusName(pRow->status));
   } else {
   }
+#endif
 }
 
 static SHashObj *sdbGetHash(SSdb *pSdb, int32_t type) {

source/dnode/mnode/sdb/src/sdbRaw.c

@@ -37,13 +37,17 @@ SSdbRaw *sdbAllocRaw(ESdbType type, int8_t sver, int32_t dataLen) {
   pRaw->sver = sver;
   pRaw->dataLen = dataLen;
 
+#if 0
   mTrace("raw:%p, is created, len:%d table:%s", pRaw, dataLen, sdbTableName(type));
+#endif
   return pRaw;
 }
 
 void sdbFreeRaw(SSdbRaw *pRaw) {
   if (pRaw != NULL) {
+#if 0
     mTrace("raw:%p, is freed", pRaw);
+#endif
     taosMemoryFree(pRaw);
   }
 }

source/dnode/mnode/sdb/src/sdbRow.c

@@ -23,7 +23,9 @@ SSdbRow *sdbAllocRow(int32_t objSize) {
     return NULL;
   }
 
+#if 0
   mTrace("row:%p, is created, len:%d", pRow->pObj, objSize);
+#endif
   return pRow;
 }
 
@@ -45,6 +47,8 @@ void sdbFreeRow(SSdb *pSdb, SSdbRow *pRow, bool callFunc) {
 
   sdbPrintOper(pSdb, pRow, "free");
 
+#if 0
   mTrace("row:%p, is freed", pRow->pObj);
+#endif
   taosMemoryFreeClear(pRow);
 }

source/dnode/vnode/inc/vnode.h

@@ -89,7 +89,7 @@ typedef struct SMetaFltParam {
   tb_uid_t suid;
   int16_t  cid;
   int16_t  type;
-  char *   val;
+  char    *val;
   bool     reverse;
   int (*filterFunc)(void *a, void *b, int16_t type);
 
@@ -116,16 +116,16 @@ typedef void *tsdbReaderT;
 #define BLOCK_LOAD_TABLE_SEQ_ORDER  2
 #define BLOCK_LOAD_TABLE_RR_ORDER   3
 
-tsdbReaderT *tsdbQueryTables(SVnode *pVnode, SQueryTableDataCond *pCond, STableListInfo *tableInfoGroup, uint64_t qId,
-                             uint64_t taskId);
+tsdbReaderT *tsdbReaderOpen(SVnode *pVnode, SQueryTableDataCond *pCond, STableListInfo *tableInfoGroup, uint64_t qId,
+                            uint64_t taskId);
 tsdbReaderT  tsdbQueryCacheLast(SVnode *pVnode, SQueryTableDataCond *pCond, STableListInfo *groupList, uint64_t qId,
                                 void *pMemRef);
 int32_t      tsdbGetFileBlocksDistInfo(tsdbReaderT *pReader, STableBlockDistInfo *pTableBlockInfo);
 bool         isTsdbCacheLastRow(tsdbReaderT *pReader);
 int32_t      tsdbGetAllTableList(SMeta *pMeta, uint64_t uid, SArray *list);
 int32_t      tsdbGetCtbIdList(SMeta *pMeta, int64_t suid, SArray *list);
-void *       tsdbGetIdx(SMeta *pMeta);
-void *       tsdbGetIvtIdx(SMeta *pMeta);
+void        *tsdbGetIdx(SMeta *pMeta);
+void        *tsdbGetIvtIdx(SMeta *pMeta);
 int64_t      tsdbGetNumOfRowsInMemTable(tsdbReaderT *pHandle);
 
 bool    tsdbNextDataBlock(tsdbReaderT pTsdbReadHandle);
@@ -201,7 +201,7 @@ struct SMetaEntry {
   int64_t  version;
   int8_t   type;
   tb_uid_t uid;
-  char *   name;
+  char    *name;
   union {
     struct {
       SSchemaWrapper schemaRow;
@@ -229,17 +229,17 @@ struct SMetaEntry {
 
 struct SMetaReader {
   int32_t    flags;
-  SMeta *    pMeta;
+  SMeta     *pMeta;
   SDecoder   coder;
   SMetaEntry me;
-  void *     pBuf;
+  void      *pBuf;
   int32_t    szBuf;
 };
 
 struct SMTbCursor {
-  TBC *       pDbc;
-  void *      pKey;
-  void *      pVal;
+  TBC        *pDbc;
+  void       *pKey;
+  void       *pVal;
   int32_t     kLen;
   int32_t     vLen;
   SMetaReader mr;

source/dnode/vnode/src/inc/tq.h

@@ -58,7 +58,7 @@ struct STqReadHandle {
   SArray*   pColIdList;  // SArray<int16_t>
 
   int32_t         cachedSchemaVer;
-  int64_t         cachedSchemaUid;
+  int64_t         cachedSchemaSuid;
   SSchemaWrapper* pSchemaWrapper;
   STSchema*       pSchema;
 };

source/dnode/vnode/src/inc/vnodeInt.h

@@ -119,8 +119,8 @@ int          tsdbInsertData(STsdb* pTsdb, int64_t version, SSubmitReq* pMsg, SSu
 int32_t      tsdbInsertTableData(STsdb* pTsdb, int64_t version, SSubmitMsgIter* pMsgIter, SSubmitBlk* pBlock,
                                  SSubmitBlkRsp* pRsp);
 int32_t      tsdbDeleteTableData(STsdb* pTsdb, int64_t version, tb_uid_t suid, tb_uid_t uid, TSKEY sKey, TSKEY eKey);
-tsdbReaderT* tsdbQueryTables(SVnode* pVnode, SQueryTableDataCond* pCond, STableListInfo* tableList, uint64_t qId,
-                             uint64_t taskId);
+tsdbReaderT* tsdbReaderOpen(SVnode* pVnode, SQueryTableDataCond* pCond, STableListInfo* tableList, uint64_t qId,
+                            uint64_t taskId);
 tsdbReaderT  tsdbQueryCacheLastT(STsdb* tsdb, SQueryTableDataCond* pCond, STableListInfo* tableList, uint64_t qId,
                                  void* pMemRef);
 int32_t      tsdbSnapshotReaderOpen(STsdb* pTsdb, STsdbSnapshotReader** ppReader, int64_t sver, int64_t ever);

source/dnode/vnode/src/tq/tq.c

@@ -130,7 +130,17 @@ int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
           TD_VID(pTq->pVnode), pReq->currentOffset, fetchOffset);
 
