Merge branch '3.0' into cpwu/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/common/tcommon.h

@@ -37,19 +37,12 @@ enum {
   TMQ_MSG_TYPE__EP_RSP,
 };
 
-enum {
-  STREAM_TRIGGER__AT_ONCE = 1,
-  STREAM_TRIGGER__WINDOW_CLOSE,
-  STREAM_TRIGGER__BY_COUNT,
-  STREAM_TRIGGER__BY_BATCH_COUNT,
-  STREAM_TRIGGER__BY_EVENT_TIME,
-};
-
 typedef enum EStreamType {
   STREAM_NORMAL = 1,
   STREAM_INVERT,
   STREAM_REPROCESS,
   STREAM_INVALID,
+  STREAM_GET_ALL,
 } EStreamType;
 
 typedef struct {

include/common/tglobal.h

@@ -96,6 +96,7 @@ extern bool    tsDeadLockKillQuery;
 
 // query client
 extern int32_t tsQueryPolicy;
+extern int32_t tsQuerySmaOptimize;
 
 // client
 extern int32_t tsMinSlidingTime;

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];
@@ -2337,24 +2336,26 @@ typedef struct {
 } SVgEpSet;
 
 typedef struct {
-  int8_t    version;       // for compatibility(default 0)
-  int8_t    intervalUnit;  // MACRO: TIME_UNIT_XXX
-  int8_t    slidingUnit;   // MACRO: TIME_UNIT_XXX
-  int8_t    timezoneInt;   // sma data expired if timezone changes.
-  int32_t   dstVgId;
-  char      indexName[TSDB_INDEX_NAME_LEN];
-  int32_t   exprLen;
-  int32_t   tagsFilterLen;
-  int32_t   numOfVgroups;
-  int64_t   indexUid;
-  tb_uid_t  tableUid;  // super/child/common table uid
-  int64_t   interval;
-  int64_t   offset;  // use unit by precision of DB
-  int64_t   sliding;
-  char*     expr;  // sma expression
-  char*     tagsFilter;
-  SVgEpSet* pVgEpSet;
-} STSma;  // Time-range-wise SMA
+  int8_t         version;       // for compatibility(default 0)
+  int8_t         intervalUnit;  // MACRO: TIME_UNIT_XXX
+  int8_t         slidingUnit;   // MACRO: TIME_UNIT_XXX
+  int8_t         timezoneInt;   // sma data expired if timezone changes.
+  int32_t        dstVgId;
+  char           indexName[TSDB_INDEX_NAME_LEN];
+  int32_t        exprLen;
+  int32_t        tagsFilterLen;
+  int64_t        indexUid;
+  tb_uid_t       tableUid;  // super/child/common table uid
+  tb_uid_t       dstTbUid;  // for dstVgroup
+  int64_t        interval;
+  int64_t        offset;  // use unit by precision of DB
+  int64_t        sliding;
+  char*          dstTbName;  // for dstVgroup
+  char*          expr;       // sma expression
+  char*          tagsFilter;
+  SSchemaWrapper schemaRow;  // for dstVgroup
+  SSchemaWrapper schemaTag;  // for dstVgroup
+} STSma;                     // Time-range-wise SMA
 
 typedef STSma SVCreateTSmaReq;
 
@@ -2438,27 +2439,6 @@ static int32_t tDecodeTSmaWrapper(SDecoder* pDecoder, STSmaWrapper* pReq) {
   return 0;
 }
 
-typedef struct {
-  int64_t     indexUid;
-  STimeWindow queryWindow;
-} SVGetTsmaExpWndsReq;
-
-#define SMA_WNDS_EXPIRE_FLAG      (0x1)
-#define SMA_WNDS_IS_EXPIRE(flag)  (((flag)&SMA_WNDS_EXPIRE_FLAG) != 0)
-#define SMA_WNDS_SET_EXPIRE(flag) ((flag) |= SMA_WNDS_EXPIRE_FLAG)
-
-typedef struct {
-  int64_t indexUid;
-  int8_t  flags;  // 0x1 all window expired
-  int32_t numExpWnds;
-  TSKEY   wndSKeys[];
-} SVGetTsmaExpWndsRsp;
-
-int32_t tEncodeSVGetTSmaExpWndsReq(SEncoder* pCoder, const SVGetTsmaExpWndsReq* pReq);
-int32_t tDecodeSVGetTsmaExpWndsReq(SDecoder* pCoder, SVGetTsmaExpWndsReq* pReq);
-int32_t tEncodeSVGetTSmaExpWndsRsp(SEncoder* pCoder, const SVGetTsmaExpWndsRsp* pReq);
-int32_t tDecodeSVGetTsmaExpWndsRsp(SDecoder* pCoder, SVGetTsmaExpWndsRsp* pReq);
-
 typedef struct {
   int idx;
 } SMCreateFullTextReq;
@@ -2507,7 +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;
@@ -2518,7 +2498,8 @@ typedef struct {
 
 int32_t tSerializeSTableIndexRsp(void* buf, int32_t bufLen, const STableIndexRsp* pRsp);
 int32_t tDeserializeSTableIndexRsp(void* buf, int32_t bufLen, STableIndexRsp* pRsp);
-void    tFreeSTableIndexInfo(void* pInfo);
+
+void tFreeSTableIndexInfo(void* pInfo);
 
 typedef struct {
   int8_t  mqMsgType;

include/common/tmsgdef.h

@@ -190,7 +190,6 @@ enum {
   TD_DEF_MSG_TYPE(TDMT_VND_CANCEL_SMA, "vnode-cancel-sma", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_VND_DROP_SMA, "vnode-drop-sma", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_VND_SUBMIT_RSMA, "vnode-submit-rsma", SSubmitReq, SSubmitRsp)
-  TD_DEF_MSG_TYPE(TDMT_VND_GET_TSMA_EXP_WNDS, "vnode-get-tsma-expired-windows", SVGetTsmaExpWndsReq, SVGetTsmaExpWndsRsp)
   TD_DEF_MSG_TYPE(TDMT_VND_DELETE, "delete-data", SVDeleteReq, SVDeleteRsp)
   TD_DEF_MSG_TYPE(TDMT_VND_ALTER_CONFIG, "alter-config", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_VND_ALTER_REPLICA, "alter-replica", NULL, NULL)
@@ -221,7 +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)
@@ -237,6 +236,7 @@ enum {
   TD_DEF_MSG_TYPE(TDMT_SYNC_CONFIG_CHANGE, "sync-config-change", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_SYNC_SNAPSHOT_SEND, "sync-snapshot-send", NULL, NULL)
   TD_DEF_MSG_TYPE(TDMT_SYNC_SNAPSHOT_RSP, "sync-snapshot-rsp", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_SYNC_LEADER_TRANSFER, "sync-leader-transfer", NULL, NULL)
   
 #if defined(TD_MSG_NUMBER_)
   TDMT_MAX

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/function/functionMgt.h

@@ -121,7 +121,7 @@ typedef enum EFunctionType {
 
   // internal function
   FUNCTION_TYPE_SELECT_VALUE,
-  FUNCTION_TYPE_BLOCK_DIST,   // block distribution aggregate function
+  FUNCTION_TYPE_BLOCK_DIST,  // block distribution aggregate function
 
   // distributed splitting functions
   FUNCTION_TYPE_APERCENTILE_PARTIAL,
@@ -170,6 +170,7 @@ bool fmIsMultiResFunc(int32_t funcId);
 bool fmIsRepeatScanFunc(int32_t funcId);
 bool fmIsUserDefinedFunc(int32_t funcId);
 bool fmIsDistExecFunc(int32_t funcId);
+bool fmIsForbidFillFunc(int32_t funcId);
 
 int32_t fmGetDistMethod(const SFunctionNode* pFunc, SFunctionNode** pPartialFunc, SFunctionNode** pMergeFunc);
 

include/libs/nodes/cmdnodes.h

@@ -47,7 +47,7 @@ typedef struct SDatabaseOptions {
   int32_t     maxRowsPerBlock;
   int32_t     minRowsPerBlock;
   SNodeList*  pKeep;
-  int32_t     keep[3];
+  int64_t     keep[3];
   int32_t     pages;
   int32_t     pagesize;
   char        precisionStr[3];

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

@@ -48,6 +48,7 @@ typedef enum {
   TAOS_SYNC_PROPOSE_SUCCESS = 0,
   TAOS_SYNC_PROPOSE_NOT_LEADER = 1,
   TAOS_SYNC_PROPOSE_OTHER_ERROR = 2,
+  TAOS_SYNC_ONLY_ONE_REPLICA = 3,
 } ESyncProposeCode;
 
 typedef enum {
@@ -83,8 +84,10 @@ 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 +109,7 @@ 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 +187,6 @@ 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 +196,13 @@ 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);
+
+int32_t syncLeaderTransfer(int64_t rid);
+int32_t syncLeaderTransferTo(int64_t rid, SNodeInfo newLeader);
 
 // to be moved to static
 void syncStartNormal(int64_t rid);

include/libs/sync/syncTools.h

@@ -398,6 +398,8 @@ typedef struct SyncSnapshotSend {
   SyncTerm  term;
   SyncIndex lastIndex;  // lastIndex of snapshot
   SyncTerm  lastTerm;   // lastTerm of snapshot
+  SyncIndex lastConfigIndex;
+  SSyncCfg  lastConfig;
   SyncTerm  privateTerm;
   int32_t   seq;
   uint32_t  dataLen;
@@ -456,6 +458,36 @@ void syncSnapshotRspPrint2(char* s, const SyncSnapshotRsp* pMsg);
 void syncSnapshotRspLog(const SyncSnapshotRsp* pMsg);
 void syncSnapshotRspLog2(char* s, const SyncSnapshotRsp* pMsg);
 
+// ---------------------------------------------
+typedef struct SyncLeaderTransfer {
+  uint32_t bytes;
+  int32_t  vgId;
+  uint32_t msgType;
+  /*
+   SRaftId  srcId;
+   SRaftId  destId;
+   */
+  SRaftId newLeaderId;
+} SyncLeaderTransfer;
+
+SyncLeaderTransfer* syncLeaderTransferBuild(int32_t vgId);
+void                syncLeaderTransferDestroy(SyncLeaderTransfer* pMsg);
+void                syncLeaderTransferSerialize(const SyncLeaderTransfer* pMsg, char* buf, uint32_t bufLen);
+void                syncLeaderTransferDeserialize(const char* buf, uint32_t len, SyncLeaderTransfer* pMsg);
+char*               syncLeaderTransferSerialize2(const SyncLeaderTransfer* pMsg, uint32_t* len);
+SyncLeaderTransfer* syncLeaderTransferDeserialize2(const char* buf, uint32_t len);
+void                syncLeaderTransfer2RpcMsg(const SyncLeaderTransfer* pMsg, SRpcMsg* pRpcMsg);
+void                syncLeaderTransferFromRpcMsg(const SRpcMsg* pRpcMsg, SyncLeaderTransfer* pMsg);
+SyncLeaderTransfer* syncLeaderTransferFromRpcMsg2(const SRpcMsg* pRpcMsg);
+cJSON*              syncLeaderTransfer2Json(const SyncLeaderTransfer* pMsg);
+char*               syncLeaderTransfer2Str(const SyncLeaderTransfer* pMsg);
+
+// for debug ----------------------
+void syncLeaderTransferPrint(const SyncLeaderTransfer* pMsg);
+void syncLeaderTransferPrint2(char* s, const SyncLeaderTransfer* pMsg);
+void syncLeaderTransferLog(const SyncLeaderTransfer* pMsg);
+void syncLeaderTransferLog2(char* s, const SyncLeaderTransfer* pMsg);
+
 // on message ----------------------
 int32_t syncNodeOnPingCb(SSyncNode* ths, SyncPing* pMsg);
 int32_t syncNodeOnPingReplyCb(SSyncNode* ths, SyncPingReply* pMsg);

include/util/taoserror.h

@@ -352,9 +352,6 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_TDB_NO_CACHE_LAST_ROW         TAOS_DEF_ERROR_CODE(0, 0x0619)
 #define TSDB_CODE_TDB_TABLE_RECREATED           TAOS_DEF_ERROR_CODE(0, 0x061A)
 #define TSDB_CODE_TDB_TDB_ENV_OPEN_ERROR        TAOS_DEF_ERROR_CODE(0, 0x061B)
-#define TSDB_CODE_TDB_NO_SMA_INDEX_IN_META      TAOS_DEF_ERROR_CODE(0, 0x061C)
-#define TSDB_CODE_TDB_INVALID_SMA_STAT          TAOS_DEF_ERROR_CODE(0, 0x061D)
-#define TSDB_CODE_TDB_TSMA_ALREADY_EXIST        TAOS_DEF_ERROR_CODE(0, 0x061E)
 
 // query
 #define TSDB_CODE_QRY_INVALID_QHANDLE           TAOS_DEF_ERROR_CODE(0, 0x0700)
@@ -655,6 +652,7 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_PAR_INTERNAL_ERROR            TAOS_DEF_ERROR_CODE(0, 0x2654)
 #define TSDB_CODE_PAR_INVALID_DELETE_WHERE      TAOS_DEF_ERROR_CODE(0, 0x2655)
 #define TSDB_CODE_PAR_INVALID_REDISTRIBUTE_VG   TAOS_DEF_ERROR_CODE(0, 0x2656)
+#define TSDB_CODE_PAR_FILL_NOT_ALLOWED_FUNC     TAOS_DEF_ERROR_CODE(0, 0x2657)
 
 //planner
 #define TSDB_CODE_PLAN_INTERNAL_ERROR           TAOS_DEF_ERROR_CODE(0, 0x2700)
@@ -685,6 +683,19 @@ int32_t* taosGetErrno();
 #define TSDB_CODE_SML_INVALID_DATA              TAOS_DEF_ERROR_CODE(0, 0x3002)
 #define TSDB_CODE_SML_INVALID_DB_CONF           TAOS_DEF_ERROR_CODE(0, 0x3003)
 
+//tsma
+#define TSDB_CODE_TSMA_ALREADY_EXIST             TAOS_DEF_ERROR_CODE(0, 0x3100)
+#define TSDB_CODE_TSMA_NO_INDEX_IN_META          TAOS_DEF_ERROR_CODE(0, 0x3101)
+#define TSDB_CODE_TSMA_INVALID_ENV               TAOS_DEF_ERROR_CODE(0, 0x3102)
+#define TSDB_CODE_TSMA_INVALID_STAT              TAOS_DEF_ERROR_CODE(0, 0x3103)
+#define TSDB_CODE_TSMA_NO_INDEX_IN_CACHE         TAOS_DEF_ERROR_CODE(0, 0x3104)
+#define TSDB_CODE_TSMA_RM_SKEY_IN_HASH           TAOS_DEF_ERROR_CODE(0, 0x3105)
+
+//rsma
+#define TSDB_CODE_RSMA_INVALID_ENV               TAOS_DEF_ERROR_CODE(0, 0x3150)
+#define TSDB_CODE_RSMA_INVALID_STAT              TAOS_DEF_ERROR_CODE(0, 0x3151)
+
+
 #ifdef __cplusplus
 }
 #endif

