Merge branch '3.0' of github.com:taosdata/TDengine into test/chr/TD-14699

cmake/cmake.options

@@ -51,6 +51,13 @@ IF(${TD_WINDOWS})
         "If build unit tests using googletest" 
         ON
     )
+    
+    option(
+        TDENGINE_3
+        "TDengine 3.x"
+        ON
+        )
+
 ELSEIF (TD_DARWIN_64)
     add_definitions(-DCOMPILER_SUPPORTS_CXX13)
     option(

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

@@ -91,7 +91,7 @@ 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:
 
 ```
-git clone https://github.com/taosdata/taos-connector-jdbc.git
+git clone https://github.com/taosdata/taos-connector-jdbc.git --branch 2.0
 cd taos-connector-jdbc
 mvn clean install -Dmaven.test.skip=true
 ```
@@ -140,34 +140,34 @@ 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.
 

docs/zh/02-intro.md

@@ -52,7 +52,7 @@ TDengine的主要功能如下：
 采用 TDengine，可将典型的物联网、车联网、工业互联网大数据平台的总拥有成本大幅降低。表现在几个方面：
 
 1. 由于其超强性能，它能将系统需要的计算资源和存储资源大幅降低
-2. 因为采用 SQL 接口，能与众多第三放软件无缝集成，学习迁移成本大幅下降
+2. 因为采用 SQL 接口，能与众多第三方软件无缝集成，学习迁移成本大幅下降
 3. 因为其 All In One 的特性，系统复杂度降低，能降研发成本
 4. 因为运维维护简单，运营维护成本能大幅降低
 

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

@@ -93,7 +93,7 @@ Maven 项目中，在 pom.xml 中添加以下依赖：
 可以通过下载 TDengine 的源码，自己编译最新版本的 Java connector
 
 ```shell
-git clone https://github.com/taosdata/taos-connector-jdbc.git
+git clone https://github.com/taosdata/taos-connector-jdbc.git --branch 2.0
 cd taos-connector-jdbc
 mvn clean install -Dmaven.test.skip=true
 ```

include/libs/function/functionMgt.h

@@ -197,6 +197,7 @@ bool fmIsSystemInfoFunc(int32_t funcId);
 bool fmIsImplicitTsFunc(int32_t funcId);
 bool fmIsClientPseudoColumnFunc(int32_t funcId);
 bool fmIsMultiRowsFunc(int32_t funcId);
+bool fmIsKeepOrderFunc(int32_t funcId);
 
 int32_t fmGetDistMethod(const SFunctionNode* pFunc, SFunctionNode** pPartialFunc, SFunctionNode** pMergeFunc);
 

include/libs/nodes/plannodes.h

@@ -29,9 +29,17 @@ extern "C" {
 typedef enum EDataOrderLevel {
   DATA_ORDER_LEVEL_NONE = 1,
   DATA_ORDER_LEVEL_IN_BLOCK,
-  DATA_ORDER_LEVEL_IN_GROUP
+  DATA_ORDER_LEVEL_IN_GROUP,
+  DATA_ORDER_LEVEL_GLOBAL
 } EDataOrderLevel;
 
+typedef enum EGroupAction {
+  GROUP_ACTION_NONE = 1,
+  GROUP_ACTION_SET,
+  GROUP_ACTION_KEEP,
+  GROUP_ACTION_CLEAR
+} EGroupAction;
+
 typedef struct SLogicNode {
   ENodeType          type;
   SNodeList*         pTargets;  // SColumnNode
@@ -44,6 +52,7 @@ typedef struct SLogicNode {
   SNode*             pSlimit;
   EDataOrderLevel    requireDataOrder;  // requirements for input data
   EDataOrderLevel    resultDataOrder;   // properties of the output data
+  EGroupAction       groupAction;
 } SLogicNode;
 
 typedef enum EScanType {

include/os/osSignal.h

@@ -44,7 +44,11 @@ extern "C" {
   #define SIGBREAK 1234
 #endif
 
+#ifdef WINDOWS
+typedef BOOL (*FSignalHandler)(DWORD fdwCtrlType);
+#else
 typedef void (*FSignalHandler)(int32_t signum, void *sigInfo, void *context);
+#endif
 void taosSetSignal(int32_t signum, FSignalHandler sigfp);
 void taosIgnSignal(int32_t signum);
 void taosDflSignal(int32_t signum);

include/os/osSystem.h

@@ -29,9 +29,6 @@ extern "C" {
     #define tcgetattr TCGETATTR_FUNC_TAOS_FORBID
 #endif
 