   STqHandle* pHandle = taosHashGet(pTq->handles, pReq->subKey, strlen(pReq->subKey));
-  ASSERT(pHandle);
+  /*ASSERT(pHandle);*/
+  if (pHandle == NULL) {
+    tqError("tmq poll: no consumer handle for consumer %ld in vg %d, subkey %s", consumerId, pTq->pVnode->config.vgId,
+            pReq->subKey);
+    return -1;
+  }
+  if (pHandle->consumerId != consumerId) {
+    tqError("tmq poll: consumer handle mismatch for consumer %ld in vg %d, subkey %s, handle consumer id %ld",
+            consumerId, pTq->pVnode->config.vgId, pReq->subKey, pHandle->consumerId);
+    return -1;
+  }
 
   int32_t consumerEpoch = atomic_load_32(&pHandle->epoch);
   while (consumerEpoch < reqEpoch) {

source/dnode/vnode/src/tq/tqRead.c

@@ -67,7 +67,7 @@ STqReadHandle* tqInitSubmitMsgScanner(SMeta* pMeta) {
   pReadHandle->ver = -1;
   pReadHandle->pColIdList = NULL;
   pReadHandle->cachedSchemaVer = -1;
-  pReadHandle->cachedSchemaUid = -1;
+  pReadHandle->cachedSchemaSuid = -1;
   pReadHandle->pSchema = NULL;
   pReadHandle->pSchemaWrapper = NULL;
   pReadHandle->tbIdHash = NULL;
@@ -130,7 +130,8 @@ int32_t tqRetrieveDataBlock(SArray** ppCols, STqReadHandle* pHandle, uint64_t* p
   // TODO set to real sversion
   /*int32_t sversion = 1;*/
   int32_t sversion = htonl(pHandle->pBlock->sversion);
-  if (pHandle->cachedSchemaVer != sversion || pHandle->cachedSchemaUid != pHandle->msgIter.suid) {
+  if (pHandle->cachedSchemaSuid == 0 || pHandle->cachedSchemaVer != sversion ||
+      pHandle->cachedSchemaSuid != pHandle->msgIter.suid) {
     pHandle->pSchema = metaGetTbTSchema(pHandle->pVnodeMeta, pHandle->msgIter.uid, sversion);
     if (pHandle->pSchema == NULL) {
       tqWarn("cannot found tsschema for table: uid: %ld (suid: %ld), version %d, possibly dropped table",
@@ -150,7 +151,7 @@ int32_t tqRetrieveDataBlock(SArray** ppCols, STqReadHandle* pHandle, uint64_t* p
       return -1;
     }
     pHandle->cachedSchemaVer = sversion;
-    pHandle->cachedSchemaUid = pHandle->msgIter.suid;
+    pHandle->cachedSchemaSuid = pHandle->msgIter.suid;
   }
 
   STSchema*       pTschema = pHandle->pSchema;

source/dnode/vnode/src/tsdb/tsdbRead.c

@@ -500,8 +500,8 @@ static int32_t setCurrentSchema(SVnode* pVnode, STsdbReadHandle* pTsdbReadHandle
   return TSDB_CODE_SUCCESS;
 }
 
-tsdbReaderT* tsdbQueryTables(SVnode* pVnode, SQueryTableDataCond* pCond, STableListInfo* tableList, uint64_t qId,
-                             uint64_t taskId) {
+tsdbReaderT* tsdbReaderOpen(SVnode* pVnode, SQueryTableDataCond* pCond, STableListInfo* tableList, uint64_t qId,
+                            uint64_t taskId) {
   STsdbReadHandle* pTsdbReadHandle = tsdbQueryTablesImpl(pVnode, pCond, qId, taskId);
   if (pTsdbReadHandle == NULL) {
     return NULL;
@@ -642,7 +642,7 @@ tsdbReaderT tsdbQueryLastRow(SVnode* pVnode, SQueryTableDataCond* pCond, STableL
     return NULL;
   }
 
-  STsdbReadHandle* pTsdbReadHandle = (STsdbReadHandle*)tsdbQueryTables(pVnode, pCond, pList, qId, taskId);
+  STsdbReadHandle* pTsdbReadHandle = (STsdbReadHandle*)tsdbReaderOpen(pVnode, pCond, pList, qId, taskId);
   if (pTsdbReadHandle == NULL) {
     return NULL;
   }

source/dnode/vnode/src/vnd/vnodeSvr.c

@@ -303,6 +303,10 @@ int32_t vnodeProcessSyncReq(SVnode *pVnode, SRpcMsg *pMsg, SRpcMsg **pRsp) {
     char  logBuf[512] = {0};
     char *syncNodeStr = sync2SimpleStr(pVnode->sync);
     snprintf(logBuf, sizeof(logBuf), "==vnodeProcessSyncReq== msgType:%d, syncNode: %s", pMsg->msgType, syncNodeStr);
+    static int64_t vndTick = 0;
+    if (++vndTick % 10 == 1) {
+      vTrace("sync trace msg:%s, %s", TMSG_INFO(pMsg->msgType), syncNodeStr);
+    }
     syncRpcMsgLog2(logBuf, pMsg);
     taosMemoryFree(syncNodeStr);
 
@@ -900,4 +904,4 @@ static int32_t vnodeProcessAlterHasnRangeReq(SVnode *pVnode, int64_t version, vo
   // 2. adjust hash range / compact / remove wals / rename vgroups
   // 3. reload sync
   return 0;
-}
+}
\ No newline at end of file

source/dnode/vnode/src/vnd/vnodeSync.c

@@ -180,13 +180,22 @@ static int32_t vnodeSyncGetSnapshot(SSyncFSM *pFsm, SSnapshot *pSnapshot) {
   return 0;
 }
 
-static void vnodeSyncReconfig(struct SSyncFSM *pFsm, SSyncCfg newCfg, SReConfigCbMeta cbMeta) {
+static void vnodeSyncReconfig(struct SSyncFSM *pFsm, const SRpcMsg *pMsg, SReConfigCbMeta cbMeta) {
   SVnode *pVnode = pFsm->data;
   vInfo("vgId:%d, sync reconfig is confirmed", TD_VID(pVnode));
 