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

include/util/tlrucache.h

+/*
+ * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
+ *
+ * This program is free software: you can use, redistribute, and/or modify
+ * it under the terms of the GNU Affero General Public License, version 3
+ * or later ("AGPL"), as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _TD_UTIL_LRUCACHE_H_
+#define _TD_UTIL_LRUCACHE_H_
+
+#include "thash.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct SLRUCache SLRUCache;
+
+typedef void (*_taos_lru_deleter_t)(const void *key, size_t keyLen, void *value);
+
+typedef struct LRUHandle LRUHandle;
+
+typedef enum {
+  TAOS_LRU_PRIORITY_HIGH,
+  TAOS_LRU_PRIORITY_LOW
+} LRUPriority;
+  
+typedef enum {
+  TAOS_LRU_STATUS_OK,
+  TAOS_LRU_STATUS_FAIL,
+  TAOS_LRU_STATUS_INCOMPLETE,
+  TAOS_LRU_STATUS_OK_OVERWRITTEN
+} LRUStatus;
+  
+SLRUCache *taosLRUCacheInit(size_t capacity, int numShardBits, double highPriPoolRatio);  
+void taosLRUCacheCleanup(SLRUCache *cache);
+
+LRUStatus taosLRUCacheInsert(SLRUCache *cache, const void *key, size_t keyLen, void *value, size_t charge,
+                             _taos_lru_deleter_t deleter, LRUHandle **handle, LRUPriority priority);
+LRUHandle *taosLRUCacheLookup(SLRUCache * cache, const void *key, size_t keyLen);
+void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
+
+void taosLRUCacheEraseUnrefEntries(SLRUCache *cache);
+
+bool taosLRUCacheRef(SLRUCache *cache, LRUHandle *handle);
+bool taosLRUCacheRelease(SLRUCache *cache, LRUHandle *handle, bool eraseIfLastRef);
+
+void* taosLRUCacheValue(SLRUCache *cache, LRUHandle *handle);
+
+size_t taosLRUCacheGetUsage(SLRUCache *cache);
+size_t taosLRUCacheGetPinnedUsage(SLRUCache *cache);
+
+void taosLRUCacheSetCapacity(SLRUCache *cache, size_t capacity);
+size_t taosLRUCacheGetCapacity(SLRUCache *cache);
+
+void taosLRUCacheSetStrictCapacity(SLRUCache *cache, bool strict);
+bool taosLRUCacheIsStrictCapacity(SLRUCache *cache);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // _TD_UTIL_LRUCACHE_H_

source/client/src/clientEnv.c

@@ -167,7 +167,7 @@ void *createTscObj(const char *user, const char *auth, const char *db, int32_t c
 
   taosThreadMutexInit(&pObj->mutex, NULL);
   pObj->id = taosAddRef(clientConnRefPool, pObj);
-  pObj->schemalessType = 0;
+  pObj->schemalessType = 1;
 
   tscDebug("connObj created, 0x%" PRIx64, pObj->id);
   return pObj;

source/client/src/clientImpl.c

@@ -689,16 +689,15 @@ void launchAsyncQuery(SRequestObj* pRequest, SQuery* pQuery) {
                           .msgLen = ERROR_MSG_BUF_DEFAULT_SIZE};
 
       SAppInstInfo* pAppInfo = getAppInfo(pRequest);
-
       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) {
         schedulerAsyncExecJob(pAppInfo->pTransporter, pNodeList, pRequest->body.pDag, &pRequest->body.queryJob,
                               pRequest->sqlstr, pRequest->metric.start, schedulerExecCb, pRequest);
       } else {
+        tscError("0x%"PRIx64" failed to create query plan, code:%s 0x%"PRIx64, pRequest->self, tstrerror(code), pRequest->requestId);
         pRequest->body.queryFp(pRequest->body.param, pRequest, 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  20000
 //=================================================================================================
 typedef TSDB_SML_PROTOCOL_TYPE SMLProtocolType;
 
@@ -153,8 +159,16 @@ typedef struct {
   int64_t endTime;
 } SSmlCostInfo;
 
+typedef struct{
+  SRequestObj*    request;
+  tsem_t          sem;
+  TdThreadSpinlock lock;
+} Params;
+
 typedef struct {
   int64_t           id;
+  Params            *params;
+  bool              isLast;
 
   SMLProtocolType   protocol;
   int8_t            precision;
@@ -292,19 +306,10 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
       const char* errStr = taos_errstr(res);
       if (code != TSDB_CODE_SUCCESS) {
         uError("SML:0x%"PRIx64" apply schema action. error: %s", info->id, errStr);
+        taosMsleep(100);
       }
       taos_free_result(res);
 
-//      if (code == TSDB_CODE_MND_FIELD_ALREADY_EXIST || code == TSDB_CODE_MND_TAG_ALREADY_EXIST || tscDupColNames) {
-      if (code == TSDB_CODE_MND_TAG_ALREADY_EXIST) {
-        TAOS_RES* res2 = taos_query(info->taos, "RESET QUERY CACHE");
-        code = taos_errno(res2);
-        if (code != TSDB_CODE_SUCCESS) {
-          uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
-        }
-        taos_free_result(res2);
-        taosMsleep(10);
-      }
       break;
     }
     case SCHEMA_ACTION_ADD_TAG: {
@@ -316,19 +321,10 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
       const char* errStr = taos_errstr(res);
       if (code != TSDB_CODE_SUCCESS) {
         uError("SML:0x%"PRIx64" apply schema action. error : %s", info->id, taos_errstr(res));
+        taosMsleep(100);
       }
       taos_free_result(res);
 
-//      if (code ==TSDB_CODE_MND_TAG_ALREADY_EXIST || code == TSDB_CODE_MND_FIELD_ALREAY_EXIST || tscDupColNames) {
-      if (code ==TSDB_CODE_MND_TAG_ALREADY_EXIST) {
-        TAOS_RES* res2 = taos_query(info->taos, "RESET QUERY CACHE");
-        code = taos_errno(res2);
-        if (code != TSDB_CODE_SUCCESS) {
-          uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
-        }
-        taos_free_result(res2);
-        taosMsleep(10);
-      }
       break;
     }
     case SCHEMA_ACTION_CHANGE_COLUMN_SIZE: {
@@ -339,19 +335,10 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
       code = taos_errno(res);
       if (code != TSDB_CODE_SUCCESS) {
         uError("SML:0x%"PRIx64" apply schema action. error : %s", info->id, taos_errstr(res));
+        taosMsleep(100);
       }
       taos_free_result(res);
 
-//      if (code == TSDB_CODE_MND_INVALID_COLUMN_LENGTH || code == TSDB_CODE_TSC_INVALID_COLUMN_LENGTH) {
-      if (code == TSDB_CODE_TSC_INVALID_COLUMN_LENGTH) {
-        TAOS_RES* res2 = taos_query(info->taos, "RESET QUERY CACHE");
-        code = taos_errno(res2);
-        if (code != TSDB_CODE_SUCCESS) {
-          uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
-        }
-        taos_free_result(res2);
-        taosMsleep(10);
-      }
       break;
     }
     case SCHEMA_ACTION_CHANGE_TAG_SIZE: {
@@ -362,19 +349,10 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
       code = taos_errno(res);
       if (code != TSDB_CODE_SUCCESS) {
         uError("SML:0x%"PRIx64" apply schema action. error : %s", info->id, taos_errstr(res));
+        taosMsleep(100);
       }
       taos_free_result(res);
 
-//      if (code == TSDB_CODE_MND_INVALID_TAG_LENGTH || code == TSDB_CODE_TSC_INVALID_TAG_LENGTH) {
-      if (code == TSDB_CODE_TSC_INVALID_TAG_LENGTH) {
-        TAOS_RES* res2 = taos_query(info->taos, "RESET QUERY CACHE");
-        code = taos_errno(res2);
-        if (code != TSDB_CODE_SUCCESS) {
-          uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
-        }
-        taos_free_result(res2);
-        taosMsleep(10);
-      }
       break;
     }
     case SCHEMA_ACTION_CREATE_STABLE: {
@@ -414,18 +392,10 @@ static int32_t smlApplySchemaAction(SSmlHandle* info, SSchemaAction* action) {
       code = taos_errno(res);
       if (code != TSDB_CODE_SUCCESS) {
         uError("SML:0x%"PRIx64" apply schema action. error : %s", info->id, taos_errstr(res));
+        taosMsleep(100);
       }
       taos_free_result(res);
 
-      if (code == TSDB_CODE_MND_STB_ALREADY_EXIST) {
-        TAOS_RES* res2 = taos_query(info->taos, "RESET QUERY CACHE");
-        code = taos_errno(res2);
-        if (code != TSDB_CODE_SUCCESS) {
-          uError("SML:0x%" PRIx64 " apply schema action. reset query cache. error: %s", info->id, taos_errstr(res2));
-        }
-        taos_free_result(res2);
-        taosMsleep(10);
-      }
       break;
     }
 
@@ -459,6 +429,21 @@ static int32_t smlProcessSchemaAction(SSmlHandle* info, SSchema* schemaField, SH
   return TSDB_CODE_SUCCESS;
 }
 
+static int32_t smlCheckMeta(SSchema* schema, int32_t length, SArray* cols){
+  SHashObj *hashTmp = taosHashInit(length, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BINARY), true, HASH_NO_LOCK);
+  for(uint16_t i = 0; i < length; i++){
+    taosHashPut(hashTmp, schema[i].name, strlen(schema[i].name), &i, SHORT_BYTES);
+  }
+
+  for(int32_t i = 0; i < taosArrayGetSize(cols); i++){
+    SSmlKv* kv = (SSmlKv*)taosArrayGetP(cols, i);
+    if(taosHashGet(hashTmp, kv->key, kv->keyLen) == NULL){
+      return -1;
+    }
+  }
+  return 0;
+}
+
 static int32_t smlModifyDBSchemas(SSmlHandle* info) {
   int32_t code = 0;
   SEpSet ep = getEpSet_s(&info->taos->pAppInfo->mgmtEp);
@@ -469,6 +454,7 @@ static int32_t smlModifyDBSchemas(SSmlHandle* info) {
   while (tableMetaSml) {
     SSmlSTableMeta* sTableData = *tableMetaSml;
     STableMeta *pTableMeta = NULL;
+    bool needCheckMeta = false;     // for multi thread
 
     size_t superTableLen = 0;
     void *superTable = taosHashGetKey(tableMetaSml, &superTableLen);
@@ -519,6 +505,7 @@ static int32_t smlModifyDBSchemas(SSmlHandle* info) {
       if (code != TSDB_CODE_SUCCESS) {
         goto end;
       }
+      needCheckMeta = true;
     } else {
       uError("SML:0x%"PRIx64" load table meta error: %s", info->id, tstrerror(code));
       goto end;
@@ -530,6 +517,20 @@ static int32_t smlModifyDBSchemas(SSmlHandle* info) {
       uError("SML:0x%"PRIx64" catalogGetSTableMeta failed. super table name %s", info->id, (char*)superTable);
       goto end;
     }
+
+    if(needCheckMeta){
+      code = smlCheckMeta(&(pTableMeta->schema[pTableMeta->tableInfo.numOfColumns]), pTableMeta->tableInfo.numOfTags, sTableData->tags);
+      if (code != TSDB_CODE_SUCCESS) {
+        uError("SML:0x%"PRIx64" check tag failed. super table name %s", info->id, (char*)superTable);
+        goto end;
+      }
+      code = smlCheckMeta(&(pTableMeta->schema[0]), pTableMeta->tableInfo.numOfColumns, sTableData->cols);
+      if (code != TSDB_CODE_SUCCESS) {
+        uError("SML:0x%"PRIx64" check cols failed. super table name %s", info->id, (char*)superTable);
+        goto end;
+      }
+    }
+
     sTableData->tableMeta = pTableMeta;
 
     tableMetaSml = (SSmlSTableMeta**)taosHashIterate(info->superTables, tableMetaSml);
@@ -541,56 +542,6 @@ 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;
@@ -1327,9 +1278,46 @@ static void smlDestroyTableInfo(SSmlHandle* info, SSmlTableInfo *tag){
   taosMemoryFree(tag);
 }
 
+static int32_t smlKvTimeArrayCompare(const void* key1, const void* key2) {
+  SArray *s1 = *(SArray **)key1;
+  SArray *s2 = *(SArray **)key2;
+  SSmlKv *kv1 = (SSmlKv *)taosArrayGetP(s1, 0);
+  SSmlKv *kv2 = (SSmlKv *)taosArrayGetP(s2, 0);
+  ASSERT(kv1->type == TSDB_DATA_TYPE_TIMESTAMP);
+  ASSERT(kv2->type == TSDB_DATA_TYPE_TIMESTAMP);
+  if (kv1->i < kv2->i) {
+    return -1;
+  } else if (kv1->i > kv2->i) {
+    return 1;
+  } else {
+    return 0;
+  }
+}
+
+static int32_t smlKvTimeHashCompare(const void* key1, const void* key2) {
+  SHashObj *s1 = *(SHashObj **)key1;
+  SHashObj *s2 = *(SHashObj **)key2;
+  SSmlKv *kv1 = (SSmlKv *)taosHashGet(s1, TS, TS_LEN);
+  SSmlKv *kv2 = (SSmlKv *)taosHashGet(s2, TS, TS_LEN);
+  ASSERT(kv1->type == TSDB_DATA_TYPE_TIMESTAMP);
+  ASSERT(kv2->type == TSDB_DATA_TYPE_TIMESTAMP);
+  if (kv1->i < kv2->i) {
+    return -1;
+  } else if (kv1->i > kv2->i) {
+    return 1;
+  } else {
+    return 0;
+  }
+}
+
 static int32_t smlDealCols(SSmlTableInfo* oneTable, bool dataFormat, SArray *cols){
   if(dataFormat){
-    taosArrayPush(oneTable->cols, &cols);
+    void *p = taosArraySearch(oneTable->cols, &cols, smlKvTimeArrayCompare, TD_GE);
+    if(p == NULL){
+      taosArrayPush(oneTable->cols, &cols);
+    }else{
+      taosArrayInsert(oneTable->cols, TARRAY_ELEM_IDX(oneTable->cols, p), &cols);
+    }
     return TSDB_CODE_SUCCESS;
   }
 
@@ -1342,8 +1330,13 @@ static int32_t smlDealCols(SSmlTableInfo* oneTable, bool dataFormat, SArray *col
     SSmlKv *kv = (SSmlKv *)taosArrayGetP(cols, i);
     taosHashPut(kvHash, kv->key, kv->keyLen, &kv, POINTER_BYTES);
   }
-  taosArrayPush(oneTable->cols, &kvHash);
 
+  void *p = taosArraySearch(oneTable->cols, &kvHash, smlKvTimeHashCompare, TD_GE);
+  if(p == NULL){
+    taosArrayPush(oneTable->cols, &kvHash);
+  }else{
+    taosArrayInsert(oneTable->cols, TARRAY_ELEM_IDX(oneTable->cols, p), &kvHash);
+  }
   return TSDB_CODE_SUCCESS;
 }
 
@@ -1426,6 +1419,7 @@ static void smlDestroyInfo(SSmlHandle* info){
   if(!info->dataFormat){
     taosArrayDestroy(info->colsContainer);
   }
+  destroyRequest(info->pRequest);
   taosMemoryFreeClear(info);
 }
 
@@ -2206,7 +2200,6 @@ end:
   return ret;
 }
 
-
 static int32_t smlInsertData(SSmlHandle* info) {
   int32_t code = TSDB_CODE_SUCCESS;
 