-#define TAOS_CONSOLE_PROMPT_HEADER "taos> "
-#define TAOS_CONSOLE_PROMPT_CONTINUE "   -> "
-
 typedef struct TdCmd *TdCmdPtr;
 
 TdCmdPtr taosOpenCmd(const char* cmd);

source/common/src/tdatablock.c

@@ -1107,6 +1107,11 @@ int32_t blockDataSort_rv(SSDataBlock* pDataBlock, SArray* pOrderInfo, bool nullF
 
 void blockDataCleanup(SSDataBlock* pDataBlock) {
   pDataBlock->info.rows = 0;
+  pDataBlock->info.groupId = 0;
+
+  pDataBlock->info.window.ekey = 0;
+  pDataBlock->info.window.skey = 0;
+
   size_t numOfCols = taosArrayGetSize(pDataBlock->pDataBlock);
   for (int32_t i = 0; i < numOfCols; ++i) {
     SColumnInfoData* p = taosArrayGet(pDataBlock->pDataBlock, i);

source/common/src/tglobal.c

@@ -183,7 +183,7 @@ bool tsStartUdfd = true;
 int32_t tsTransPullupInterval = 2;
 int32_t tsMqRebalanceInterval = 2;
 int32_t tsTtlUnit = 86400;
-int32_t tsTtlPushInterval = 60;
+int32_t tsTtlPushInterval = 86400;
 int32_t tsGrantHBInterval = 60;
 
 void taosAddDataDir(int32_t index, char *v1, int32_t level, int32_t primary) {
@@ -466,7 +466,7 @@ static int32_t taosAddServerCfg(SConfig *pCfg) {
   if (cfgAddInt32(pCfg, "transPullupInterval", tsTransPullupInterval, 1, 10000, 1) != 0) return -1;
   if (cfgAddInt32(pCfg, "mqRebalanceInterval", tsMqRebalanceInterval, 1, 10000, 1) != 0) return -1;
   if (cfgAddInt32(pCfg, "ttlUnit", tsTtlUnit, 1, 86400 * 365, 1) != 0) return -1;
-  if (cfgAddInt32(pCfg, "ttlPushInterval", tsTtlPushInterval, 1, 10000, 1) != 0) return -1;
+  if (cfgAddInt32(pCfg, "ttlPushInterval", tsTtlPushInterval, 1, 100000, 1) != 0) return -1;
 
   if (cfgAddBool(pCfg, "udf", tsStartUdfd, 0) != 0) return -1;
   return 0;

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

@@ -68,7 +68,7 @@ typedef struct {
 
 typedef struct {
   char*       qmsg;
-  qTaskInfo_t task[5];
+  qTaskInfo_t task;
 } STqExecCol;
 
 typedef struct {
@@ -82,7 +82,7 @@ typedef struct {
 typedef struct {
   int8_t subType;
 
-  STqReader* pExecReader[5];
+  STqReader* pExecReader;
   union {
     STqExecCol execCol;
     STqExecTb  execTb;
@@ -139,8 +139,7 @@ int64_t tqScan(STQ* pTq, const STqHandle* pHandle, SMqDataRsp* pRsp, STqOffsetVa
 int64_t tqFetchLog(STQ* pTq, STqHandle* pHandle, int64_t* fetchOffset, SWalCkHead** pHeadWithCkSum);
 
 // tqExec
-int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataRsp* pRsp, int32_t workerId);
-int32_t tqScanSnapshot(STQ* pTq, const STqExecHandle* pExec, SMqDataRsp* pRsp, STqOffsetVal offset, int32_t workerId);
+int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataRsp* pRsp);
 int32_t tqSendDataRsp(STQ* pTq, const SRpcMsg* pMsg, const SMqPollReq* pReq, const SMqDataRsp* pRsp);
 