+#if 0
+// send response
+  SRpcMsg rpcMsg = {.msgType = pMsg->msgType, .contLen = pMsg->contLen, .conn.applyIndex = cbMeta.index};
+  rpcMsg.pCont = rpcMallocCont(rpcMsg.contLen);
+  memcpy(rpcMsg.pCont, pMsg->pCont, pMsg->contLen);
+  syncGetAndDelRespRpc(pVnode->sync, cbMeta.seqNum, &rpcMsg.info);
+#endif
+
   // todo rpc response here
   // build rpc msg
   // put into apply queue
+  vnodePostBlockMsg(pVnode, TDMT_VND_ALTER_REPLICA);
 }
 
 static void vnodeSyncCommitMsg(SSyncFSM *pFsm, const SRpcMsg *pMsg, SFsmCbMeta cbMeta) {
@@ -212,6 +221,7 @@ static void vnodeSyncCommitMsg(SSyncFSM *pFsm, const SRpcMsg *pMsg, SFsmCbMeta c
     memcpy(rpcMsg.pCont, pMsg->pCont, pMsg->contLen);
     syncGetAndDelRespRpc(pVnode->sync, cbMeta.seqNum, &rpcMsg.info);
     tmsgPutToQueue(&pVnode->msgCb, APPLY_QUEUE, &rpcMsg);
+
   } else {
     char logBuf[256] = {0};
     snprintf(logBuf, sizeof(logBuf),

source/libs/catalog/src/ctgAsync.c

@@ -525,7 +525,7 @@ int32_t ctgDumpTbIndexRes(SCtgTask* pTask) {
   }
 
   SMetaRes res = {.code = pTask->code, .pRes = pTask->res};
-  taosArrayPush(pJob->jobRes.pTableHash, &res);
+  taosArrayPush(pJob->jobRes.pTableIndex, &res);
 
   return TSDB_CODE_SUCCESS;
 }
@@ -875,7 +875,9 @@ int32_t ctgHandleGetTbIndexRsp(SCtgTask* pTask, int32_t reqType, const SDataBuf
   TSWAP(pTask->res, pTask->msgCtx.out);
   
 _return:
-
+  if (TSDB_CODE_MND_DB_INDEX_NOT_EXIST == code) {
+    code = TSDB_CODE_SUCCESS;
+  }
   ctgHandleTaskEnd(pTask, code);
 
   CTG_RET(code);

source/libs/executor/inc/executorimpl.h

@@ -458,7 +458,6 @@ typedef struct STimeWindowSupp {
   int64_t          waterMark;
   TSKEY            maxTs;
   SColumnInfoData  timeWindowData;     // query time window info for scalar function execution.
-  SHashObj        *winMap;
 } STimeWindowAggSupp;
 
 typedef struct SIntervalAggOperatorInfo {
@@ -809,6 +808,11 @@ SOperatorInfo* createSortedMergeOperatorInfo(SOperatorInfo** downstream, int32_t
 SOperatorInfo* createIntervalOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
                                           SSDataBlock* pResBlock, SInterval* pInterval, int32_t primaryTsSlotId,
                                           STimeWindowAggSupp *pTwAggSupp, SExecTaskInfo* pTaskInfo, bool isStream);
+
+SOperatorInfo* createMergeIntervalOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
+                                          SSDataBlock* pResBlock, SInterval* pInterval, int32_t primaryTsSlotId,
+                                          SExecTaskInfo* pTaskInfo);
+
 SOperatorInfo* createStreamFinalIntervalOperatorInfo(SOperatorInfo* downstream,
     SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo, int32_t numOfChild);
 SOperatorInfo* createStreamIntervalOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
@@ -903,10 +907,11 @@ SResultWindowInfo* getSessionTimeWindow(SArray* pWinInfos, TSKEY ts, int64_t gap
 int32_t updateSessionWindowInfo(SResultWindowInfo* pWinInfo, TSKEY* pTs, int32_t rows,
     int32_t start, int64_t gap, SHashObj* pStDeleted);
 bool functionNeedToExecute(SqlFunctionCtx* pCtx);
-int64_t getSmaWaterMark(int64_t interval, double filesFactor);
-bool isSmaStream(int8_t triggerType);
 
 int32_t compareTimeWindow(const void* p1, const void* p2, const void* param);
+int32_t finalizeResultRowIntoResultDataBlock(SDiskbasedBuf* pBuf, SResultRowPosition* resultRowPosition,
+                                       SqlFunctionCtx* pCtx, SExprInfo* pExprInfo, int32_t numOfExprs, const int32_t* rowCellOffset,
+                                       SSDataBlock* pBlock, SExecTaskInfo* pTaskInfo);
 
 #ifdef __cplusplus
 }

source/libs/executor/src/executorimpl.c

@@ -1819,7 +1819,7 @@ void setResultRowInitCtx(SResultRow* pResult, SqlFunctionCtx* pCtx, int32_t numO
   }
 }
 
-static void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const int8_t* rowRes, bool keep, bool needFree);
+static void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const int8_t* rowRes, bool keep);
 
 void doFilter(const SNode* pFilterNode, SSDataBlock* pBlock, bool needFree) {
   if (pFilterNode == NULL) {
@@ -1840,30 +1840,29 @@ void doFilter(const SNode* pFilterNode, SSDataBlock* pBlock, bool needFree) {
   bool keep = filterExecute(filter, pBlock, &rowRes, NULL, param1.numOfCols);
   filterFreeInfo(filter);
 
-  extractQualifiedTupleByFilterResult(pBlock, rowRes, keep, needFree);
+  extractQualifiedTupleByFilterResult(pBlock, rowRes, keep);
   blockDataUpdateTsWindow(pBlock, 0);
 }
 
-void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const int8_t* rowRes, bool keep, bool needFree) {
+void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const int8_t* rowRes, bool keep) {
   if (keep) {
     return;
   }
 
   if (rowRes != NULL) {
-    SSDataBlock* px = createOneDataBlock(pBlock, false);
-    blockDataEnsureCapacity(px, pBlock->info.rows);
+    SSDataBlock* px = createOneDataBlock(pBlock, true);
 
     int32_t totalRows = pBlock->info.rows;
-
     for (int32_t i = 0; i < pBlock->info.numOfCols; ++i) {
-      SColumnInfoData* pDst = taosArrayGet(px->pDataBlock, i);
-      SColumnInfoData* pSrc = taosArrayGet(pBlock->pDataBlock, i);
-
+      SColumnInfoData* pSrc = taosArrayGet(px->pDataBlock, i);
+      SColumnInfoData* pDst = taosArrayGet(pBlock->pDataBlock, i);
       // it is a reserved column for scalar function, and no data in this column yet.
-      if (pSrc->pData == NULL) {
+      if (pDst->pData == NULL) {
         continue;
       }
 
+      colInfoDataCleanup(pDst, pBlock->info.rows);
+
       int32_t numOfRows = 0;
       for (int32_t j = 0; j < totalRows; ++j) {
         if (rowRes[j] == 0) {
@@ -1883,20 +1882,8 @@ void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const int8_t* rowR
       } else {
         ASSERT(pBlock->info.rows == numOfRows);
       }
-
-      SColumnInfoData tmp = *pSrc;
-      *pSrc = *pDst;
-      *pDst = tmp;
-
-      if (!needFree) {
-        if (IS_VAR_DATA_TYPE(pDst->info.type)) {  // this elements do not need free
-          pDst->varmeta.offset = NULL;
-        } else {
-          pDst->nullbitmap = NULL;
-        }
-        pDst->pData = NULL;
-      }
     }
+
     blockDataDestroy(px);  // fix memory leak
   } else {
     // do nothing
@@ -1956,6 +1943,57 @@ static void doUpdateNumOfRows(SResultRow* pRow, int32_t numOfExprs, const int32_
   }
 }
 