@@ -2236,6 +2229,7 @@ static int32_t smlInsertData(SSmlHandle* info) {
     code = smlBindData(info->exec, tableData->tags, (*pMeta)->cols, tableData->cols, info->dataFormat,
                        (*pMeta)->tableMeta, tableData->childTableName, info->msgBuf.buf, info->msgBuf.len);
     if(code != TSDB_CODE_SUCCESS){
+      uError("SML:0x%"PRIx64" smlBindData failed", info->id);
       return code;
     }
     oneTable = (SSmlTableInfo**)taosHashIterate(info->childTables, oneTable);
@@ -2248,10 +2242,12 @@ 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){
@@ -2299,7 +2295,7 @@ static int smlProcess(SSmlHandle *info, char* lines[], int numLines) {
   code = smlParseLine(info, lines, numLines);
   if (code != 0) {
     uError("SML:0x%"PRIx64" smlParseLine error : %s", info->id, tstrerror(code));
-    goto cleanup;
+    return code;
   }
 
   info->cost.lineNum = numLines;
@@ -2311,51 +2307,76 @@ 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));
-    goto cleanup;
+    return code;
   }
 
   info->cost.insertBindTime = taosGetTimestampUs();
   code = smlInsertData(info);
   if (code != 0) {
     uError("SML:0x%"PRIx64" smlInsertData error : %s", info->id, tstrerror(code));
-    goto cleanup;
+    return code;
   }
-  info->cost.endTime = taosGetTimestampUs();
 
-cleanup:
-  info->cost.code = code;
-  smlPrintStatisticInfo(info);
   return code;
 }
 
-static int32_t isSchemalessDb(SSmlHandle* info){
+static int32_t isSchemalessDb(STscObj *taos){
+  SCatalog* catalog = NULL;
+  int32_t code = catalogGetHandle(((STscObj *)taos)->pAppInfo->clusterId, &catalog);
+  if(code != TSDB_CODE_SUCCESS){
+    uError("SML get catalog error %d", code);
+    return code;
+  }
+
   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);
+  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;
+
+  uDebug("SML:0x%"PRIx64" result. code:%d, msg:%s", info->id, pRequest->code, pRequest->msgBuf);
+  // 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;
+  info->cost.endTime = taosGetTimestampUs();
+  info->cost.code = code;
+  smlPrintStatisticInfo(info);
+  smlDestroyInfo(info);
+
+  if(isLast){
+    tsem_post(&pParam->sem);
+  }
+}
+
 /**
  * taos_schemaless_insert() parse and insert data points into database according to
  * different protocol.
@@ -2384,48 +2405,88 @@ 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);
 
-  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)) != 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->affectedRows = perBatch;
+    info->pRequest->body.queryFp = smlInsertCallback;
+    info->pRequest->body.param   = info;
+    int32_t 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;
+  ((STscObj *)taos)->schemalessType = 1;
+  uDebug("resultend:%s", request->msgBuf);
   return (TAOS_RES*)request;
 }
 

source/client/src/tmq.c

@@ -408,7 +408,7 @@ int32_t tmqCommitInner(tmq_t* tmq, const tmq_topic_vgroup_list_t* offsets, int8_
   pParam->userParam = userParam;
   if (!async) tsem_init(&pParam->rspSem, 0, 0);
 
-  sendInfo = taosMemoryMalloc(sizeof(SMsgSendInfo));
+  sendInfo = taosMemoryCalloc(1, sizeof(SMsgSendInfo));
   if (sendInfo == NULL) goto END;
   sendInfo->msgInfo = (SDataBuf){
       .pData = buf,
@@ -704,7 +704,7 @@ tmq_resp_err_t tmq_subscribe(tmq_t* tmq, const tmq_list_t* topic_list) {
   void* abuf = buf;
   tSerializeSCMSubscribeReq(&abuf, &req);
 
-  SMsgSendInfo* sendInfo = taosMemoryMalloc(sizeof(SMsgSendInfo));
+  SMsgSendInfo* sendInfo = taosMemoryCalloc(1, sizeof(SMsgSendInfo));
   if (sendInfo == NULL) goto FAIL;
 
   SMqSubscribeCbParam param = {
@@ -1008,7 +1008,7 @@ int32_t tmqAskEp(tmq_t* tmq, bool async) {
   pParam->async = async;
   tsem_init(&pParam->rspSem, 0, 0);
 
-  SMsgSendInfo* sendInfo = taosMemoryMalloc(sizeof(SMsgSendInfo));
+  SMsgSendInfo* sendInfo = taosMemoryCalloc(1, sizeof(SMsgSendInfo));
   if (sendInfo == NULL) {
     tsem_destroy(&pParam->rspSem);
     taosMemoryFree(pParam);
@@ -1162,7 +1162,7 @@ int32_t tmqPollImpl(tmq_t* tmq, int64_t timeout) {
       pParam->vgId = pVg->vgId;
       pParam->epoch = tmq->epoch;
 
-      SMsgSendInfo* sendInfo = taosMemoryMalloc(sizeof(SMsgSendInfo));
+      SMsgSendInfo* sendInfo = taosMemoryCalloc(1, sizeof(SMsgSendInfo));
       if (sendInfo == NULL) {
         taosMemoryFree(pReq);
         taosMemoryFree(pParam);

source/client/test/CMakeLists.txt

@@ -41,7 +41,7 @@ TARGET_INCLUDE_DIRECTORIES(
         PRIVATE "${TD_SOURCE_DIR}/source/client/inc"
 )
 
-#add_test(
-#        NAME smlTest
-#        COMMAND smlTest
-#)
+add_test(
+        NAME smlTest
+        COMMAND smlTest
+)

source/client/test/clientTests.cpp

@@ -778,9 +778,9 @@ TEST(testCase, async_api_test) {
   TAOS* pConn = taos_connect("localhost", "root", "taosdata", NULL, 0);
   ASSERT_NE(pConn, nullptr);
 
-  taos_query(pConn, "use test");
+  taos_query(pConn, "use nest");
 
-  TAOS_RES* pRes = taos_query(pConn, "desc abc1.tu");
+  TAOS_RES* pRes = taos_query(pConn, "select NOW() from (select * from regular_table_2 where tbname in ('regular_table_2_1') and  q_bigint <= 9223372036854775807 and  q_tinyint <= 127 and    q_bool in ( true , false) ) order by ts;");
   if (taos_errno(pRes) != 0) {
     printf("failed, reason:%s\n", taos_errstr(pRes));
   }

source/common/src/systable.c

@@ -91,7 +91,7 @@ static const SSysDbTableSchema userDBSchema[] = {
     {.name = "precision", .bytes = 2 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
     {.name = "single_stable_model", .bytes = 1, .type = TSDB_DATA_TYPE_BOOL},
     {.name = "status", .bytes = 10 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
-    {.name = "schemaless", .bytes = 1, .type = TSDB_DATA_TYPE_BOOL},
+//    {.name = "schemaless", .bytes = 1, .type = TSDB_DATA_TYPE_BOOL},
     {.name = "retension", .bytes = 60 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
 
     // {.name = "update", .bytes = 1, .type = TSDB_DATA_TYPE_TINYINT},  // disable update
@@ -175,7 +175,7 @@ static const SSysDbTableSchema userUsersSchema[] = {
 };
 
 static const SSysDbTableSchema grantsSchema[] = {
-    {.name = "version", .bytes = 8 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
+    {.name = "version", .bytes = 9 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
     {.name = "expire time", .bytes = 19 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
     {.name = "expired", .bytes = 5 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
     {.name = "storage(GB)", .bytes = 21 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},

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;
   }
 
@@ -1239,6 +1239,9 @@ SSDataBlock* createOneDataBlock(const SSDataBlock* pDataBlock, bool copyData) {
         return NULL;
       }
 
+      if (pSrc->pData == NULL) {
+        continue;
+      }
       colDataAssign(pDst, pSrc, pDataBlock->info.rows);
     }
 
@@ -1631,25 +1634,31 @@ int32_t buildSubmitReqFromDataBlock(SSubmitReq** pReq, const SArray* pDataBlocks
             break;
           default:
             if (pColInfoData->info.type < TSDB_DATA_TYPE_MAX && pColInfoData->info.type > TSDB_DATA_TYPE_NULL) {
-              char tv[8] = {0};
-              if (pColInfoData->info.type == TSDB_DATA_TYPE_FLOAT) {
-                float v = 0;
-                GET_TYPED_DATA(v, float, pColInfoData->info.type, var);
-                SET_TYPED_DATA(&tv, pCol->type, v);
-              } else if (pColInfoData->info.type == TSDB_DATA_TYPE_DOUBLE) {
-                double v = 0;
-                GET_TYPED_DATA(v, double, pColInfoData->info.type, var);
-                SET_TYPED_DATA(&tv, pCol->type, v);
-              } else if (IS_SIGNED_NUMERIC_TYPE(pColInfoData->info.type)) {
-                int64_t v = 0;
-                GET_TYPED_DATA(v, int64_t, pColInfoData->info.type, var);
-                SET_TYPED_DATA(&tv, pCol->type, v);
+              if (pCol->type == pColInfoData->info.type) {
+                tdAppendColValToRow(&rb, PRIMARYKEY_TIMESTAMP_COL_ID + k, pCol->type, TD_VTYPE_NORM, var, true, offset,
+                                    k);
               } else {
-                uint64_t v = 0;
-                GET_TYPED_DATA(v, uint64_t, pColInfoData->info.type, var);
-                SET_TYPED_DATA(&tv, pCol->type, v);
+                char tv[8] = {0};
+                if (pColInfoData->info.type == TSDB_DATA_TYPE_FLOAT) {
+                  float v = 0;
+                  GET_TYPED_DATA(v, float, pColInfoData->info.type, var);
+                  SET_TYPED_DATA(&tv, pCol->type, v);
+                } else if (pColInfoData->info.type == TSDB_DATA_TYPE_DOUBLE) {
+                  double v = 0;
+                  GET_TYPED_DATA(v, double, pColInfoData->info.type, var);
+                  SET_TYPED_DATA(&tv, pCol->type, v);
+                } else if (IS_SIGNED_NUMERIC_TYPE(pColInfoData->info.type)) {
+                  int64_t v = 0;
+                  GET_TYPED_DATA(v, int64_t, pColInfoData->info.type, var);
+                  SET_TYPED_DATA(&tv, pCol->type, v);
+                } else {
+                  uint64_t v = 0;
+                  GET_TYPED_DATA(v, uint64_t, pColInfoData->info.type, var);
+                  SET_TYPED_DATA(&tv, pCol->type, v);
+                }
+                tdAppendColValToRow(&rb, PRIMARYKEY_TIMESTAMP_COL_ID + k, pCol->type, TD_VTYPE_NORM, tv, true, offset,
+                                    k);
               }
-              tdAppendColValToRow(&rb, PRIMARYKEY_TIMESTAMP_COL_ID + k, pCol->type, TD_VTYPE_NORM, tv, true, offset, k);
             } else {
               uError("the column type %" PRIi16 " is undefined\n", pColInfoData->info.type);
               TASSERT(0);

source/common/src/tglobal.c

@@ -86,6 +86,7 @@ bool tsSmlDataFormat =
 
 // query
 int32_t tsQueryPolicy = 1;
+int32_t tsQuerySmaOptimize = 1;
 
 /*
  * denote if the server needs to compress response message at the application layer to client, including query rsp,
@@ -113,7 +114,7 @@ int32_t tsCompatibleModel = 1;
 int32_t tsCountAlwaysReturnValue = 1;
 
 // 10 ms for sliding time, the value will changed in case of time precision changed
-int32_t   tsMinSlidingTime = 10;
+int32_t tsMinSlidingTime = 10;
 
 // the maxinum number of distict query result
 int32_t tsMaxNumOfDistinctResults = 1000 * 10000;
@@ -331,6 +332,7 @@ static int32_t taosAddClientCfg(SConfig *pCfg) {
   if (cfgAddInt32(pCfg, "compressColData", tsCompressColData, -1, 100000000, 1) != 0) return -1;
   if (cfgAddBool(pCfg, "keepColumnName", tsKeepOriginalColumnName, 1) != 0) return -1;
   if (cfgAddInt32(pCfg, "queryPolicy", tsQueryPolicy, 1, 3, 1) != 0) return -1;
+  if (cfgAddInt32(pCfg, "querySmaOptimize", tsQuerySmaOptimize, 0, 1, 1) != 0) return -1;
   if (cfgAddString(pCfg, "smlChildTableName", "", 1) != 0) return -1;
   if (cfgAddString(pCfg, "smlTagName", tsSmlTagName, 1) != 0) return -1;
   if (cfgAddBool(pCfg, "smlDataFormat", tsSmlDataFormat, 1) != 0) return -1;
@@ -541,6 +543,7 @@ static int32_t taosSetClientCfg(SConfig *pCfg) {
   tsKeepOriginalColumnName = cfgGetItem(pCfg, "keepColumnName")->bval;
   tsNumOfTaskQueueThreads = cfgGetItem(pCfg, "numOfTaskQueueThreads")->i32;
   tsQueryPolicy = cfgGetItem(pCfg, "queryPolicy")->i32;
+  tsQuerySmaOptimize = cfgGetItem(pCfg, "querySmaOptimize")->i32;
   return 0;
 }
 

source/common/src/tmsg.c

@@ -3877,9 +3877,10 @@ int32_t tEncodeTSma(SEncoder *pCoder, const STSma *pSma) {
   if (tEncodeCStr(pCoder, pSma->indexName) < 0) return -1;
   if (tEncodeI32(pCoder, pSma->exprLen) < 0) return -1;
   if (tEncodeI32(pCoder, pSma->tagsFilterLen) < 0) return -1;
-  if (tEncodeI32(pCoder, pSma->numOfVgroups) < 0) return -1;
   if (tEncodeI64(pCoder, pSma->indexUid) < 0) return -1;
   if (tEncodeI64(pCoder, pSma->tableUid) < 0) return -1;
+  if (tEncodeI64(pCoder, pSma->dstTbUid) < 0) return -1;
+  if (tEncodeCStr(pCoder, pSma->dstTbName) < 0) return -1;
   if (tEncodeI64(pCoder, pSma->interval) < 0) return -1;
   if (tEncodeI64(pCoder, pSma->offset) < 0) return -1;
   if (tEncodeI64(pCoder, pSma->sliding) < 0) return -1;
@@ -3889,17 +3890,10 @@ int32_t tEncodeTSma(SEncoder *pCoder, const STSma *pSma) {
   if (pSma->tagsFilterLen > 0) {
     if (tEncodeCStr(pCoder, pSma->tagsFilter) < 0) return -1;
   }
-  for (int32_t v = 0; v < pSma->numOfVgroups; ++v) {
-    if (tEncodeI32(pCoder, pSma->pVgEpSet[v].vgId) < 0) return -1;
-    if (tEncodeI8(pCoder, pSma->pVgEpSet[v].epSet.inUse) < 0) return -1;
-    int8_t numOfEps = pSma->pVgEpSet[v].epSet.numOfEps;
-    if (tEncodeI8(pCoder, numOfEps) < 0) return -1;
-    for (int32_t n = 0; n < numOfEps; ++n) {
-      const SEp *pEp = &pSma->pVgEpSet[v].epSet.eps[n];
-      if (tEncodeCStr(pCoder, pEp->fqdn) < 0) return -1;
-      if (tEncodeU16(pCoder, pEp->port) < 0) return -1;
-    }
-  }
+
+  tEncodeSSchemaWrapper(pCoder, &pSma->schemaRow);
+  tEncodeSSchemaWrapper(pCoder, &pSma->schemaTag);
+
   return 0;
 }
 