 // tqMeta

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

@@ -40,12 +40,9 @@ typedef struct SDelIdx       SDelIdx;
 typedef struct STbData       STbData;
 typedef struct SMemTable     SMemTable;
 typedef struct STbDataIter   STbDataIter;
-typedef struct STable        STable;
 typedef struct SMapData      SMapData;
 typedef struct SBlockIdx     SBlockIdx;
 typedef struct SBlock        SBlock;
-typedef struct SBlockStatis  SBlockStatis;
-typedef struct SAggrBlkCol   SAggrBlkCol;
 typedef struct SColData      SColData;
 typedef struct SBlockDataHdr SBlockDataHdr;
 typedef struct SBlockData    SBlockData;
@@ -62,8 +59,7 @@ typedef struct SDelFReader   SDelFReader;
 typedef struct SRowIter      SRowIter;
 typedef struct STsdbFS       STsdbFS;
 typedef struct SRowMerger    SRowMerger;
-typedef struct STsdbFSState  STsdbFSState;
-typedef struct STsdbSnapHdr  STsdbSnapHdr;
+typedef struct STsdbReadSnap STsdbReadSnap;
 
 #define TSDB_MAX_SUBBLOCKS 8
 #define TSDB_FHDR_SIZE     512
@@ -176,8 +172,6 @@ void    tsdbMemTableDestroy(SMemTable *pMemTable);
 void    tsdbGetTbDataFromMemTable(SMemTable *pMemTable, tb_uid_t suid, tb_uid_t uid, STbData **ppTbData);
 void    tsdbRefMemTable(SMemTable *pMemTable);
 void    tsdbUnrefMemTable(SMemTable *pMemTable);
-int32_t tsdbTakeMemSnapshot(STsdb *pTsdb, SMemTable **ppMem, SMemTable **ppIMem);
-void    tsdbUntakeMemSnapshot(STsdb *pTsdb, SMemTable *pMem, SMemTable *pIMem);
 // STbDataIter
 int32_t  tsdbTbDataIterCreate(STbData *pTbData, TSDBKEY *pFrom, int8_t backward, STbDataIter **ppIter);
 void    *tsdbTbDataIterDestroy(STbDataIter *pIter);
@@ -188,30 +182,39 @@ bool     tsdbTbDataIterNext(STbDataIter *pIter);
 int32_t tsdbGetNRowsInTbData(STbData *pTbData);
 // tsdbFile.c ==============================================================================================
 typedef enum { TSDB_HEAD_FILE = 0, TSDB_DATA_FILE, TSDB_LAST_FILE, TSDB_SMA_FILE } EDataFileT;
-void    tsdbDataFileName(STsdb *pTsdb, SDFileSet *pDFileSet, EDataFileT ftype, char fname[]);
-bool    tsdbFileIsSame(SDFileSet *pDFileSet1, SDFileSet *pDFileSet2, EDataFileT ftype);
+
 bool    tsdbDelFileIsSame(SDelFile *pDelFile1, SDelFile *pDelFile2);
-int32_t tsdbUpdateDFileHdr(TdFilePtr pFD, SDFileSet *pSet, EDataFileT ftype);
 int32_t tsdbDFileRollback(STsdb *pTsdb, SDFileSet *pSet, EDataFileT ftype);
-int32_t tPutDataFileHdr(uint8_t *p, SDFileSet *pSet, EDataFileT ftype);
+int32_t tPutHeadFile(uint8_t *p, SHeadFile *pHeadFile);
+int32_t tPutDataFile(uint8_t *p, SDataFile *pDataFile);
+int32_t tPutLastFile(uint8_t *p, SLastFile *pLastFile);
+int32_t tPutSmaFile(uint8_t *p, SSmaFile *pSmaFile);
 int32_t tPutDelFile(uint8_t *p, SDelFile *pDelFile);
 int32_t tGetDelFile(uint8_t *p, SDelFile *pDelFile);
 int32_t tPutDFileSet(uint8_t *p, SDFileSet *pSet);
 int32_t tGetDFileSet(uint8_t *p, SDFileSet *pSet);
+
+void tsdbHeadFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SHeadFile *pHeadF, char fname[]);
+void tsdbDataFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SDataFile *pDataF, char fname[]);
+void tsdbLastFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SLastFile *pLastF, char fname[]);
+void tsdbSmaFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SSmaFile *pSmaF, char fname[]);
 // SDelFile
 void tsdbDelFileName(STsdb *pTsdb, SDelFile *pFile, char fname[]);
 // tsdbFS.c ==============================================================================================
-int32_t tsdbFSOpen(STsdb *pTsdb, STsdbFS **ppFS);
-int32_t tsdbFSClose(STsdbFS *pFS);
-int32_t tsdbFSBegin(STsdbFS *pFS);
-int32_t tsdbFSCommit(STsdbFS *pFS);
+int32_t tsdbFSOpen(STsdb *pTsdb);
+int32_t tsdbFSClose(STsdb *pTsdb);
+int32_t tsdbFSCopy(STsdb *pTsdb, STsdbFS *pFS);
+void    tsdbFSDestroy(STsdbFS *pFS);
+int32_t tDFileSetCmprFn(const void *p1, const void *p2);
+int32_t tsdbFSCommit1(STsdb *pTsdb, STsdbFS *pFS);
+int32_t tsdbFSCommit2(STsdb *pTsdb, STsdbFS *pFS);
+int32_t tsdbFSRef(STsdb *pTsdb, STsdbFS *pFS);
+void    tsdbFSUnref(STsdb *pTsdb, STsdbFS *pFS);
+
 int32_t tsdbFSRollback(STsdbFS *pFS);
 