+int32_t finalizeResultRowIntoResultDataBlock(SDiskbasedBuf* pBuf, SResultRowPosition* resultRowPosition,
+                                             SqlFunctionCtx* pCtx, SExprInfo* pExprInfo, int32_t numOfExprs,
+                                             const int32_t* rowCellOffset, SSDataBlock* pBlock,
+                                             SExecTaskInfo* pTaskInfo) {
+  SFilePage*  page = getBufPage(pBuf, resultRowPosition->pageId);
+  SResultRow* pRow = (SResultRow*)((char*)page + resultRowPosition->offset);
+
+  doUpdateNumOfRows(pRow, numOfExprs, rowCellOffset);
+  if (pRow->numOfRows == 0) {
+    releaseBufPage(pBuf, page);
+    return 0;
+  }
+
+  while (pBlock->info.rows + pRow->numOfRows > pBlock->info.capacity) {
+    int32_t code = blockDataEnsureCapacity(pBlock, pBlock->info.capacity * 1.25);
+    if (TAOS_FAILED(code)) {
+      releaseBufPage(pBuf, page);
+      qError("%s ensure result data capacity failed, code %s", GET_TASKID(pTaskInfo), tstrerror(code));
+      longjmp(pTaskInfo->env, code);
+    }
+  }
+
+  for (int32_t j = 0; j < numOfExprs; ++j) {
+    int32_t slotId = pExprInfo[j].base.resSchema.slotId;
+
+    pCtx[j].resultInfo = getResultCell(pRow, j, rowCellOffset);
+    if (pCtx[j].fpSet.finalize) {
+      int32_t code = pCtx[j].fpSet.finalize(&pCtx[j], pBlock);
+      if (TAOS_FAILED(code)) {
+        qError("%s build result data block error, code %s", GET_TASKID(pTaskInfo), tstrerror(code));
+        longjmp(pTaskInfo->env, code);
+      }
+    } else if (strcmp(pCtx[j].pExpr->pExpr->_function.functionName, "_select_value") == 0) {
+      // do nothing, todo refactor
+    } else {
+      // expand the result into multiple rows. E.g., _wstartts, top(k, 20)
+      // the _wstartts needs to copy to 20 following rows, since the results of top-k expands to 20 different rows.
+      SColumnInfoData* pColInfoData = taosArrayGet(pBlock->pDataBlock, slotId);
+      char*            in = GET_ROWCELL_INTERBUF(pCtx[j].resultInfo);
+      for (int32_t k = 0; k < pRow->numOfRows; ++k) {
+        colDataAppend(pColInfoData, pBlock->info.rows + k, in, pCtx[j].resultInfo->isNullRes);
+      }
+    }
+  }
+
+  releaseBufPage(pBuf, page);
+  pBlock->info.rows += pRow->numOfRows;
+
+  return 0;
+}
+
 int32_t doCopyToSDataBlock(SExecTaskInfo* pTaskInfo, SSDataBlock* pBlock, SExprInfo* pExprInfo, SDiskbasedBuf* pBuf,
                            SGroupResInfo* pGroupResInfo, const int32_t* rowCellOffset, SqlFunctionCtx* pCtx,
                            int32_t numOfExprs) {
@@ -2010,9 +2048,9 @@ int32_t doCopyToSDataBlock(SExecTaskInfo* pTaskInfo, SSDataBlock* pBlock, SExprI
         SColumnInfoData* pColInfoData = taosArrayGet(pBlock->pDataBlock, slotId);
         char*            in = GET_ROWCELL_INTERBUF(pCtx[j].resultInfo);
         if (pCtx[j].increase) {
-          int64_t ts = *(int64_t*) in;
+          int64_t ts = *(int64_t*)in;
           for (int32_t k = 0; k < pRow->numOfRows; ++k) {
-            colDataAppend(pColInfoData, pBlock->info.rows + k, (const char *)&ts, pCtx[j].resultInfo->isNullRes);
+            colDataAppend(pColInfoData, pBlock->info.rows + k, (const char*)&ts, pCtx[j].resultInfo->isNullRes);
             ts++;
           }
         } else {
@@ -2086,11 +2124,6 @@ static int32_t compressQueryColData(SColumnInfoData* pColRes, int32_t numOfRows,
 }
 
 int32_t doFillTimeIntervalGapsInResults(struct SFillInfo* pFillInfo, SSDataBlock* pBlock, int32_t capacity) {
-  //  for(int32_t i = 0; i < pFillInfo->numOfCols; ++i) {
-  //    SColumnInfoData* pColInfoData = taosArrayGet(pOutput->pDataBlock, i);
-  //    p[i] = pColInfoData->pData + (pColInfoData->info.bytes * pOutput->info.rows);
-  //  }
-
   int32_t numOfRows = (int32_t)taosFillResultDataBlock(pFillInfo, pBlock, capacity - pBlock->info.rows);
   pBlock->info.rows += numOfRows;
 
@@ -3112,8 +3145,8 @@ static SSDataBlock* doMerge(SOperatorInfo* pOperator) {
   return (pInfo->binfo.pRes->info.rows > 0) ? pInfo->binfo.pRes : NULL;
 }
 
-SSDataBlock* getSortedMergeBlockData(SSortHandle* pHandle, SSDataBlock* pDataBlock, int32_t capacity, SArray* pColMatchInfo,
-                                SSortedMergeOperatorInfo *pInfo) {
+SSDataBlock* getSortedMergeBlockData(SSortHandle* pHandle, SSDataBlock* pDataBlock, int32_t capacity,
+                                     SArray* pColMatchInfo, SSortedMergeOperatorInfo* pInfo) {
   blockDataCleanup(pDataBlock);
 