@@ -3907,14 +3901,15 @@ int32_t tDecodeTSma(SDecoder *pCoder, STSma *pSma) {
   if (tDecodeI8(pCoder, &pSma->version) < 0) return -1;
   if (tDecodeI8(pCoder, &pSma->intervalUnit) < 0) return -1;
   if (tDecodeI8(pCoder, &pSma->slidingUnit) < 0) return -1;
-  if (tDecodeI32(pCoder, &pSma->dstVgId) < 0) return -1;
   if (tDecodeI8(pCoder, &pSma->timezoneInt) < 0) return -1;
+  if (tDecodeI32(pCoder, &pSma->dstVgId) < 0) return -1;
   if (tDecodeCStrTo(pCoder, pSma->indexName) < 0) return -1;
   if (tDecodeI32(pCoder, &pSma->exprLen) < 0) return -1;
   if (tDecodeI32(pCoder, &pSma->tagsFilterLen) < 0) return -1;
-  if (tDecodeI32(pCoder, &pSma->numOfVgroups) < 0) return -1;
   if (tDecodeI64(pCoder, &pSma->indexUid) < 0) return -1;
   if (tDecodeI64(pCoder, &pSma->tableUid) < 0) return -1;
+  if (tDecodeI64(pCoder, &pSma->dstTbUid) < 0) return -1;
+  if (tDecodeCStr(pCoder, &pSma->dstTbName) < 0) return -1;
   if (tDecodeI64(pCoder, &pSma->interval) < 0) return -1;
   if (tDecodeI64(pCoder, &pSma->offset) < 0) return -1;
   if (tDecodeI64(pCoder, &pSma->sliding) < 0) return -1;
@@ -3928,27 +3923,9 @@ int32_t tDecodeTSma(SDecoder *pCoder, STSma *pSma) {
   } else {
     pSma->tagsFilter = NULL;
   }
-  if (pSma->numOfVgroups > 0) {
-    pSma->pVgEpSet = (SVgEpSet *)tDecoderMalloc(pCoder, pSma->numOfVgroups * sizeof(SVgEpSet));
-    if (!pSma->pVgEpSet) {
-      terrno = TSDB_CODE_OUT_OF_MEMORY;
-      return -1;
-    }
-
-    memset(pSma->pVgEpSet, 0, pSma->numOfVgroups * sizeof(SVgEpSet));
-
-    for (int32_t v = 0; v < pSma->numOfVgroups; ++v) {
-      if (tDecodeI32(pCoder, &pSma->pVgEpSet[v].vgId) < 0) return -1;
-      if (tDecodeI8(pCoder, &pSma->pVgEpSet[v].epSet.inUse) < 0) return -1;
-      if (tDecodeI8(pCoder, &pSma->pVgEpSet[v].epSet.numOfEps) < 0) return -1;
-      int8_t numOfEps = pSma->pVgEpSet[v].epSet.numOfEps;
-      for (int32_t n = 0; n < numOfEps; ++n) {
-        SEp *pEp = &pSma->pVgEpSet[v].epSet.eps[n];
-        if (tDecodeCStrTo(pCoder, pEp->fqdn) < 0) return -1;
-        if (tDecodeU16(pCoder, &pEp->port) < 0) return -1;
-      }
-    }
-  }
+  // only needed in dstVgroup
+  tDecodeSSchemaWrapperEx(pCoder, &pSma->schemaRow);
+  tDecodeSSchemaWrapperEx(pCoder, &pSma->schemaTag);
 
   return 0;
 }
@@ -3991,55 +3968,6 @@ int32_t tDecodeSVDropTSmaReq(SDecoder *pCoder, SVDropTSmaReq *pReq) {
   return 0;
 }
 
-int32_t tEncodeSVGetTSmaExpWndsReq(SEncoder *pCoder, const SVGetTsmaExpWndsReq *pReq) {
-  if (tStartEncode(pCoder) < 0) return -1;
-
-  if (tEncodeI64(pCoder, pReq->indexUid) < 0) return -1;
-  if (tEncodeI64(pCoder, pReq->queryWindow.skey) < 0) return -1;
-  if (tEncodeI64(pCoder, pReq->queryWindow.ekey) < 0) return -1;
-
-  tEndEncode(pCoder);
-  return 0;
-}
-
-int32_t tDecodeSVGetTsmaExpWndsReq(SDecoder *pCoder, SVGetTsmaExpWndsReq *pReq) {
-  if (tStartDecode(pCoder) < 0) return -1;
-
-  if (tDecodeI64(pCoder, &pReq->indexUid) < 0) return -1;
-  if (tDecodeI64(pCoder, &pReq->queryWindow.skey) < 0) return -1;
-  if (tDecodeI64(pCoder, &pReq->queryWindow.ekey) < 0) return -1;
-
-  tEndDecode(pCoder);
-  return 0;
-}
-
-int32_t tEncodeSVGetTSmaExpWndsRsp(SEncoder *pCoder, const SVGetTsmaExpWndsRsp *pReq) {
-  if (tStartEncode(pCoder) < 0) return -1;
-
-  if (tEncodeI64(pCoder, pReq->indexUid) < 0) return -1;
-  if (tEncodeI8(pCoder, pReq->flags) < 0) return -1;
-  if (tEncodeI32(pCoder, pReq->numExpWnds) < 0) return -1;
-  for (int32_t i = 0; i < pReq->numExpWnds; ++i) {
-    if (tEncodeI64(pCoder, pReq->wndSKeys[i]) < 0) return -1;
-  }
-  tEndEncode(pCoder);
-  return 0;
-}
-
-int32_t tDecodeSVGetTsmaExpWndsRsp(SDecoder *pCoder, SVGetTsmaExpWndsRsp *pReq) {
-  if (tStartDecode(pCoder) < 0) return -1;
-
-  if (tDecodeI64(pCoder, &pReq->indexUid) < 0) return -1;
-  if (tDecodeI8(pCoder, &pReq->flags) < 0) return -1;
-  if (tDecodeI32(pCoder, &pReq->numExpWnds) < 0) return -1;
-  for (int32_t i = 0; i < pReq->numExpWnds; ++i) {
-    if (tDecodeI64(pCoder, &pReq->wndSKeys[i]) < 0) return -1;
-  }
-
-  tEndDecode(pCoder);
-  return 0;
-}
-
 int32_t tSerializeSVDeleteReq(void *buf, int32_t bufLen, SVDeleteReq *pReq) {
   int32_t headLen = sizeof(SMsgHead);
   if (buf != NULL) {

source/common/src/ttime.c

@@ -76,22 +76,22 @@ void           deltaToUtcInitOnce() {
 
 static int64_t parseFraction(char* str, char** end, int32_t timePrec);
 static int32_t parseTimeWithTz(const char* timestr, int64_t* time, int32_t timePrec, char delim);
-static int32_t parseLocaltime(char* timestr, int64_t* time, int32_t timePrec);
-static int32_t parseLocaltimeDst(char* timestr, int64_t* time, int32_t timePrec);
+static int32_t parseLocaltime(char* timestr, int32_t len, int64_t* utime, int32_t timePrec);
+static int32_t parseLocaltimeDst(char* timestr, int32_t len, int64_t* utime, int32_t timePrec);
 static char*   forwardToTimeStringEnd(char* str);
 static bool    checkTzPresent(const char* str, int32_t len);
 
-static int32_t (*parseLocaltimeFp[])(char* timestr, int64_t* time, int32_t timePrec) = {parseLocaltime,
+static int32_t (*parseLocaltimeFp[])(char* timestr, int32_t len, int64_t* utime, int32_t timePrec) = {parseLocaltime,
                                                                                         parseLocaltimeDst};
 
-int32_t taosParseTime(const char* timestr, int64_t* time, int32_t len, int32_t timePrec, int8_t day_light) {
+int32_t taosParseTime(const char* timestr, int64_t* utime, int32_t len, int32_t timePrec, int8_t day_light) {
   /* parse datatime string in with tz */
   if (strnchr(timestr, 'T', len, false) != NULL) {
-    return parseTimeWithTz(timestr, time, timePrec, 'T');
+    return parseTimeWithTz(timestr, utime, timePrec, 'T');
   } else if (checkTzPresent(timestr, len)) {
-    return parseTimeWithTz(timestr, time, timePrec, 0);
+    return parseTimeWithTz(timestr, utime, timePrec, 0);
   } else {
-    return (*parseLocaltimeFp[day_light])((char*)timestr, time, timePrec);
+    return (*parseLocaltimeFp[day_light])((char*)timestr, len, utime, timePrec);
   }
 }
 
@@ -309,12 +309,36 @@ int32_t parseTimeWithTz(const char* timestr, int64_t* time, int32_t timePrec, ch
   return 0;
 }
 
-int32_t parseLocaltime(char* timestr, int64_t* time, int32_t timePrec) {
+static FORCE_INLINE bool validateTm(struct tm* pTm) {
+  if (pTm == NULL) {
+    return false;
+  }
+
+  int32_t dayOfMonth[12] = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
+
+  int32_t leapYearMonthDay = 29;
+  int32_t year = pTm->tm_year + 1900;
+  bool isLeapYear = ((year % 100) == 0)? ((year % 400) == 0):((year % 4) == 0);
+
+  if (isLeapYear && (pTm->tm_mon == 1)) {
+    if (pTm->tm_mday > leapYearMonthDay) {
+      return false;
+    }
+  } else {
+    if (pTm->tm_mday > dayOfMonth[pTm->tm_mon]) {
+      return false;
+    }
+  }
+
+  return  true;
+}
+
+int32_t parseLocaltime(char* timestr, int32_t len, int64_t* time, int32_t timePrec) {
   *time = 0;
   struct tm tm = {0};
 
   char* str = taosStrpTime(timestr, "%Y-%m-%d %H:%M:%S", &tm);
-  if (str == NULL) {
+  if (str == NULL || (((str - timestr) < len) && (*str != '.')) || !validateTm(&tm)) {
     return -1;
   }
 
@@ -343,13 +367,13 @@ int32_t parseLocaltime(char* timestr, int64_t* time, int32_t timePrec) {
   return 0;
 }
 
-int32_t parseLocaltimeDst(char* timestr, int64_t* time, int32_t timePrec) {
+int32_t parseLocaltimeDst(char* timestr, int32_t len, int64_t* time, int32_t timePrec) {
   *time = 0;
   struct tm tm = {0};
   tm.tm_isdst = -1;
 
   char* str = taosStrpTime(timestr, "%Y-%m-%d %H:%M:%S", &tm);
-  if (str == NULL) {
+  if (str == NULL || (((str - timestr) < len) && (*str != '.')) || !validateTm(&tm)) {
     return -1;
   }
 

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/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

@@ -298,31 +298,32 @@ typedef struct {
 } SVgObj;
 
 typedef struct {
-  char      name[TSDB_TABLE_FNAME_LEN];
-  char      stb[TSDB_TABLE_FNAME_LEN];
-  char      db[TSDB_DB_FNAME_LEN];
-  int64_t   createdTime;
-  int64_t   uid;
-  int64_t   stbUid;
-  int64_t   dbUid;
-  int8_t    intervalUnit;
-  int8_t    slidingUnit;
-  int8_t    timezone;
-  int32_t   dstVgId;  // for stream
-  int64_t   dstTbUid;
-  int64_t   interval;
-  int64_t   offset;
-  int64_t   sliding;
-  int32_t   exprLen;  // strlen + 1
-  int32_t   tagsFilterLen;
-  int32_t   sqlLen;
-  int32_t   astLen;
-  int32_t   numOfVgroups;
-  char*     expr;
-  char*     tagsFilter;
-  char*     sql;
-  char*     ast;
-  SVgEpSet* pVgEpSet;
+  char           name[TSDB_TABLE_FNAME_LEN];
+  char           stb[TSDB_TABLE_FNAME_LEN];
+  char           db[TSDB_DB_FNAME_LEN];
+  char           dstTbName[TSDB_TABLE_FNAME_LEN];
+  int64_t        createdTime;
+  int64_t        uid;
+  int64_t        stbUid;
+  int64_t        dbUid;
+  int64_t        dstTbUid;
+  int8_t         intervalUnit;
+  int8_t         slidingUnit;
+  int8_t         timezone;
+  int32_t        dstVgId;  // for stream
+  int64_t        interval;
+  int64_t        offset;
+  int64_t        sliding;
+  int32_t        exprLen;  // strlen + 1
+  int32_t        tagsFilterLen;
+  int32_t        sqlLen;
+  int32_t        astLen;
+  char*          expr;
+  char*          tagsFilter;
+  char*          sql;
+  char*          ast;
+  SSchemaWrapper schemaRow;  // for dstVgroup
+  SSchemaWrapper schemaTag;  // for dstVgroup
 } SSmaObj;
 
 typedef struct {

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

@@ -20,6 +20,8 @@
 "C" {
 #endif
 
+#include "mndInt.h"
+
 typedef enum {
   TSDB_GRANT_ALL,
   TSDB_GRANT_TIME,

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/mndTrans.h

@@ -75,6 +75,7 @@ int32_t mndTransPrepare(SMnode *pMnode, STrans *pTrans);
 int32_t mndTransProcessRsp(SRpcMsg *pRsp);
 void    mndTransPullup(SMnode *pMnode);
 int32_t mndKillTrans(SMnode *pMnode, STrans *pTrans);
+void    mndTransExecute(SMnode *pMnode, STrans *pTrans);
 
 #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

@@ -447,6 +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;
@@ -463,7 +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;

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

@@ -1424,10 +1424,10 @@ static void dumpDbInfoData(SSDataBlock *pBlock, SDbObj *pDb, SShowObj *pShow, in
     char    tmp[128] = {0};
     int32_t len = 0;
     if (pDb->cfg.daysToKeep0 > pDb->cfg.daysToKeep1 || pDb->cfg.daysToKeep0 > pDb->cfg.daysToKeep2) {
-      len = sprintf(&tmp[VARSTR_HEADER_SIZE], "%d,%d,%d", pDb->cfg.daysToKeep1, pDb->cfg.daysToKeep2,
+      len = sprintf(&tmp[VARSTR_HEADER_SIZE], "%dm,%dm,%dm", pDb->cfg.daysToKeep1, pDb->cfg.daysToKeep2,
                     pDb->cfg.daysToKeep0);
     } else {
-      len = sprintf(&tmp[VARSTR_HEADER_SIZE], "%d,%d,%d", pDb->cfg.daysToKeep0, pDb->cfg.daysToKeep1,
+      len = sprintf(&tmp[VARSTR_HEADER_SIZE], "%dm,%dm,%dm", pDb->cfg.daysToKeep0, pDb->cfg.daysToKeep1,
                     pDb->cfg.daysToKeep2);
     }
 
@@ -1503,8 +1503,8 @@ static void dumpDbInfoData(SSDataBlock *pBlock, SDbObj *pDb, SShowObj *pShow, in
     pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
     colDataAppend(pColInfo, rows, (const char *)statusB, false);
 
-    pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
-    colDataAppend(pColInfo, rows, (const char *)&pDb->cfg.schemaless, false);
+//    pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
+//    colDataAppend(pColInfo, rows, (const char *)&pDb->cfg.schemaless, false);
 
     char *p = buildRetension(pDb->cfg.pRetensions);
 
@@ -1592,4 +1592,3 @@ static void mndCancelGetNextDb(SMnode *pMnode, void *pIter) {
   SSdb *pSdb = pMnode->pSdb;
   sdbCancelFetch(pSdb, pIter);
 }
-

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/mndGrant.c

@@ -14,19 +14,115 @@
  */
 
 #define _DEFAULT_SOURCE
-#include "os.h"
-#include "taoserror.h"
 #include "mndGrant.h"
-#include "mndInt.h"
 #include "mndShow.h"
 