-int32_t    tsdbFSStateUpsertDelFile(STsdbFSState *pState, SDelFile *pDelFile);
-int32_t    tsdbFSStateUpsertDFileSet(STsdbFSState *pState, SDFileSet *pSet);
-void       tsdbFSStateDeleteDFileSet(STsdbFSState *pState, int32_t fid);
-SDelFile  *tsdbFSStateGetDelFile(STsdbFSState *pState);
-SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid, int32_t flag);
+int32_t tsdbFSUpsertFSet(STsdbFS *pFS, SDFileSet *pSet);
+int32_t tsdbFSUpsertDelFile(STsdbFS *pFS, SDelFile *pDelFile);
 // tsdbReaderWriter.c ==============================================================================================
 // SDataFWriter
 int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pSet);
@@ -222,8 +225,7 @@ int32_t tsdbWriteBlock(SDataFWriter *pWriter, SMapData *pMapData, uint8_t **ppBu
 int32_t tsdbWriteBlockData(SDataFWriter *pWriter, SBlockData *pBlockData, uint8_t **ppBuf1, uint8_t **ppBuf2,
                            SBlockIdx *pBlockIdx, SBlock *pBlock, int8_t cmprAlg);
 
-SDFileSet *tsdbDataFWriterGetWSet(SDataFWriter *pWriter);
-int32_t    tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo);
+int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo);
 // SDataFReader
 int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pSet);
 int32_t tsdbDataFReaderClose(SDataFReader **ppReader);
@@ -245,6 +247,9 @@ int32_t tsdbDelFReaderOpen(SDelFReader **ppReader, SDelFile *pFile, STsdb *pTsdb
 int32_t tsdbDelFReaderClose(SDelFReader **ppReader);
 int32_t tsdbReadDelData(SDelFReader *pReader, SDelIdx *pDelIdx, SArray *aDelData, uint8_t **ppBuf);
 int32_t tsdbReadDelIdx(SDelFReader *pReader, SArray *aDelIdx, uint8_t **ppBuf);
+// tsdbRead.c ==============================================================================================
+int32_t tsdbTakeReadSnap(STsdb *pTsdb, STsdbReadSnap **ppSnap);
+void    tsdbUntakeReadSnap(STsdb *pTsdb, STsdbReadSnap *pSnap);
 