   SSDataBlock* p = tsortGetSortedDataBlock(pHandle);
@@ -4575,7 +4608,7 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
       SScanPhysiNode*      pScanPhyNode = (SScanPhysiNode*)pPhyNode;  // simple child table.
       STableScanPhysiNode* pTableScanNode = (STableScanPhysiNode*)pPhyNode;
       STimeWindowAggSupp   twSup = {
-          .waterMark = pTableScanNode->watermark, .calTrigger = pTableScanNode->triggerType, .maxTs = INT64_MIN};
+            .waterMark = pTableScanNode->watermark, .calTrigger = pTableScanNode->triggerType, .maxTs = INT64_MIN};
       tsdbReaderT pDataReader = NULL;
       if (pHandle->vnode) {
         pDataReader = doCreateDataReader(pTableScanNode, pHandle, pTableListInfo, (uint64_t)queryId, taskId, pTagCond);
@@ -4671,28 +4704,35 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
         .waterMark = pIntervalPhyNode->window.watermark,
         .calTrigger = pIntervalPhyNode->window.triggerType,
         .maxTs = INT64_MIN,
-        .winMap = NULL,
     };
-    if (isSmaStream(pIntervalPhyNode->window.triggerType)) {
-      if (FLT_LESS(pIntervalPhyNode->window.filesFactor, 1.000000)) {
-        as.calTrigger = STREAM_TRIGGER_AT_ONCE_SMA;
-      } else {
-        _hash_fn_t hashFn = taosGetDefaultHashFunction(TSDB_DATA_TYPE_TIMESTAMP);
-        as.winMap = taosHashInit(64, hashFn, true, HASH_NO_LOCK);
-        as.waterMark = getSmaWaterMark(interval.interval, pIntervalPhyNode->window.filesFactor);
-        as.calTrigger = STREAM_TRIGGER_WINDOW_CLOSE_SMA;
-      }
-    }
 
     int32_t tsSlotId = ((SColumnNode*)pIntervalPhyNode->window.pTspk)->slotId;
-    bool isStream = (QUERY_NODE_PHYSICAL_PLAN_STREAM_INTERVAL == type);
-    pOptr = createIntervalOperatorInfo(ops[0], pExprInfo, num, pResBlock, &interval, tsSlotId, &as, pTaskInfo, isStream);
+    bool    isStream = (QUERY_NODE_PHYSICAL_PLAN_STREAM_INTERVAL == type);
+    pOptr =
+        createIntervalOperatorInfo(ops[0], pExprInfo, num, pResBlock, &interval, tsSlotId, &as, pTaskInfo, isStream);
+
+  } else if (QUERY_NODE_PHYSICAL_PLAN_MERGE_INTERVAL == type) {
+    SMergeIntervalPhysiNode * pIntervalPhyNode = (SMergeIntervalPhysiNode*)pPhyNode;
+
+    SExprInfo*   pExprInfo = createExprInfo(pIntervalPhyNode->window.pFuncs, NULL, &num);
+    SSDataBlock* pResBlock = createResDataBlock(pPhyNode->pOutputDataBlockDesc);
+
+    SInterval interval = {.interval = pIntervalPhyNode->interval,
+                          .sliding = pIntervalPhyNode->sliding,
+                          .intervalUnit = pIntervalPhyNode->intervalUnit,
+                          .slidingUnit = pIntervalPhyNode->slidingUnit,
+                          .offset = pIntervalPhyNode->offset,
+                          .precision = ((SColumnNode*)pIntervalPhyNode->window.pTspk)->node.resType.precision};
 
+    int32_t tsSlotId = ((SColumnNode*)pIntervalPhyNode->window.pTspk)->slotId;
+    pOptr = createMergeIntervalOperatorInfo(ops[0], pExprInfo, num, pResBlock, &interval, tsSlotId, pTaskInfo);
   } else if (QUERY_NODE_PHYSICAL_PLAN_STREAM_SEMI_INTERVAL == type) {
-    int32_t children = 8;
+    qDebug("[******]create Semi");
+    int32_t children = 0;
     pOptr = createStreamFinalIntervalOperatorInfo(ops[0], pPhyNode, pTaskInfo, children);
   } else if (QUERY_NODE_PHYSICAL_PLAN_STREAM_FINAL_INTERVAL == type) {
-    int32_t children = 0;
+    qDebug("[******]create Final");
+    int32_t children = 1;
     pOptr = createStreamFinalIntervalOperatorInfo(ops[0], pPhyNode, pTaskInfo, children);
   } else if (QUERY_NODE_PHYSICAL_PLAN_SORT == type) {
     SSortPhysiNode* pSortPhyNode = (SSortPhysiNode*)pPhyNode;
@@ -4720,7 +4760,7 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
     int32_t numOfOutputCols = 0;
     SArray* pColList =
         extractColMatchInfo(pMergePhyNode->pTargets, pDescNode, &numOfOutputCols, pTaskInfo, COL_MATCH_FROM_SLOT_ID);
-    SPhysiNode* pChildNode = (SPhysiNode*)nodesListGetNode(pPhyNode->pChildren, 0);
+    SPhysiNode*  pChildNode = (SPhysiNode*)nodesListGetNode(pPhyNode->pChildren, 0);
     SSDataBlock* pInputDataBlock = createResDataBlock(pChildNode->pOutputDataBlockDesc);
     pOptr = createMultiwaySortMergeOperatorInfo(ops, size, pInputDataBlock, pResBlock, sortInfo, pColList, pTaskInfo);
   } else if (QUERY_NODE_PHYSICAL_PLAN_MERGE_SESSION == type) {
@@ -5067,7 +5107,7 @@ tsdbReaderT doCreateDataReader(STableScanPhysiNode* pTableScanNode, SReadHandle*
     goto _error;
   }
 
-  return tsdbQueryTables(pHandle->vnode, &cond, pTableListInfo, queryId, taskId);
+  return tsdbReaderOpen(pHandle->vnode, &cond, pTableListInfo, queryId, taskId);
 
 _error:
   terrno = code;
@@ -5349,7 +5389,8 @@ int32_t getOperatorExplainExecInfo(SOperatorInfo* operatorInfo, SExplainExecInfo
   return TSDB_CODE_SUCCESS;
 }
 
-int32_t initStreamAggSupporter(SStreamAggSupporter* pSup, const char* pKey, SqlFunctionCtx* pCtx, int32_t numOfOutput, size_t size) {
+int32_t initStreamAggSupporter(SStreamAggSupporter* pSup, const char* pKey, SqlFunctionCtx* pCtx, int32_t numOfOutput,
+                               size_t size) {
   pSup->resultRowSize = getResultRowSize(pCtx, numOfOutput);
   pSup->keySize = sizeof(int64_t) + sizeof(TSKEY);
   pSup->pKeyBuf = taosMemoryCalloc(1, pSup->keySize);
@@ -5370,22 +5411,9 @@ int32_t initStreamAggSupporter(SStreamAggSupporter* pSup, const char* pKey, SqlF
     bufSize = pageSize * 4;
   }
   int32_t code = createDiskbasedBuf(&pSup->pResultBuf, pageSize, bufSize, pKey, TD_TMP_DIR_PATH);
-  for(int32_t i = 0; i < numOfOutput; ++i) {
+  for (int32_t i = 0; i < numOfOutput; ++i) {
     pCtx[i].pBuf = pSup->pResultBuf;
   }
   return code;
 }
 