 #ifndef _GRANT
-static int32_t mndRetrieveGrant(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock* pBlock, int32_t rows) { return TSDB_CODE_OPS_NOT_SUPPORT; }
+
+static int32_t mndRetrieveGrant(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *pBlock, int32_t rows) {
+  int32_t numOfRows = 0;
+  char   *pWrite;
+  int32_t cols = 0;
+  char    tmp[32];
+  char    tmp1[32];
+
+  if (pShow->numOfRows < 1) {
+    cols = 0;
+    SColumnInfoData *pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    const char      *src = "community";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "false";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    cols++;
+    pColInfo = taosArrayGet(pBlock->pDataBlock, cols);
+    src = "unlimited";
+    STR_WITH_SIZE_TO_VARSTR(tmp, src, strlen(src));
+    colDataAppend(pColInfo, numOfRows, tmp, false);
+
+    numOfRows++;
+  }
+
+  pShow->numOfRows += numOfRows;
+  return numOfRows;
+}
 
 int32_t mndInitGrant(SMnode *pMnode) {
-    mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_GRANTS, mndRetrieveGrant);
-    return TSDB_CODE_SUCCESS; 
+  mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_GRANTS, mndRetrieveGrant);
+  return 0;
 }
+
 void    mndCleanupGrant() {}
 void    grantParseParameter() { mError("can't parsed parameter k"); }
 int32_t grantCheck(EGrantType grant) { return TSDB_CODE_SUCCESS; }

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

@@ -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/mndMnode.c

@@ -397,17 +397,17 @@ static int32_t mndProcessCreateMnodeReq(SRpcMsg *pReq) {
     goto _OVER;
   }
 
-  if (sdbGetSize(pMnode->pSdb, SDB_MNODE) >= 3) {
-    terrno = TSDB_CODE_MND_TOO_MANY_MNODES;
-    goto _OVER;
-  }
-
   pDnode = mndAcquireDnode(pMnode, createReq.dnodeId);
   if (pDnode == NULL) {
     terrno = TSDB_CODE_MND_DNODE_NOT_EXIST;
     goto _OVER;
   }
 
+  if (sdbGetSize(pMnode->pSdb, SDB_MNODE) >= 3) {
+    terrno = TSDB_CODE_MND_TOO_MANY_MNODES;
+    goto _OVER;
+  }
+
   if (!mndIsDnodeOnline(pDnode, taosGetTimestampMs())) {
     terrno = TSDB_CODE_NODE_OFFLINE;
     goto _OVER;
@@ -597,6 +597,11 @@ static int32_t mndProcessDropMnodeReq(SRpcMsg *pReq) {
     goto _OVER;
   }
 
+  if (!mndIsDnodeOnline(pObj->pDnode, taosGetTimestampMs())) {
+    terrno = TSDB_CODE_NODE_OFFLINE;
+    goto _OVER;
+  }
+
   pUser = mndAcquireUser(pMnode, pReq->conn.user);
   if (pUser == NULL) {
     terrno = TSDB_CODE_MND_NO_USER_FROM_CONN;

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 +127,64 @@ 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) {
+      ASSERT(0);
+      return -1;
+    }
+    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;
+          ASSERT(pVgInfo->taskId != 0);
+          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 +197,7 @@ 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 +241,7 @@ 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 +293,7 @@ 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);
@@ -292,185 +351,109 @@ int32_t mndScheduleStream(SMnode* pMnode, STrans* pTrans, SStreamObj* pStream) {
   ASSERT(totLevel <= 2);
   pStream->tasks = taosArrayInit(totLevel, sizeof(void*));
 
-  bool hasExtraSink = false;
-  bool externalTargetDB = strcmp(pStream->sourceDb, pStream->targetDb) != 0;
-  if (totLevel == 2 || externalTargetDB) {
+  bool    hasExtraSink = false;
+  bool    externalTargetDB = strcmp(pStream->sourceDb, pStream->targetDb) != 0;
+  SDbObj* pDbObj = mndAcquireDb(pMnode, pStream->targetDb);
+  ASSERT(pDbObj != NULL);
+  sdbRelease(pSdb, pDbObj);
+
+  bool multiTarget = pDbObj->cfg.numOfVgroups > 1;
+
+  if (totLevel == 2 || externalTargetDB || multiTarget) {
     SArray* taskOneLevel = taosArrayInit(0, sizeof(void*));
     taosArrayPush(pStream->tasks, &taskOneLevel);
     // 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
+      if (mndAddDispatcherToInnerTask(pMnode, pTrans, pStream, pFinalTask) < 0) {
+        qDestroyQueryPlan(pPlan);
+        return -1;
+      }
 
-        // 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 +464,28 @@ 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;
-
-      // sink part
-      pTask->sinkType = TASK_SINK__NONE;
+      // input
+      pTask->inputType = TASK_INPUT_TYPE__SUMBIT_BLOCK;
 
-      // 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/mndSma.c

@@ -26,6 +26,7 @@
 #include "mndTrans.h"
 #include "mndUser.h"
 #include "mndVgroup.h"
+#include "parser.h"
 #include "tname.h"
 
 #define TSDB_SMA_VER_NUMBER   1
@@ -82,10 +83,12 @@ static SSdbRaw *mndSmaActionEncode(SSmaObj *pSma) {
   SDB_SET_BINARY(pRaw, dataPos, pSma->name, TSDB_TABLE_FNAME_LEN, _OVER)
   SDB_SET_BINARY(pRaw, dataPos, pSma->stb, TSDB_TABLE_FNAME_LEN, _OVER)
   SDB_SET_BINARY(pRaw, dataPos, pSma->db, TSDB_DB_FNAME_LEN, _OVER)
+  SDB_SET_BINARY(pRaw, dataPos, pSma->dstTbName, TSDB_DB_FNAME_LEN, _OVER)
   SDB_SET_INT64(pRaw, dataPos, pSma->createdTime, _OVER)
   SDB_SET_INT64(pRaw, dataPos, pSma->uid, _OVER)
   SDB_SET_INT64(pRaw, dataPos, pSma->stbUid, _OVER)
   SDB_SET_INT64(pRaw, dataPos, pSma->dbUid, _OVER)
+  SDB_SET_INT64(pRaw, dataPos, pSma->dstTbUid, _OVER)
   SDB_SET_INT8(pRaw, dataPos, pSma->intervalUnit, _OVER)
   SDB_SET_INT8(pRaw, dataPos, pSma->slidingUnit, _OVER)
   SDB_SET_INT8(pRaw, dataPos, pSma->timezone, _OVER)
@@ -147,10 +150,12 @@ static SSdbRow *mndSmaActionDecode(SSdbRaw *pRaw) {
   SDB_GET_BINARY(pRaw, dataPos, pSma->name, TSDB_TABLE_FNAME_LEN, _OVER)
   SDB_GET_BINARY(pRaw, dataPos, pSma->stb, TSDB_TABLE_FNAME_LEN, _OVER)
   SDB_GET_BINARY(pRaw, dataPos, pSma->db, TSDB_DB_FNAME_LEN, _OVER)
+  SDB_GET_BINARY(pRaw, dataPos, pSma->dstTbName, TSDB_DB_FNAME_LEN, _OVER)
   SDB_GET_INT64(pRaw, dataPos, &pSma->createdTime, _OVER)
   SDB_GET_INT64(pRaw, dataPos, &pSma->uid, _OVER)
   SDB_GET_INT64(pRaw, dataPos, &pSma->stbUid, _OVER)
   SDB_GET_INT64(pRaw, dataPos, &pSma->dbUid, _OVER)
+  SDB_GET_INT64(pRaw, dataPos, &pSma->dstTbUid, _OVER)
   SDB_GET_INT8(pRaw, dataPos, &pSma->intervalUnit, _OVER)
   SDB_GET_INT8(pRaw, dataPos, &pSma->slidingUnit, _OVER)
   SDB_GET_INT8(pRaw, dataPos, &pSma->timezone, _OVER)
@@ -260,14 +265,17 @@ static void *mndBuildVCreateSmaReq(SMnode *pMnode, SVgObj *pVgroup, SSmaObj *pSm
   req.tagsFilterLen = pSma->tagsFilterLen;
   req.indexUid = pSma->uid;
   req.tableUid = pSma->stbUid;
+  req.dstVgId = pSma->dstVgId;
+  req.dstTbUid = pSma->dstTbUid;
   req.interval = pSma->interval;
   req.offset = pSma->offset;
   req.sliding = pSma->sliding;
   req.expr = pSma->expr;
   req.tagsFilter = pSma->tagsFilter;
-  req.numOfVgroups = pSma->numOfVgroups;
-  req.pVgEpSet = pSma->pVgEpSet;
-  
+  req.schemaRow = pSma->schemaRow;
+  req.schemaTag = pSma->schemaTag;
+  req.dstTbName = pSma->dstTbName;
+
   // get length
   int32_t ret = 0;
   tEncodeSize(tEncodeSVCreateTSmaReq, &req, contLen, ret);
@@ -425,14 +433,30 @@ static int32_t mndSetCreateSmaVgroupRedoActions(SMnode *pMnode, STrans *pTrans,
   mndReleaseDnode(pMnode, pDnode);
 
   // todo add sma info here
-  SVgEpSet *pVgEpSet = NULL;
-  int32_t   numOfVgroups = 0;
-  if (mndSmaGetVgEpSet(pMnode, pDb, &pVgEpSet, &numOfVgroups) != 0) {
+  SNode *pAst = NULL;
+  if (nodesStringToNode(pSma->ast, &pAst) < 0) {
+    return -1;
+  }
+  if (qExtractResultSchema(pAst, &pSma->schemaRow.nCols, &pSma->schemaRow.pSchema) != 0) {
+    nodesDestroyNode(pAst);
     return -1;
   }
+  nodesDestroyNode(pAst);
+  pSma->schemaRow.version = 1;
+
+  // TODO: the schemaTag generated by qExtractResultXXX later.
+  pSma->schemaTag.nCols = 1;
+  pSma->schemaTag.version = 1;
+  pSma->schemaTag.pSchema = taosMemoryCalloc(1, sizeof(SSchema));
+  if (!pSma->schemaTag.pSchema) {
+    return -1;
+  }
+  pSma->schemaTag.pSchema[0].type = TSDB_DATA_TYPE_BIGINT;
+  pSma->schemaTag.pSchema[0].bytes = TYPE_BYTES[TSDB_DATA_TYPE_BIGINT];
+  pSma->schemaTag.pSchema[0].colId = pSma->schemaRow.nCols + PRIMARYKEY_TIMESTAMP_COL_ID;
+  pSma->schemaTag.pSchema[0].flags = 0;
+  snprintf(pSma->schemaTag.pSchema[0].name, TSDB_COL_NAME_LEN, "groupId");
 
-  pSma->pVgEpSet = pVgEpSet;
-  pSma->numOfVgroups = numOfVgroups;
 
   int32_t smaContLen = 0;
   void   *pSmaReq = mndBuildVCreateSmaReq(pMnode, pVgroup, pSma, &smaContLen);
@@ -464,12 +488,15 @@ static int32_t mndCreateSma(SMnode *pMnode, SRpcMsg *pReq, SMCreateSmaReq *pCrea
   memcpy(smaObj.db, pDb->name, TSDB_DB_FNAME_LEN);
   smaObj.createdTime = taosGetTimestampMs();
   smaObj.uid = mndGenerateUid(pCreate->name, TSDB_TABLE_FNAME_LEN);
+  char resultTbName[TSDB_TABLE_FNAME_LEN + 16] = {0};
+  snprintf(resultTbName, TSDB_TABLE_FNAME_LEN + 16, "td.tsma.rst.tb.%s", pCreate->name);
+  memcpy(smaObj.dstTbName, resultTbName, TSDB_TABLE_FNAME_LEN);
+  smaObj.dstTbUid = mndGenerateUid(smaObj.dstTbName, TSDB_TABLE_FNAME_LEN);
   smaObj.stbUid = pStb->uid;
   smaObj.dbUid = pStb->dbUid;
   smaObj.intervalUnit = pCreate->intervalUnit;
   smaObj.slidingUnit = pCreate->slidingUnit;
   smaObj.timezone = pCreate->timezone;
-  smaObj.dstVgId = pCreate->dstVgId;
   smaObj.interval = pCreate->interval;
   smaObj.offset = pCreate->offset;
   smaObj.sliding = pCreate->sliding;
@@ -1087,53 +1114,4 @@ static int32_t mndRetrieveSma(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *pBloc
 static void mndCancelGetNextSma(SMnode *pMnode, void *pIter) {
   SSdb *pSdb = pMnode->pSdb;
   sdbCancelFetch(pSdb, pIter);
-}
-
+}
\ No newline at end of file
-static int32_t mndSmaGetVgEpSet(SMnode *pMnode, SDbObj *pDb, SVgEpSet **ppVgEpSet, int32_t *numOfVgroups) {
-  SSdb     *pSdb = pMnode->pSdb;
-  SVgObj   *pVgroup = NULL;
-  void     *pIter = NULL;
-  SVgEpSet *pVgEpSet = NULL;
-  int32_t   nAllocVgs = 16;
-  int32_t   nVgs = 0;
-
-  pVgEpSet = taosMemoryCalloc(nAllocVgs, sizeof(SVgEpSet));
-  if (!pVgEpSet) {
-    terrno = TSDB_CODE_OUT_OF_MEMORY;
-    return -1;
-  }
-
-  while (1) {
-    pIter = sdbFetch(pSdb, SDB_VGROUP, pIter, (void **)&pVgroup);
-    if (pIter == NULL) break;
-    if (pVgroup->dbUid != pDb->uid) {
-      sdbRelease(pSdb, pVgroup);
-      continue;
-    }
-
-    if (nVgs >= nAllocVgs) {
-      void *p = taosMemoryRealloc(pVgEpSet, nAllocVgs * 2 * sizeof(SVgEpSet));
-      if (!p) {
-        taosMemoryFree(pVgEpSet);
-        sdbCancelFetch(pSdb, pIter);
-        sdbRelease(pSdb, pVgroup);
-        terrno = TSDB_CODE_OUT_OF_MEMORY;
-        return -1;
-      }
-      pVgEpSet = (SVgEpSet *)p;
-      nAllocVgs *= 2;
-    }
-
-    (pVgEpSet + nVgs)->vgId = pVgroup->vgId;
-    (pVgEpSet + nVgs)->epSet = mndGetVgroupEpset(pMnode, pVgroup);
-
-    ++nVgs;
-
-    sdbRelease(pSdb, pVgroup);
-  }
-
-  *ppVgEpSet = pVgEpSet;
-  *numOfVgroups = nVgs;
-
-  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/mndStream.c

@@ -252,8 +252,12 @@ int32_t mndAddStreamToTrans(SMnode *pMnode, SStreamObj *pStream, const char *ast
   }
 
   if (qExtractResultSchema(pAst, (int32_t *)&pStream->outputSchema.nCols, &pStream->outputSchema.pSchema) != 0) {
+    nodesDestroyNode(pAst);
     return -1;
   }
+  // free
+  nodesDestroyNode(pAst);
+
 
 #if 0
   printf("|");

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

@@ -61,6 +61,12 @@ void mndSyncCommitMsg(struct SSyncFSM *pFsm, const SRpcMsg *pMsg, SFsmCbMeta cbM
     }
     tsem_post(&pMgmt->syncSem);
   } else {
+    STrans *pTrans = mndAcquireTrans(pMnode, transId);
+    if (pTrans != NULL) {
+      mndTransExecute(pMnode, pTrans);
+      mndReleaseTrans(pMnode, pTrans);
+    }
+
     if (cbMeta.index - sdbGetApplyIndex(pMnode->pSdb) > 100) {
       SSnapshotMeta sMeta = {0};
       if (syncGetSnapshotMeta(pMnode->syncMgmt.sync, &sMeta) == 0) {
@@ -96,10 +102,18 @@ 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 +206,14 @@ 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/mndTrans.c