-int64_t getSmaWaterMark(int64_t interval, double filesFactor) {
-  int64_t waterMark = 0;
-  ASSERT(FLT_GREATEREQUAL(filesFactor, 0.000000));
-  waterMark = -1 * filesFactor;
-  return waterMark;
-}
-
-bool isSmaStream(int8_t triggerType) {
-  if (triggerType == STREAM_TRIGGER_AT_ONCE || triggerType == STREAM_TRIGGER_WINDOW_CLOSE) {
-    return false;
-  }
-  return true;
-}

source/libs/executor/src/scanoperator.c

@@ -809,11 +809,18 @@ static void getUpdateDataBlock(SStreamBlockScanInfo* pInfo, bool invertible, SSD
     //  return p;
     SColumnInfoData* pCol = (SColumnInfoData*)taosArrayGet(pUpdateBlock->pDataBlock, pInfo->primaryTsIndex);
     ASSERT(pCol->info.type == TSDB_DATA_TYPE_TIMESTAMP);
-    colInfoDataEnsureCapacity(pCol, 0, size);
+    blockDataEnsureCapacity(pUpdateBlock, size);
     for (int32_t i = 0; i < size; i++) {
       TSKEY* pTs = (TSKEY*)taosArrayGet(pInfo->tsArray, i);
       colDataAppend(pCol, i, (char*)pTs, false);
     }
+    for (int32_t i = 0; i < pUpdateBlock->info.numOfCols; i++) {
+      if (i == pInfo->primaryTsIndex) {
+        continue;
+      }
+      SColumnInfoData* pCol = (SColumnInfoData*)taosArrayGet(pUpdateBlock->pDataBlock, i);
+      colDataAppendNNULL(pCol, 0, size);
+    }
     pUpdateBlock->info.rows = size;
     pUpdateBlock->info.type = STREAM_REPROCESS;
     blockDataUpdateTsWindow(pUpdateBlock, 0);
@@ -841,7 +848,9 @@ static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
     }
 
     int32_t current = pInfo->validBlockIndex++;
-    return taosArrayGetP(pInfo->pBlockLists, current);
+    SSDataBlock* pBlock = taosArrayGetP(pInfo->pBlockLists, current);
+    blockDataUpdateTsWindow(pBlock, 0);
+    return pBlock;
   } else {
     if (pInfo->scanMode == STREAM_SCAN_FROM_RES) {
       blockDataDestroy(pInfo->pUpdateRes);
@@ -940,7 +949,7 @@ static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
       }
 
       doFilter(pInfo->pCondition, pInfo->pRes, false);
-      blockDataUpdateTsWindow(pInfo->pRes, 0);
+      blockDataUpdateTsWindow(pInfo->pRes, pInfo->primaryTsIndex);
       break;
     }
 
@@ -1019,10 +1028,6 @@ SOperatorInfo* createStreamScanOperatorInfo(void* pDataReader, SReadHandle* pHan
     goto _error;
   }
 
-  if (isSmaStream(pTableScanNode->triggerType)) {
-    pTwSup->waterMark = getSmaWaterMark(pSTInfo->interval.interval, pTableScanNode->filesFactor);
-  }
-
   if (pSTInfo->interval.interval > 0 && pDataReader) {
     pInfo->pUpdateInfo = updateInfoInitP(&pSTInfo->interval, pTwSup->waterMark);
   } else {

source/libs/function/inc/builtinsimpl.h

@@ -112,6 +112,7 @@ int32_t spreadFunctionMerge(SqlFunctionCtx* pCtx);
 int32_t spreadFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t spreadPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t getSpreadInfoSize();
+int32_t spreadCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx);
 
 bool getElapsedFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
 bool elapsedFunctionSetup(SqlFunctionCtx *pCtx, SResultRowEntryInfo* pResultInfo);
@@ -120,6 +121,7 @@ int32_t elapsedFunctionMerge(SqlFunctionCtx* pCtx);
 int32_t elapsedFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t elapsedPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t getElapsedInfoSize();
+int32_t elapsedCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx);
 
 bool getHistogramFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
 bool histogramFunctionSetup(SqlFunctionCtx *pCtx, SResultRowEntryInfo* pResultInfo);
@@ -128,6 +130,7 @@ int32_t histogramFunctionMerge(SqlFunctionCtx* pCtx);
 int32_t histogramFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t getHistogramInfoSize();
+int32_t histogramCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx);
 
 bool getHLLFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
 int32_t hllFunction(SqlFunctionCtx* pCtx);
@@ -135,6 +138,7 @@ int32_t hllFunctionMerge(SqlFunctionCtx* pCtx);
 int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t hllPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t getHLLInfoSize();
+int32_t hllCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx);
 
 bool getStateFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
 bool stateFunctionSetup(SqlFunctionCtx *pCtx, SResultRowEntryInfo* pResultInfo);

source/libs/function/src/builtins.c

@@ -1112,7 +1112,7 @@ static bool validateHourRange(int8_t hour) {
 }
 
 static bool validateMinuteRange(int8_t hour, int8_t minute, char sign) {
-  if (minute == 0 || (minute == 30 && (hour == 3 || hour == 5) && sign == '-')) {
+  if (minute == 0 || (minute == 30 && (hour == 3 || hour == 5) && sign == '+')) {
     return true;
   }
 
@@ -1447,6 +1447,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .initFunc     = apercentileFunctionSetup,
     .processFunc  = apercentileFunction,
     .finalizeFunc = apercentileFinalize,
+    .invertFunc   = NULL,
     .combineFunc  = apercentileCombine,
     .pPartialFunc = "_apercentile_partial",
     .pMergeFunc   = "_apercentile_merge"
@@ -1459,7 +1460,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getApercentileFuncEnv,
     .initFunc     = apercentileFunctionSetup,
     .processFunc  = apercentileFunction,
-    .finalizeFunc = apercentilePartialFinalize
+    .finalizeFunc = apercentilePartialFinalize,
+    .invertFunc   = NULL,
+    .combineFunc = apercentileCombine,
   },
   {
     .name = "_apercentile_merge",
@@ -1469,7 +1472,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getApercentileFuncEnv,
     .initFunc     = functionSetup,
     .processFunc  = apercentileFunctionMerge,
-    .finalizeFunc = apercentileFinalize
+    .finalizeFunc = apercentileFinalize,
+    .invertFunc   = NULL,
+    .combineFunc = apercentileCombine,
   },
   {
     .name = "top",
@@ -1503,6 +1508,8 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .initFunc     = spreadFunctionSetup,
     .processFunc  = spreadFunction,
     .finalizeFunc = spreadFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = spreadCombine,
     .pPartialFunc = "_spread_partial",
     .pMergeFunc   = "_spread_merge"
   },
@@ -1515,7 +1522,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getSpreadFuncEnv,
     .initFunc     = spreadFunctionSetup,
     .processFunc  = spreadFunction,
-    .finalizeFunc = spreadPartialFinalize
+    .finalizeFunc = spreadPartialFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = spreadCombine,
   },
   {
     .name = "_spread_merge",
@@ -1526,7 +1535,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getSpreadFuncEnv,
     .initFunc     = spreadFunctionSetup,
     .processFunc  = spreadFunctionMerge,
-    .finalizeFunc = spreadFinalize
+    .finalizeFunc = spreadFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = spreadCombine,
   },
   {
     .name = "elapsed",
@@ -1538,6 +1549,8 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .initFunc     = elapsedFunctionSetup,
     .processFunc  = elapsedFunction,
     .finalizeFunc = elapsedFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = elapsedCombine,
     .pPartialFunc = "_elapsed_partial",
     .pMergeFunc   = "_elapsed_merge"
   },
@@ -1550,7 +1563,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getElapsedFuncEnv,
     .initFunc     = elapsedFunctionSetup,
     .processFunc  = elapsedFunction,
-    .finalizeFunc = elapsedPartialFinalize
+    .finalizeFunc = elapsedPartialFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = elapsedCombine,
   },
   {
     .name = "_elapsed_merge",
@@ -1561,7 +1576,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getElapsedFuncEnv,
     .initFunc     = elapsedFunctionSetup,
     .processFunc  = elapsedFunctionMerge,
-    .finalizeFunc = elapsedFinalize
+    .finalizeFunc = elapsedFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = elapsedCombine,
   },
   {
     .name = "last_row",
@@ -1614,8 +1631,10 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .initFunc     = histogramFunctionSetup,
     .processFunc  = histogramFunction,
     .finalizeFunc = histogramFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = histogramCombine,
     .pPartialFunc = "_histogram_partial",
-    .pMergeFunc   = "_histogram_merge"
+    .pMergeFunc   = "_histogram_merge",
   },
   {
     .name = "_histogram_partial",
@@ -1625,7 +1644,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getHistogramFuncEnv,
     .initFunc     = histogramFunctionSetup,
     .processFunc  = histogramFunction,
-    .finalizeFunc = histogramPartialFinalize
+    .finalizeFunc = histogramPartialFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = histogramCombine,
   },
   {
     .name = "_histogram_merge",
@@ -1635,7 +1656,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getHistogramFuncEnv,
     .initFunc     = functionSetup,
     .processFunc  = histogramFunctionMerge,
-    .finalizeFunc = histogramFinalize
+    .finalizeFunc = histogramFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = histogramCombine,
   },
   {
     .name = "hyperloglog",
@@ -1646,6 +1669,8 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .initFunc     = functionSetup,
     .processFunc  = hllFunction,
     .finalizeFunc = hllFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = hllCombine,
     .pPartialFunc = "_hyperloglog_partial",
     .pMergeFunc   = "_hyperloglog_merge"
   },
@@ -1657,7 +1682,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getHLLFuncEnv,
     .initFunc     = functionSetup,
     .processFunc  = hllFunction,
-    .finalizeFunc = hllPartialFinalize
+    .finalizeFunc = hllPartialFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = hllCombine,
   },
   {
     .name = "_hyperloglog_merge",
@@ -1667,7 +1694,9 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .getEnvFunc   = getHLLFuncEnv,
     .initFunc     = functionSetup,
     .processFunc  = hllFunctionMerge,
-    .finalizeFunc = hllFinalize
+    .finalizeFunc = hllFinalize,
+    .invertFunc   = NULL,
+    .combineFunc  = hllCombine,
   },
   {
     .name = "diff",

source/libs/function/src/tpercentile.c

@@ -127,9 +127,11 @@ int32_t tBucketIntHash(tMemBucket *pBucket, const void *value) {
     int64_t delta = v - pBucket->range.i64MinVal;
     index = (delta % pBucket->numOfSlots);
   } else {
-    double slotSpan = (double)span / pBucket->numOfSlots;
-    index = (int32_t)((v - pBucket->range.i64MinVal) / slotSpan);
-    if (v == pBucket->range.i64MaxVal) {
+    double slotSpan = ((double)span) / pBucket->numOfSlots;
+    uint64_t delta = v - pBucket->range.i64MinVal;
+
+    index = (int32_t)(delta / slotSpan);
+    if (v == pBucket->range.i64MaxVal || index == pBucket->numOfSlots) {
       index -= 1;
     }
   }
@@ -324,7 +326,6 @@ int32_t tMemBucketPut(tMemBucket *pBucket, const void *data, size_t size) {
   int32_t bytes = pBucket->bytes;
   for (int32_t i = 0; i < size; ++i) {
     char *d = (char *) data + i * bytes;
-
     int32_t index = (pBucket->hashFunc)(pBucket, d);
     if (index < 0) {
       continue;

source/libs/nodes/src/nodesCodeFuncs.c

@@ -2816,10 +2816,85 @@ static int32_t jsonToTableNode(const SJson* pJson, void* pObj) {
   return code;
 }
 