@@ -52,8 +52,8 @@ static bool    mndTransPerformCommitActionStage(SMnode *pMnode, STrans *pTrans);
 static bool    mndTransPerformCommitStage(SMnode *pMnode, STrans *pTrans);
 static bool    mndTransPerformRollbackStage(SMnode *pMnode, STrans *pTrans);
 static bool    mndTransPerfromFinishedStage(SMnode *pMnode, STrans *pTrans);
+static bool    mndCantExecuteTransAction(SMnode *pMnode) { return !pMnode->deploy && !mndIsMaster(pMnode); }
 
-static void    mndTransExecute(SMnode *pMnode, STrans *pTrans);
 static void    mndTransSendRpcRsp(SMnode *pMnode, STrans *pTrans);
 static int32_t mndProcessTransReq(SRpcMsg *pReq);
 static int32_t mndProcessKillTransReq(SRpcMsg *pReq);
@@ -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;
@@ -517,12 +517,12 @@ static int32_t mndTransActionUpdate(SSdb *pSdb, STrans *pOld, STrans *pNew) {
 
   if (pOld->stage == TRN_STAGE_COMMIT) {
     pOld->stage = TRN_STAGE_COMMIT_ACTION;
-    mTrace("trans:%d, stage from commit to commitAction", pNew->id);
+    mTrace("trans:%d, stage from commit to commitAction since perform update action", pNew->id);
   }
 
   if (pOld->stage == TRN_STAGE_ROLLBACK) {
     pOld->stage = TRN_STAGE_FINISHED;
-    mTrace("trans:%d, stage from rollback to finished", pNew->id);
+    mTrace("trans:%d, stage from rollback to finished since perform update action", pNew->id);
   }
   return 0;
 }
@@ -914,7 +914,7 @@ static int32_t mndTransWriteSingleLog(SMnode *pMnode, STrans *pTrans, STransActi
 
 static int32_t mndTransSendSingleMsg(SMnode *pMnode, STrans *pTrans, STransAction *pAction) {
   if (pAction->msgSent) return 0;
-  if (!pMnode->deploy && !mndIsMaster(pMnode)) return -1;
+  if (mndCantExecuteTransAction(pMnode)) return -1;
 
   int64_t signature = pTrans->id;
   signature = (signature << 32);
@@ -1114,9 +1114,9 @@ static int32_t mndTransExecuteRedoActionsSerial(SMnode *pMnode, STrans *pTrans)
       pTrans->lastEpset = pAction->epSet;
     }
 
-    if (code == 0) {
-      if (!pMnode->deploy && !mndIsMaster(pMnode)) break;
+    if (mndCantExecuteTransAction(pMnode)) break;
 
+    if (code == 0) {
       pTrans->code = 0;
       pTrans->redoActionPos++;
       mDebug("trans:%d, %s:%d is executed and need sync to other mnodes", pTrans->id, mndTransStr(pAction->stage),
@@ -1160,6 +1160,8 @@ static bool mndTransPerformRedoActionStage(SMnode *pMnode, STrans *pTrans) {
     code = mndTransExecuteRedoActions(pMnode, pTrans);
   }
 
+  if (mndCantExecuteTransAction(pMnode)) return false;
+
   if (code == 0) {
     pTrans->code = 0;
     pTrans->stage = TRN_STAGE_COMMIT;
@@ -1185,6 +1187,8 @@ static bool mndTransPerformRedoActionStage(SMnode *pMnode, STrans *pTrans) {
 }
 
 static bool mndTransPerformCommitStage(SMnode *pMnode, STrans *pTrans) {
+  if (mndCantExecuteTransAction(pMnode)) return false;
+
   bool    continueExec = true;
   int32_t code = mndTransCommit(pMnode, pTrans);
 
@@ -1233,6 +1237,8 @@ static bool mndTransPerformUndoActionStage(SMnode *pMnode, STrans *pTrans) {
   bool    continueExec = true;
   int32_t code = mndTransExecuteUndoActions(pMnode, pTrans);
 
+  if (mndCantExecuteTransAction(pMnode)) return false;
+
   if (code == 0) {
     pTrans->stage = TRN_STAGE_ROLLBACK;
     mDebug("trans:%d, stage from undoAction to rollback", pTrans->id);
@@ -1250,6 +1256,8 @@ static bool mndTransPerformUndoActionStage(SMnode *pMnode, STrans *pTrans) {
 }
 
 static bool mndTransPerformRollbackStage(SMnode *pMnode, STrans *pTrans) {
+  if (mndCantExecuteTransAction(pMnode)) return false;
+
   bool    continueExec = true;
   int32_t code = mndTransRollback(pMnode, pTrans);
 
@@ -1284,10 +1292,11 @@ static bool mndTransPerfromFinishedStage(SMnode *pMnode, STrans *pTrans) {
   return continueExec;
 }
 
-static void mndTransExecute(SMnode *pMnode, STrans *pTrans) {
+void mndTransExecute(SMnode *pMnode, STrans *pTrans) {
   bool continueExec = true;
 
   while (continueExec) {
+    mDebug("trans:%d, continue to execute, stage:%s", pTrans->id, mndTransStr(pTrans->stage));
     pTrans->lastExecTime = taosGetTimestampMs();
     switch (pTrans->stage) {
       case TRN_STAGE_PREPARE:

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

@@ -394,12 +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;
@@ -434,6 +446,7 @@ static int32_t mndGetAvailableDnode(SMnode *pMnode, SVgObj *pVgroup, SArray *pAr
     pDnode->numOfVnodes++;
   }
 
+  mndSortVnodeGid(pVgroup);
   return 0;
 }
 
@@ -1035,7 +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));
@@ -1044,7 +1057,7 @@ 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 (pNew1 != pOld1) {
+  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,
@@ -1055,7 +1068,8 @@ static int32_t mndRedistributeVgroup(SMnode *pMnode, SRpcMsg *pReq, SDbObj *pDb,
     if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew1->id) != 0) goto _OVER;
     if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld1->id) != 0) goto _OVER;
   }
-  if (pNew2 != pOld2) {
+
+  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,
@@ -1066,7 +1080,8 @@ static int32_t mndRedistributeVgroup(SMnode *pMnode, SRpcMsg *pReq, SDbObj *pDb,
     if (mndAddIncVgroupReplicaToTrans(pMnode, pTrans, pDb, &newVg, pNew2->id) != 0) goto _OVER;
     if (mndAddDecVgroupReplicaFromTrans(pMnode, pTrans, pDb, &newVg, pOld2->id) != 0) goto _OVER;
   }
-  if (pNew3 != pOld3) {
+
+  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,
@@ -1111,15 +1126,18 @@ static int32_t mndProcessRedistributeVgroupMsg(SRpcMsg *pReq) {
   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 redReq = {0};
-  if (tDeserializeSRedistributeVgroupReq(pReq->pCont, pReq->contLen, &redReq) != 0) {
+  SRedistributeVgroupReq req = {0};
+  if (tDeserializeSRedistributeVgroupReq(pReq->pCont, pReq->contLen, &req) != 0) {
     terrno = TSDB_CODE_INVALID_MSG;
     goto _OVER;
   }
 
-  mInfo("vgId:%d, start to redistribute to dnode %d:%d:%d", redReq.vgId, redReq.dnodeId1, redReq.dnodeId2,
-        redReq.dnodeId3);
+  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;
@@ -1128,65 +1146,147 @@ static int32_t mndProcessRedistributeVgroupMsg(SRpcMsg *pReq) {
 
   if (mndCheckNodeAuth(pUser) != 0) goto _OVER;
 
-  pVgroup = mndAcquireVgroup(pMnode, redReq.vgId);
+  pVgroup = mndAcquireVgroup(pMnode, req.vgId);
   if (pVgroup == NULL) goto _OVER;
 
   pDb = mndAcquireDb(pMnode, pVgroup->dbName);
   if (pDb == NULL) goto _OVER;
 
   if (pVgroup->replica == 1) {
-    if (redReq.dnodeId2 != -1 || redReq.dnodeId3 != -1) {
+    if (req.dnodeId1 <= 0 || req.dnodeId2 > 0 || req.dnodeId3 > 0) {
       terrno = TSDB_CODE_MND_INVALID_REPLICA;
       goto _OVER;
     }
-    pNew1 = mndAcquireDnode(pMnode, redReq.dnodeId1);
-    pOld1 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[0].dnodeId);
-    if (pNew1 == NULL || pOld1 == NULL) {
-      terrno = TSDB_CODE_MND_DNODE_NOT_EXIST;
+
+    if (req.dnodeId1 == pVgroup->vnodeGid[0].dnodeId) {
+      terrno = TSDB_CODE_MND_VGROUP_UN_CHANGED;
       goto _OVER;
     }
-    if (pNew1 == pOld1) {
-      terrno = TSDB_CODE_MND_VGROUP_UN_CHANGED;
+
+    pNew1 = mndAcquireDnode(pMnode, req.dnodeId1);
+    if (pNew1 == NULL) goto _OVER;
+    if (!mndIsDnodeOnline(pNew1, curMs)) {
+      terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
       goto _OVER;
     }
-    if (!mndIsDnodeOnline(pNew1, curMs) || !mndIsDnodeOnline(pOld1, curMs)) {
+
+    pOld1 = mndAcquireDnode(pMnode, pVgroup->vnodeGid[0].dnodeId);
+    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 (redReq.dnodeId2 == -1 || redReq.dnodeId3 == -1) {
+    if (req.dnodeId1 <= 0 || req.dnodeId2 <= 0 || req.dnodeId3 <= 0) {
       terrno = TSDB_CODE_MND_INVALID_REPLICA;
       goto _OVER;
     }
-    pNew1 = mndAcquireDnode(pMnode, redReq.dnodeId1);
-    pNew2 = mndAcquireDnode(pMnode, redReq.dnodeId2);
-    pNew3 = mndAcquireDnode(pMnode, redReq.dnodeId3);
-    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) {
-      terrno = TSDB_CODE_MND_DNODE_NOT_EXIST;
-      goto _OVER;
-    }
-    if (pNew1 == pNew2 || pNew1 == pNew3 || pNew2 == pNew3) {
+
+    if (req.dnodeId1 == req.dnodeId2 || req.dnodeId1 == req.dnodeId3 || req.dnodeId2 == req.dnodeId3) {
       terrno = TSDB_CODE_MND_INVALID_REPLICA;
       goto _OVER;
     }
-    bool changed = false;
-    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) {
-      terrno = TSDB_CODE_MND_VGROUP_UN_CHANGED;
-      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 (!mndIsDnodeOnline(pNew1, curMs) || !mndIsDnodeOnline(pOld1, curMs) || !mndIsDnodeOnline(pNew2, curMs) ||
-        !mndIsDnodeOnline(pOld2, curMs) || !mndIsDnodeOnline(pNew3, curMs) || !mndIsDnodeOnline(pOld3, curMs)) {
-      terrno = TSDB_CODE_MND_HAS_OFFLINE_DNODE;
+
+    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;
     }
+
     code = mndRedistributeVgroup(pMnode, pReq, pDb, pVgroup, pNew1, pOld1, pNew2, pOld2, pNew3, pOld3);
+
   } else {
     terrno = TSDB_CODE_MND_INVALID_REPLICA;
     goto _OVER;
@@ -1196,8 +1296,8 @@ static int32_t mndProcessRedistributeVgroupMsg(SRpcMsg *pReq) {
 
 _OVER:
   if (code != 0 && code != TSDB_CODE_ACTION_IN_PROGRESS) {
-    mError("vgId:%d, failed to redistribute to dnode %d %d %d since %s", redReq.vgId, redReq.dnodeId1, redReq.dnodeId2,
-           redReq.dnodeId3, 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);

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

@@ -240,7 +240,7 @@ static int32_t sdbReadFileImp(SSdb *pSdb) {
   if (pFile == NULL) {
     taosMemoryFree(pRaw);
     terrno = TAOS_SYSTEM_ERROR(errno);
-    mError("failed to read sdb file:%s since %s", file, terrstr());
+    mDebug("failed to read sdb file:%s since %s", file, terrstr());
     return 0;
   }
 
@@ -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/vnode/CMakeLists.txt

@@ -28,7 +28,6 @@ target_sources(
 
     # sma
     "src/sma/sma.c"
-    "src/sma/smaTDBImpl.c"
     "src/sma/smaEnv.c"
     "src/sma/smaOpen.c"
     "src/sma/smaRollup.c"

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

@@ -43,35 +43,17 @@ typedef struct SRSmaInfo    SRSmaInfo;
 struct SSmaEnv {
   TdThreadRwlock lock;
   int8_t         type;
-  TXN            txn;
-  void          *pPool;  // SPoolMem
-  SDiskID        did;
-  TDB           *dbEnv;  // TODO: If it's better to put it in smaIndex level?
-  char          *path;   // relative path
   SSmaStat      *pStat;
 };
 
 #define SMA_ENV_LOCK(env)       ((env)->lock)
 #define SMA_ENV_TYPE(env)       ((env)->type)
-#define SMA_ENV_DID(env)        ((env)->did)
-#define SMA_ENV_ENV(env)        ((env)->dbEnv)
-#define SMA_ENV_PATH(env)       ((env)->path)
 #define SMA_ENV_STAT(env)       ((env)->pStat)
 #define SMA_ENV_STAT_ITEMS(env) ((env)->pStat->smaStatItems)
 
 struct SSmaStatItem {
-  /**
-   * @brief The field 'state' is here to demonstrate if one smaIndex is ready to provide service.
-   *    - TSDB_SMA_STAT_OK: 1) The sma calculation of history data is finished; 2) Or recevied information from
-   * Streaming Module or TSDB local persistence.
-   *    - TSDB_SMA_STAT_EXPIRED: 1) If sma calculation of history TS data is not finished; 2) Or if the TSDB is open,
-   * without information about its previous state.
-   *    - TSDB_SMA_STAT_DROPPED: 1)sma dropped
-   * N.B. only applicable to tsma
-   */
-  int8_t    state;           // ETsdbSmaStat
-  SHashObj *expiredWindows;  // key: skey of time window, value: version
-  STSma    *pTSma;           // cache schema
+  int8_t state;  // ETsdbSmaStat
+  STSma *pTSma;  // cache schema
 };
 
 struct SSmaStat {
@@ -84,29 +66,6 @@ struct SSmaStat {
 #define SMA_STAT_ITEMS(s)     ((s)->smaStatItems)
 #define SMA_STAT_INFO_HASH(s) ((s)->rsmaInfoHash)
 
-struct SSmaKey {
-  TSKEY   skey;
-  int64_t groupId;
-};
-
-typedef struct SDBFile SDBFile;
-
-struct SDBFile {
-  int32_t fid;
-  TTB    *pDB;
-  char   *path;
-};
-
-int32_t tdSmaBeginCommit(SSmaEnv *pEnv);
-int32_t tdSmaEndCommit(SSmaEnv *pEnv);
-
-int32_t smaOpenDBEnv(TDB **ppEnv, const char *path);
-int32_t smaCloseDBEnv(TDB *pEnv);
-int32_t smaOpenDBF(TDB *pEnv, SDBFile *pDBF);
-int32_t smaCloseDBF(SDBFile *pDBF);
-int32_t smaSaveSmaToDB(SDBFile *pDBF, void *pKey, int32_t keyLen, void *pVal, int32_t valLen, TXN *txn);
-void   *smaGetSmaDataByKey(SDBFile *pDBF, const void *pKey, int32_t keyLen, int32_t *valLen);
-
 void  tdDestroySmaEnv(SSmaEnv *pSmaEnv);
 void *tdFreeSmaEnv(SSmaEnv *pSmaEnv);
 #if 0
@@ -114,13 +73,6 @@ int32_t tbGetTSmaStatus(SSma *pSma, STSma *param, void *result);
 int32_t tbRemoveTSmaData(SSma *pSma, STSma *param, STimeWindow *pWin);
 #endif
 
-static FORCE_INLINE int32_t tdEncodeTSmaKey(int64_t groupId, TSKEY tsKey, void **pData) {
-  int32_t len = 0;
-  len += taosEncodeFixedI64(pData, tsKey);
-  len += taosEncodeFixedI64(pData, groupId);
-  return len;
-}
-
 int32_t tdInitSma(SSma *pSma);
 int32_t tdDropTSma(SSma *pSma, char *pMsg);
 int32_t tdDropTSmaData(SSma *pSma, int64_t indexUid);
@@ -128,13 +80,11 @@ int32_t tdInsertRSmaData(SSma *pSma, char *msg);
 
 int32_t tdRefSmaStat(SSma *pSma, SSmaStat *pStat);
 int32_t tdUnRefSmaStat(SSma *pSma, SSmaStat *pStat);
-int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType);
+int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType, bool onlyCheck);
 
 int32_t tdLockSma(SSma *pSma);
 int32_t tdUnLockSma(SSma *pSma);
 
-int32_t tdProcessTSmaInsertImpl(SSma *pSma, int64_t indexUid, const char *msg);
-
 static FORCE_INLINE int16_t tdTSmaAdd(SSma *pSma, int16_t n) { return atomic_add_fetch_16(&SMA_TSMA_NUM(pSma), n); }
 static FORCE_INLINE int16_t tdTSmaSub(SSma *pSma, int16_t n) { return atomic_sub_fetch_16(&SMA_TSMA_NUM(pSma), n); }
 
@@ -219,11 +169,8 @@ static int32_t  tdInitSmaEnv(SSma *pSma, int8_t smaType, const char *path, SDisk
 void *tdFreeRSmaInfo(SRSmaInfo *pInfo);
 
 int32_t tdProcessTSmaCreateImpl(SSma *pSma, int64_t version, const char *pMsg);
-int32_t tdUpdateExpiredWindowImpl(SSma *pSma, const SSubmitReq *pMsg, int64_t version);
-// TODO: This is the basic params, and should wrap the params to a queryHandle.
-int32_t tdGetTSmaDataImpl(SSma *pSma, char *pData, int64_t indexUid, TSKEY querySKey, int32_t nMaxResult);
-
-int32_t tdGetTSmaDaysImpl(SVnodeCfg *pCfg, void *pCont, uint32_t contLen, int32_t *days);
+int32_t tdProcessTSmaInsertImpl(SSma *pSma, int64_t indexUid, const char *msg);
+int32_t tdProcessTSmaGetDaysImpl(SVnodeCfg *pCfg, void *pCont, uint32_t contLen, int32_t *days);
 
 #ifdef __cplusplus
 }

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

@@ -150,7 +150,6 @@ int32_t tqProcessTaskRecoverRsp(STQ* pTq, SRpcMsg* pMsg);
 int32_t smaOpen(SVnode* pVnode);
 int32_t smaClose(SSma* pSma);
 
-int32_t tdUpdateExpireWindow(SSma* pSma, const SSubmitReq* pMsg, int64_t version);
 int32_t tdProcessTSmaCreate(SSma* pSma, int64_t version, const char* msg);
 int32_t tdProcessTSmaInsert(SSma* pSma, int64_t indexUid, const char* msg);
 
@@ -227,7 +226,7 @@ struct SVnode {
   SQHandle*  pQuery;
 };
 
-#define TD_VID(PVNODE) (PVNODE)->config.vgId
+#define TD_VID(PVNODE) ((PVNODE)->config.vgId)
 
 #define VND_TSDB(vnd)       ((vnd)->pTsdb)
 #define VND_RSMA0(vnd)      ((vnd)->pTsdb)

source/dnode/vnode/src/meta/metaQuery.c

@@ -86,11 +86,15 @@ tb_uid_t metaGetTableEntryUidByName(SMeta *pMeta, const char *name) {
   int      nData = 0;
   tb_uid_t uid = 0;
 
+  metaRLock(pMeta);
+
   if (tdbTbGet(pMeta->pNameIdx, name, strlen(name) + 1, &pData, &nData) == 0) {
     uid = *(tb_uid_t *)pData;
     tdbFree(pData);
   }
 
+  metaULock(pMeta);
+
   return 0;
 }
 

source/dnode/vnode/src/meta/metaSma.c

@@ -34,13 +34,13 @@ int32_t metaCreateTSma(SMeta *pMeta, int64_t version, SSmaCfg *pCfg) {
   SMetaReader mr = {0};
 
   // validate req
+  // save smaIndex
   metaReaderInit(&mr, pMeta, 0);
   if (metaGetTableEntryByUid(&mr, pCfg->indexUid) == 0) {
-// TODO: just for pass case
 #if 1
-    terrno = TSDB_CODE_TDB_TSMA_ALREADY_EXIST;
+    terrno = TSDB_CODE_TSMA_ALREADY_EXIST;
     metaReaderClear(&mr);
-    return -1;
+    return -1;  // don't goto _err;
 #else
     metaReaderClear(&mr);
     return 0;

source/dnode/vnode/src/sma/sma.c

@@ -36,25 +36,9 @@ int32_t tdProcessTSmaCreate(SSma* pSma, int64_t version, const char* msg) {
   return code;
 }
 
-int32_t tdUpdateExpireWindow(SSma* pSma, const SSubmitReq* pMsg, int64_t version) {
-  int32_t code = TSDB_CODE_SUCCESS;
-  if ((code = tdUpdateExpiredWindowImpl(pSma, pMsg, version)) < 0) {
-    smaWarn("vgId:%d, update expired sma window failed since %s", SMA_VID(pSma), tstrerror(terrno));
-  }
-  return code;
-}
-
-int32_t tdGetTSmaData(SSma* pSma, char* pData, int64_t indexUid, TSKEY querySKey, int32_t nMaxResult) {
-  int32_t code = TSDB_CODE_SUCCESS;
-  if ((code = tdGetTSmaDataImpl(pSma, pData, indexUid, querySKey, nMaxResult)) < 0) {
-    smaWarn("vgId:%d, get tsma data failed since %s", SMA_VID(pSma), tstrerror(terrno));
-  }
-  return code;
-}
-
 int32_t smaGetTSmaDays(SVnodeCfg* pCfg, void* pCont, uint32_t contLen, int32_t* days) {
   int32_t code = TSDB_CODE_SUCCESS;
-  if ((code = tdGetTSmaDaysImpl(pCfg, pCont, contLen, days)) < 0) {
+  if ((code = tdProcessTSmaGetDaysImpl(pCfg, pCont, contLen, days)) < 0) {
     smaWarn("vgId:%d, get tsma days failed since %s", pCfg->vgId, tstrerror(terrno));
   }
   smaDebug("vgId:%d, get tsma days %d", pCfg->vgId, *days);

source/dnode/vnode/src/sma/smaEnv.c

@@ -151,31 +151,11 @@ static SSmaEnv *tdNewSmaEnv(const SSma *pSma, int8_t smaType, const char *path,
     return NULL;
   }
 
-  ASSERT(path && (strlen(path) > 0));
-  SMA_ENV_PATH(pEnv) = strdup(path);
-  if (!SMA_ENV_PATH(pEnv)) {
-    tdFreeSmaEnv(pEnv);
-    return NULL;
-  }
-
-  SMA_ENV_DID(pEnv) = did;
-
   if (tdInitSmaStat(&SMA_ENV_STAT(pEnv), smaType) != TSDB_CODE_SUCCESS) {
     tdFreeSmaEnv(pEnv);
     return NULL;
   }
 
-  char aname[TSDB_FILENAME_LEN] = {0};
-  tfsAbsoluteName(SMA_TFS(pSma), did, path, aname);
-  if (smaOpenDBEnv(&pEnv->dbEnv, aname) != TSDB_CODE_SUCCESS) {
-    tdFreeSmaEnv(pEnv);
-    return NULL;
-  }
-
-  if (!(pEnv->pPool = openPool())) {
-    tdFreeSmaEnv(pEnv);
-    return NULL;
-  }
 
   return pEnv;
 }
@@ -205,10 +185,7 @@ void tdDestroySmaEnv(SSmaEnv *pSmaEnv) {
   if (pSmaEnv) {
     tdDestroySmaState(pSmaEnv->pStat, SMA_ENV_TYPE(pSmaEnv));
     taosMemoryFreeClear(pSmaEnv->pStat);
-    taosMemoryFreeClear(pSmaEnv->path);
     taosThreadRwlockDestroy(&(pSmaEnv->lock));
-    smaCloseDBEnv(pSmaEnv->dbEnv);
-    closePool(pSmaEnv->pPool);
   }
 }
 
@@ -242,7 +219,7 @@ static int32_t tdInitSmaStat(SSmaStat **pSmaStat, int8_t smaType) {
   }
 
   /**
-   *  1. Lazy mode utilized when init SSmaStat to update expired window(or hungry mode when tdNew).
+   *  1. Lazy mode utilized when init SSmaStat to update expire window(or hungry mode when tdNew).
    *  2. Currently, there is mutex lock when init SSmaEnv, thus no need add lock on SSmaStat, and please add lock if
    * tdInitSmaStat invoked in other multithread environment later.
    */
@@ -280,7 +257,6 @@ void *tdFreeSmaStatItem(SSmaStatItem *pSmaStatItem) {
   if (pSmaStatItem) {
     tDestroyTSma(pSmaStatItem->pTSma);
     taosMemoryFreeClear(pSmaStatItem->pTSma);
-    taosHashCleanup(pSmaStatItem->expiredWindows);
     taosMemoryFreeClear(pSmaStatItem);
   }
   return NULL;
@@ -341,7 +317,7 @@ int32_t tdUnLockSma(SSma *pSma) {
   return 0;
 }
 
-int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType) {
+int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType, bool onlyCheck) {
   SSmaEnv *pEnv = NULL;
 
   // return if already init
@@ -399,63 +375,3 @@ int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType) {
 
   return TSDB_CODE_SUCCESS;
 };
-
-int32_t tdSmaBeginCommit(SSmaEnv *pEnv) {
-  TXN *pTxn = &pEnv->txn;
-  // start a new txn
-  tdbTxnOpen(pTxn, 0, poolMalloc, poolFree, pEnv->pPool, TDB_TXN_WRITE | TDB_TXN_READ_UNCOMMITTED);
-  if (tdbBegin(pEnv->dbEnv, pTxn) != 0) {
-    smaWarn("tdSma tdb begin commit fail");
-    return -1;
-  }
-  return 0;
-}
-
-int32_t tdSmaEndCommit(SSmaEnv *pEnv) {
-  TXN *pTxn = &pEnv->txn;
-
-  // Commit current txn
-  if (tdbCommit(pEnv->dbEnv, pTxn) != 0) {
-    smaWarn("tdSma tdb end commit fail");
-    return -1;
-  }
-  tdbTxnClose(pTxn);
-  clearPool(pEnv->pPool);
-  return 0;
-}
-
-#if 0
-/**
- * @brief Get the start TS key of the last data block of one interval/sliding.
- *
- * @param pSma
- * @param param
- * @param result
- * @return int32_t
- *         1) Return 0 and fill the result if the check procedure is normal;
- *         2) Return -1 if error occurs during the check procedure.
- */
-int32_t tdGetTSmaStatus(SSma *pSma, void *smaIndex, void *result) {
-  const char *procedure = "";
-  if (strncmp(procedure, "get the start TS key of the last data block", 100) != 0) {
-    return -1;
-  }
-  // fill the result
-  return TSDB_CODE_SUCCESS;
-}
-
-/**
- * @brief Remove the tSma data files related to param between pWin.
- *
- * @param pSma
- * @param param
- * @param pWin
- * @return int32_t
- */
-int32_t tdRemoveTSmaData(SSma *pSma, void *smaIndex, STimeWindow *pWin) {
-  // for ("tSmaFiles of param-interval-sliding between pWin") {
-  //   // remove the tSmaFile
-  // }
-  return TSDB_CODE_SUCCESS;
-}
-#endif

source/dnode/vnode/src/sma/smaRollup.c

@@ -65,7 +65,7 @@ static FORCE_INLINE int32_t tdUpdateTbUidListImpl(SSma *pSma, tb_uid_t *suid, SA
   pRSmaInfo = taosHashGet(SMA_STAT_INFO_HASH(pStat), suid, sizeof(tb_uid_t));
   if (!pRSmaInfo || !(pRSmaInfo = *(SRSmaInfo **)pRSmaInfo)) {
     smaError("vgId:%d, failed to get rsma info for uid:%" PRIi64, SMA_VID(pSma), *suid);
-    terrno = TSDB_CODE_TDB_INVALID_SMA_STAT;
+    terrno = TSDB_CODE_RSMA_INVALID_STAT;
     return TSDB_CODE_FAILED;
   }
 
@@ -132,7 +132,7 @@ int32_t tdFetchTbUidList(SSma *pSma, STbUidStore **ppStore, tb_uid_t suid, tb_ui
   SSmaStat *pStat = SMA_ENV_STAT(pEnv);
   SHashObj *infoHash = NULL;
   if (!pStat || !(infoHash = SMA_STAT_INFO_HASH(pStat))) {
-    terrno = TSDB_CODE_TDB_INVALID_SMA_STAT;
+    terrno = TSDB_CODE_RSMA_INVALID_STAT;
     return TSDB_CODE_FAILED;
   }
 
@@ -167,13 +167,13 @@ int32_t tdFetchTbUidList(SSma *pSma, STbUidStore **ppStore, tb_uid_t suid, tb_ui
  */
 int32_t tdProcessRSmaCreate(SVnode *pVnode, SVCreateStbReq *pReq) {
   SSma *pSma = pVnode->pSma;
-  SMeta *pMeta = pVnode->pMeta;
-  SMsgCb *pMsgCb = &pVnode->msgCb;
   if (!pReq->rollup) {
     smaTrace("vgId:%d, return directly since no rollup for stable %s %" PRIi64, SMA_VID(pSma), pReq->name, pReq->suid);
     return TSDB_CODE_SUCCESS;
   }
 
+  SMeta *pMeta = pVnode->pMeta;
+  SMsgCb *pMsgCb = &pVnode->msgCb;
   SRSmaParam *param = &pReq->pRSmaParam;
 
   if ((param->qmsg1Len == 0) && (param->qmsg2Len == 0)) {
@@ -181,7 +181,7 @@ int32_t tdProcessRSmaCreate(SVnode *pVnode, SVCreateStbReq *pReq) {
     return TSDB_CODE_SUCCESS;
   }
 