+static const char* jkTableIndexInfoIntervalUnit = "IntervalUnit";
+static const char* jkTableIndexInfoSlidingUnit = "SlidingUnit";
+static const char* jkTableIndexInfoInterval = "Interval";
+static const char* jkTableIndexInfoOffset = "Offset";
+static const char* jkTableIndexInfoSliding = "Sliding";
+static const char* jkTableIndexInfoDstTbUid = "DstTbUid";
+static const char* jkTableIndexInfoDstVgId = "DstVgId";
+static const char* jkTableIndexInfoEpSet = "EpSet";
+static const char* jkTableIndexInfoExpr = "Expr";
+
+static int32_t tableIndexInfoToJson(const void* pObj, SJson* pJson) {
+  const STableIndexInfo* pNode = (const STableIndexInfo*)pObj;
+
+  int32_t code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoIntervalUnit, pNode->intervalUnit);
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoSlidingUnit, pNode->slidingUnit);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoInterval, pNode->interval);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoOffset, pNode->offset);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoSliding, pNode->sliding);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoDstTbUid, pNode->dstTbUid);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkTableIndexInfoDstVgId, pNode->dstVgId);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddObject(pJson, jkTableIndexInfoEpSet, epSetToJson, &pNode->epSet);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddStringToObject(pJson, jkTableIndexInfoExpr, pNode->expr);
+  }
+
+  return code;
+}
+
+static int32_t jsonToTableIndexInfo(const SJson* pJson, void* pObj) {
+  STableIndexInfo* pNode = (STableIndexInfo*)pObj;
+
+  int32_t code = tjsonGetTinyIntValue(pJson, jkTableIndexInfoIntervalUnit, &pNode->intervalUnit);
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetTinyIntValue(pJson, jkTableIndexInfoSlidingUnit, &pNode->slidingUnit);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetBigIntValue(pJson, jkTableIndexInfoInterval, &pNode->interval);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetBigIntValue(pJson, jkTableIndexInfoOffset, &pNode->offset);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetBigIntValue(pJson, jkTableIndexInfoSliding, &pNode->sliding);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetBigIntValue(pJson, jkTableIndexInfoDstTbUid, &pNode->dstTbUid);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonGetIntValue(pJson, jkTableIndexInfoDstVgId, &pNode->dstVgId);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonToObject(pJson, jkTableIndexInfoEpSet, jsonToEpSet, &pNode->epSet);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonDupStringValue(pJson, jkTableIndexInfoExpr, &pNode->expr);
+  }
+
+  return code;
+}
+
 static const char* jkRealTableMetaSize = "MetaSize";
 static const char* jkRealTableMeta = "Meta";
 static const char* jkRealTableVgroupsInfoSize = "VgroupsInfoSize";
 static const char* jkRealTableVgroupsInfo = "VgroupsInfo";
+static const char* jkRealTableSmaIndexes = "SmaIndexes";
 
 static int32_t realTableNodeToJson(const void* pObj, SJson* pJson) {
   const SRealTableNode* pNode = (const SRealTableNode*)pObj;
@@ -2837,6 +2912,9 @@ static int32_t realTableNodeToJson(const void* pObj, SJson* pJson) {
   if (TSDB_CODE_SUCCESS == code) {
     code = tjsonAddObject(pJson, jkRealTableVgroupsInfo, vgroupsInfoToJson, pNode->pVgroupList);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddTArray(pJson, jkRealTableSmaIndexes, tableIndexInfoToJson, pNode->pSmaIndexes);
+  }
 
   return code;
 }
@@ -2858,6 +2936,10 @@ static int32_t jsonToRealTableNode(const SJson* pJson, void* pObj) {
   if (TSDB_CODE_SUCCESS == code) {
     code = tjsonMakeObject(pJson, jkRealTableVgroupsInfo, jsonToVgroupsInfo, (void**)&pNode->pVgroupList, objSize);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    code =
+        tjsonToTArray(pJson, jkRealTableSmaIndexes, jsonToTableIndexInfo, &pNode->pSmaIndexes, sizeof(STableIndexInfo));
+  }
 
   return code;
 }
@@ -4214,6 +4296,7 @@ int32_t nodesStringToList(const char* pStr, SNodeList** pList) {
   tjsonDelete(pJson);
   if (TSDB_CODE_SUCCESS != code) {
     nodesDestroyList(*pList);
+    *pList = NULL;
     terrno = code;
     return code;
   }

source/libs/parser/inc/parUtil.h

@@ -46,6 +46,7 @@ typedef struct SParseMetaCache {
   SHashObj* pDbInfo;       // key is tbFName, element is SDbInfo*
   SHashObj* pUserAuth;     // key is SUserAuthInfo serialized string, element is bool indicating whether or not to pass
   SHashObj* pUdf;          // key is funcName, element is SFuncInfo*
+  SHashObj* pTableIndex;   // key is tbFName, element is SArray<STableIndexInfo>*
 } SParseMetaCache;
 
 int32_t generateSyntaxErrMsg(SMsgBuf* pBuf, int32_t errCode, ...);
@@ -58,7 +59,7 @@ int32_t       getNumOfColumns(const STableMeta* pTableMeta);
 int32_t       getNumOfTags(const STableMeta* pTableMeta);
 STableComInfo getTableInfo(const STableMeta* pTableMeta);
 STableMeta*   tableMetaDup(const STableMeta* pTableMeta);
-int32_t       parseJsontoTagData(const char* json, SArray* pTagVals, STag **ppTag, SMsgBuf* pMsgBuf);
+int32_t       parseJsontoTagData(const char* json, SArray* pTagVals, STag** ppTag, SMsgBuf* pMsgBuf);
 
 int32_t trimString(const char* src, int32_t len, char* dst, int32_t dlen);
 
@@ -75,6 +76,7 @@ int32_t reserveUserAuthInCache(int32_t acctId, const char* pUser, const char* pD
                                SParseMetaCache* pMetaCache);
 int32_t reserveUserAuthInCacheExt(const char* pUser, const SName* pName, AUTH_TYPE type, SParseMetaCache* pMetaCache);
 int32_t reserveUdfInCache(const char* pFunc, SParseMetaCache* pMetaCache);
+int32_t reserveTableIndexInCache(int32_t acctId, const char* pDb, const char* pTable, SParseMetaCache* pMetaCache);
 int32_t getTableMetaFromCache(SParseMetaCache* pMetaCache, const SName* pName, STableMeta** pMeta);
 int32_t getDbVgInfoFromCache(SParseMetaCache* pMetaCache, const char* pDbFName, SArray** pVgInfo);
 int32_t getTableVgroupFromCache(SParseMetaCache* pMetaCache, const SName* pName, SVgroupInfo* pVgroup);
@@ -84,6 +86,7 @@ int32_t getDbCfgFromCache(SParseMetaCache* pMetaCache, const char* pDbFName, SDb
 int32_t getUserAuthFromCache(SParseMetaCache* pMetaCache, const char* pUser, const char* pDbFName, AUTH_TYPE type,
                              bool* pPass);
 int32_t getUdfInfoFromCache(SParseMetaCache* pMetaCache, const char* pFunc, SFuncInfo* pInfo);
+int32_t getTableIndexFromCache(SParseMetaCache* pMetaCache, const SName* pName, SArray** pIndexes);
 
 #ifdef __cplusplus
 }

source/libs/planner/test/planOtherTest.cpp

@@ -42,7 +42,9 @@ TEST_F(PlanOtherTest, createStreamUseSTable) {
 TEST_F(PlanOtherTest, createSmaIndex) {
   useDb("root", "test");
 
-  run("create sma index index1 on t1 function(max(c1), min(c3 + 10), sum(c4)) interval(10s)");
+  run("CREATE SMA INDEX idx1 ON t1 FUNCTION(MAX(c1), MIN(c3 + 10), SUM(c4)) INTERVAL(10s)");
+
+  run("SELECT SUM(c4) FROM t1 INTERVAL(10s)");
 }
 
 TEST_F(PlanOtherTest, explain) {