-  if (tdCheckAndInitSmaEnv(pSma, TSDB_SMA_TYPE_ROLLUP) != TSDB_CODE_SUCCESS) {
+  if (tdCheckAndInitSmaEnv(pSma, TSDB_SMA_TYPE_ROLLUP, false) != TSDB_CODE_SUCCESS) {
     terrno = TSDB_CODE_TDB_INIT_FAILED;
     return TSDB_CODE_FAILED;
   }

source/dnode/vnode/src/sma/smaTDBImpl.c

-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define ALLOW_FORBID_FUNC
-
-#include "sma.h"
-
-int32_t smaOpenDBEnv(TDB **ppEnv, const char *path) {
-  int ret = 0;
-
-  if (path == NULL) return -1;
-
-  ret = tdbOpen(path, 4096, 256, ppEnv);  // use as param
-
-  if (ret != 0) {
-    smaError("failed to create tsdb db env, ret = %d", ret);
-    return -1;
-  }
-
-  return 0;
-}
-
-int32_t smaCloseDBEnv(TDB *pEnv) { return tdbClose(pEnv); }
-
-static inline int tdSmaKeyCmpr(const void *arg1, int len1, const void *arg2, int len2) {
-  const SSmaKey *pKey1 = (const SSmaKey *)arg1;
-  const SSmaKey *pKey2 = (const SSmaKey *)arg2;
-
-  ASSERT(len1 == len2 && len1 == sizeof(SSmaKey));
-
-  if (pKey1->skey < pKey2->skey) {
-    return -1;
-  } else if (pKey1->skey > pKey2->skey) {
-    return 1;
-  }
-  if (pKey1->groupId < pKey2->groupId) {
-    return -1;
-  } else if (pKey1->groupId > pKey2->groupId) {
-    return 1;
-  }
-
-  return 0;
-}
-
-static int32_t smaOpenDBDb(TTB **ppDB, TDB *pEnv, const char *pFName) {
-  tdb_cmpr_fn_t compFunc;
-
-  // Create a database
-  compFunc = tdSmaKeyCmpr;
-  if (tdbTbOpen(pFName, -1, -1, compFunc, pEnv, ppDB) < 0) {
-    return -1;
-  }
-
-  return 0;
-}
-
-static int32_t smaCloseDBDb(TTB *pDB) { return tdbTbClose(pDB); }
-
-int32_t smaOpenDBF(TDB *pEnv, SDBFile *pDBF) {
-  // TEnv is shared by a group of SDBFile
-  if (!pEnv || !pDBF) {
-    terrno = TSDB_CODE_INVALID_PTR;
-    return -1;
-  }
-
-  // Open DBF
-  if (smaOpenDBDb(&(pDBF->pDB), pEnv, pDBF->path) < 0) {
-    smaError("failed to open DBF: %s", pDBF->path);
-    smaCloseDBDb(pDBF->pDB);
-    return -1;
-  }
-
-  return 0;
-}
-
-int32_t smaCloseDBF(SDBFile *pDBF) {
-  int32_t ret = 0;
-  if (pDBF->pDB) {
-    ret = smaCloseDBDb(pDBF->pDB);
-    pDBF->pDB = NULL;
-  }
-  taosMemoryFreeClear(pDBF->path);
-  return ret;
-}
-
-int32_t smaSaveSmaToDB(SDBFile *pDBF, void *pKey, int32_t keyLen, void *pVal, int32_t valLen, TXN *txn) {
-  int32_t ret;
-
-  printf("save tsma data into %s, keyLen:%d valLen:%d txn:%p\n", pDBF->path, keyLen, valLen, txn);
-  ret = tdbTbUpsert(pDBF->pDB, pKey, keyLen, pVal, valLen, txn);
-  if (ret < 0) {
-    smaError("failed to upsert tsma data into db, ret = %d", ret);
-    return -1;
-  }
-
-  return 0;
-}
-
-void *smaGetSmaDataByKey(SDBFile *pDBF, const void *pKey, int32_t keyLen, int32_t *valLen) {
-  void *pVal = NULL;
-  int   ret;
-
-  ret = tdbTbGet(pDBF->pDB, pKey, keyLen, &pVal, valLen);
-
-  if (ret < 0) {
-    smaError("failed to get tsma data from db, ret = %d", ret);
-    return NULL;
-  }
-
-  ASSERT(*valLen >= 0);
-
-  // TODO: lock?
-  // TODO: Would the key/value be destoryed during return the data?
-  // TODO: How about the key is updated while value length is changed? The original value buffer would be freed
-  // automatically?
-
-  return pVal;
-}
\ No newline at end of file

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

@@ -130,7 +130,18 @@ 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/tqPush.c

@@ -238,9 +238,6 @@ int tqPushMsg(STQ* pTq, void* msg, int32_t msgLen, tmsg_t msgType, int64_t ver)
   if (msgType == TDMT_VND_SUBMIT) {
     if (taosHashGetSize(pTq->pStreamTasks) == 0) return 0;
 
-    if (tdUpdateExpireWindow(pTq->pVnode->pSma, msg, ver) != 0) {
-      // TODO handle sma error
-    }
     void* data = taosMemoryMalloc(msgLen);
     if (data == NULL) {
       return -1;

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/tsdbCommit.c

@@ -150,7 +150,7 @@ int32_t tsdbCommit(STsdb *pTsdb) {
   return code;
 
 _err:
-  tsdbError("vgId:%d failed to commit since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
+  tsdbError("vgId:%d, failed to commit since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
   return code;
 }
 

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

@@ -176,13 +176,13 @@ int32_t tsdbDeleteTableData(STsdb *pTsdb, int64_t version, tb_uid_t suid, tb_uid
 
   pMemTable->nDelOp++;
 
-  tsdbError("vgId:%d delete data from table suid:%" PRId64 " uid:%" PRId64 " skey:%" PRId64 " eKey:%" PRId64
+  tsdbError("vgId:%d, delete data from table suid:%" PRId64 " uid:%" PRId64 " skey:%" PRId64 " eKey:%" PRId64
             " since %s",
             TD_VID(pTsdb->pVnode), suid, uid, sKey, eKey, tstrerror(code));
   return code;
 
 _err:
-  tsdbError("vgId:%d failed to delete data from table suid:%" PRId64 " uid:%" PRId64 " skey:%" PRId64 " eKey:%" PRId64
+  tsdbError("vgId:%d, failed to delete data from table suid:%" PRId64 " uid:%" PRId64 " skey:%" PRId64 " eKey:%" PRId64
             " since %s",
             TD_VID(pTsdb->pVnode), suid, uid, sKey, eKey, tstrerror(code));
   return code;

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

@@ -225,6 +225,7 @@ int32_t vnodeProcessFetchMsg(SVnode *pVnode, SRpcMsg *pMsg, SQueueInfo *pInfo) {
   vTrace("message in fetch queue is processing");
   char   *msgstr = POINTER_SHIFT(pMsg->pCont, sizeof(SMsgHead));
   int32_t msgLen = pMsg->contLen - sizeof(SMsgHead);
+
   switch (pMsg->msgType) {
     case TDMT_VND_FETCH:
       return qWorkerProcessFetchMsg(pVnode, pVnode->pQuery, pMsg, 0);
@@ -236,13 +237,10 @@ int32_t vnodeProcessFetchMsg(SVnode *pVnode, SRpcMsg *pMsg, SQueueInfo *pInfo) {
       return qWorkerProcessDropMsg(pVnode, pVnode->pQuery, pMsg, 0);
     case TDMT_VND_QUERY_HEARTBEAT:
       return qWorkerProcessHbMsg(pVnode, pVnode->pQuery, pMsg, 0);
-
     case TDMT_VND_TABLE_META:
       return vnodeGetTableMeta(pVnode, pMsg);
-
     case TDMT_VND_CONSUME:
       return tqProcessPollReq(pVnode->pTq, pMsg, pInfo->workerId);
-
     case TDMT_STREAM_TASK_RUN:
       return tqProcessTaskRunReq(pVnode->pTq, pMsg);
     case TDMT_STREAM_TASK_DISPATCH:
@@ -279,7 +277,7 @@ int32_t vnodeProcessWriteMsg(SVnode *pVnode, int64_t version, SRpcMsg *pMsg, SRp
 void smaHandleRes(void *pVnode, int64_t smaId, const SArray *data) {
   // TODO
 
-  // blockDebugShowData(data);
+  // blockDebugShowData(data, __func__);
   tdProcessTSmaInsert(((SVnode *)pVnode)->pSma, smaId, (const char *)data);
 }
 
@@ -305,6 +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);
 
@@ -791,7 +793,9 @@ static int32_t vnodeProcessSubmitReq(SVnode *pVnode, int64_t version, void *pReq
         msgIter.suid = 0;
       }
 
+#ifdef TD_DEBUG_PRINT_ROW
       vnodeDebugPrintSingleSubmitMsg(pVnode->pMeta, pBlock, &msgIter, "real uid");
+#endif
       tDecoderClear(&decoder);
     } else {
       submitBlkRsp.tblFName = taosMemoryMalloc(TSDB_TABLE_FNAME_LEN);
@@ -902,4 +906,4 @@ 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

@@ -180,10 +180,18 @@ 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
@@ -213,6 +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/dnode/vnode/test/tsdbSmaTest.cpp

@@ -373,7 +373,7 @@ TEST(testCase, tSma_Data_Insert_Query_Test) {
   pTsdb->pTfs = tfsOpen(&pDisks, numOfDisks);
   EXPECT_NE(pTsdb->pTfs, nullptr);
 
-  // generate SSubmitReq msg and update expired window
+  // generate SSubmitReq msg and update expire window
   int16_t  schemaVer = 0;
   uint32_t mockRowLen = sizeof(STSRow);
   uint32_t mockRowNum = 2;

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 {
@@ -760,7 +759,7 @@ int32_t getTableScanInfo(SOperatorInfo* pOperator, int32_t *order, int32_t* scan
 int32_t getBufferPgSize(int32_t rowSize, uint32_t* defaultPgsz, uint32_t* defaultBufsz);
 
 void    doSetOperatorCompleted(SOperatorInfo* pOperator);
-void    doFilter(const SNode* pFilterNode, SSDataBlock* pBlock, bool needFree);
+void    doFilter(const SNode* pFilterNode, SSDataBlock* pBlock);
 SqlFunctionCtx* createSqlFunctionCtx(SExprInfo* pExprInfo, int32_t numOfOutput, int32_t** rowCellInfoOffset);
 void    relocateColumnData(SSDataBlock* pBlock, const SArray* pColMatchInfo, SArray* pCols);
 void    initExecTimeWindowInfo(SColumnInfoData* pColData, STimeWindow* pQueryWindow);
@@ -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

@@ -1819,9 +1819,9 @@ 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) {
+void doFilter(const SNode* pFilterNode, SSDataBlock* pBlock) {
   if (pFilterNode == NULL) {
     return;
   }
@@ -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) {
@@ -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;
 
@@ -2845,7 +2878,6 @@ static SSDataBlock* doLoadRemoteData(SOperatorInfo* pOperator) {
     return seqLoadRemoteData(pOperator);
   } else {
     return concurrentlyLoadRemoteDataImpl(pOperator, pExchangeInfo, pTaskInfo);
-    //    return concurrentlyLoadRemoteData(pOperator);
   }
 }
 
@@ -2871,9 +2903,14 @@ static int32_t initDataSource(int32_t numOfSources, SExchangeInfo* pInfo) {
   return TSDB_CODE_SUCCESS;
 }
 
-static int32_t initExchangeOperator(SExchangePhysiNode* pExNode, SExchangeInfo* pInfo) {
+static int32_t initExchangeOperator(SExchangePhysiNode* pExNode, SExchangeInfo* pInfo, const char* id) {
   size_t numOfSources = LIST_LENGTH(pExNode->pSrcEndPoints);
 
+  if (numOfSources == 0) {
+    qError("%s invalid number: %d of sources in exchange operator", id, (int32_t) numOfSources);
+    return TSDB_CODE_INVALID_PARA;
+  }
+
   pInfo->pSources = taosArrayInit(numOfSources, sizeof(SDownstreamSourceNode));
   pInfo->pSourceDataInfo = taosArrayInit(numOfSources, sizeof(SSourceDataInfo));
   if (pInfo->pSourceDataInfo == NULL || pInfo->pSources == NULL) {
@@ -2895,7 +2932,7 @@ SOperatorInfo* createExchangeOperatorInfo(void* pTransporter, SExchangePhysiNode
     goto _error;
   }
 
-  int32_t code = initExchangeOperator(pExNode, pInfo);
+  int32_t code = initExchangeOperator(pExNode, pInfo, GET_TASKID(pTaskInfo));
   if (code != TSDB_CODE_SUCCESS) {
     goto _error;
   }
@@ -2924,7 +2961,7 @@ _error:
 
   taosMemoryFreeClear(pInfo);
   taosMemoryFreeClear(pOperator);
-  pTaskInfo->code = TSDB_CODE_OUT_OF_MEMORY;
+  pTaskInfo->code = code;
   return NULL;
 }
 
@@ -3693,7 +3730,7 @@ static SSDataBlock* doProjectOperation(SOperatorInfo* pOperator) {
       longjmp(pTaskInfo->env, code);
     }
 
-    doFilter(pProjectInfo->pFilterNode, pBlock, true);
+    doFilter(pProjectInfo->pFilterNode, pBlock);
 
     setInputDataBlock(pOperator, pInfo->pCtx, pBlock, order, scanFlag, false);
     blockDataEnsureCapacity(pInfo->pRes, pInfo->pRes->info.rows + pBlock->info.rows);
@@ -4671,24 +4708,28 @@ 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);
 
+  } 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) {
     qDebug("[******]create Semi");
     int32_t children = 0;
@@ -5208,7 +5249,7 @@ int32_t createExecTaskInfoImpl(SSubplan* pPlan, SExecTaskInfo** pTaskInfo, SRead
   (*pTaskInfo)->pRoot = createOperatorTree(pPlan->pNode, *pTaskInfo, pHandle, queryId, taskId,
                                            &(*pTaskInfo)->tableqinfoList, pPlan->pTagCond);
   if (NULL == (*pTaskInfo)->pRoot) {
-    code = terrno;
+    code = (*pTaskInfo)->code;
     goto _complete;
   }
 
@@ -5221,7 +5262,6 @@ int32_t createExecTaskInfoImpl(SSubplan* pPlan, SExecTaskInfo** pTaskInfo, SRead
 
 _complete:
   taosMemoryFreeClear(*pTaskInfo);
-
   terrno = code;
   return code;
 }
@@ -5380,16 +5420,3 @@ int32_t initStreamAggSupporter(SStreamAggSupporter* pSup, const char* pKey, SqlF
   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/groupoperator.c

@@ -359,7 +359,7 @@ static SSDataBlock* hashGroupbyAggregate(SOperatorInfo* pOperator) {
 
   while(1) {
     doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
-    doFilter(pInfo->pCondition, pRes, true);
+    doFilter(pInfo->pCondition, pRes);
 
     bool hasRemain = hashRemainDataInGroupInfo(&pInfo->groupResInfo);
     if (!hasRemain) {

source/libs/function/inc/functionMgtInt.h

@@ -41,6 +41,7 @@ extern "C" {
 #define FUNC_MGT_SCAN_PC_FUNC           FUNC_MGT_FUNC_CLASSIFICATION_MASK(12)
 #define FUNC_MGT_SELECT_FUNC            FUNC_MGT_FUNC_CLASSIFICATION_MASK(13)
 #define FUNC_MGT_REPEAT_SCAN_FUNC       FUNC_MGT_FUNC_CLASSIFICATION_MASK(14)
+#define FUNC_MGT_FORBID_FILL_FUNC       FUNC_MGT_FUNC_CLASSIFICATION_MASK(15)
 
 #define FUNC_MGT_TEST_MASK(val, mask) (((val) & (mask)) != 0)
 

source/libs/function/src/functionMgt.c

@@ -159,6 +159,8 @@ bool fmIsRepeatScanFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId,
 
 bool fmIsUserDefinedFunc(int32_t funcId) { return funcId > FUNC_UDF_ID_START; }
 
+bool fmIsForbidFillFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MGT_FORBID_FILL_FUNC); }
+
 void fmFuncMgtDestroy() {
   void* m = gFunMgtService.pFuncNameHashTable;
   if (m != NULL && atomic_val_compare_exchange_ptr((void**)&gFunMgtService.pFuncNameHashTable, m, 0) == m) {