 #define TSDB_CACHE_NO(c)       ((c).cacheLast == 0)
 #define TSDB_CACHE_LAST_ROW(c) (((c).cacheLast & 1) > 0)
@@ -276,6 +281,11 @@ typedef struct {
   TSKEY minKey;
 } SRtn;
 
+struct STsdbFS {
+  SDelFile *pDelFile;
+  SArray   *aDFileSet;  // SArray<SDFileSet>
+};
+
 struct STsdb {
   char          *path;
   SVnode        *pVnode;
@@ -283,7 +293,7 @@ struct STsdb {
   TdThreadRwlock rwLock;
   SMemTable     *mem;
   SMemTable     *imem;
-  STsdbFS       *pFS;
+  STsdbFS        fs;
   SLRUCache     *lruCache;
 };
 
@@ -402,16 +412,6 @@ struct SBlock {
   SSubBlock aSubBlock[TSDB_MAX_SUBBLOCKS];
 };
 
-struct SAggrBlkCol {
-  int16_t colId;
-  int16_t maxIndex;
-  int16_t minIndex;
-  int16_t numOfNull;
-  int64_t sum;
-  int64_t max;
-  int64_t min;
-};
-
 struct SColData {
   int16_t  cid;
   int8_t   type;
@@ -465,12 +465,6 @@ struct SDelIdx {
   int64_t  size;
 };
 
-struct SDelFile {
-  int64_t commitID;
-  int64_t size;
-  int64_t offset;
-};
-
 #pragma pack(push, 1)
 struct SBlockDataHdr {
   uint32_t delimiter;
@@ -479,34 +473,50 @@ struct SBlockDataHdr {
 };
 #pragma pack(pop)
 
+struct SDelFile {
+  volatile int32_t nRef;
+
+  int64_t commitID;
+  int64_t size;
+  int64_t offset;
+};
+
 struct SHeadFile {
+  volatile int32_t nRef;
+
   int64_t commitID;
   int64_t size;
   int64_t offset;
 };
 
 struct SDataFile {
+  volatile int32_t nRef;
+
   int64_t commitID;
   int64_t size;
 };
 
 struct SLastFile {
+  volatile int32_t nRef;
+
   int64_t commitID;
   int64_t size;
 };
 
 struct SSmaFile {
+  volatile int32_t nRef;
+
   int64_t commitID;
   int64_t size;
 };
 
 struct SDFileSet {
-  SDiskID   diskId;
-  int32_t   fid;
-  SHeadFile fHead;
-  SDataFile fData;
-  SLastFile fLast;
-  SSmaFile  fSma;
+  SDiskID    diskId;
+  int32_t    fid;
+  SHeadFile *pHeadF;
+  SDataFile *pDataF;
+  SLastFile *pLastF;
+  SSmaFile  *pSmaF;
 };
 
 struct SRowIter {
@@ -521,26 +531,33 @@ struct SRowMerger {
   SArray   *pArray;  // SArray<SColVal>
 };
 
-struct STsdbFSState {
-  SDelFile *pDelFile;
-  SArray   *aDFileSet;  // SArray<aDFileSet>
-  SDelFile  delFile;
-};
-
-struct STsdbFS {
-  STsdb         *pTsdb;
-  TdThreadRwlock lock;
-  int8_t         inTxn;
-  STsdbFSState  *cState;
-  STsdbFSState  *nState;
-};
-
 struct SDelFWriter {
   STsdb    *pTsdb;
   SDelFile  fDel;
   TdFilePtr pWriteH;
 };
 
+struct SDataFWriter {
+  STsdb    *pTsdb;
+  SDFileSet wSet;
+
+  TdFilePtr pHeadFD;
+  TdFilePtr pDataFD;
+  TdFilePtr pLastFD;
+  TdFilePtr pSmaFD;
+
+  SHeadFile fHead;
+  SDataFile fData;
+  SLastFile fLast;
+  SSmaFile  fSma;
+};
+
+struct STsdbReadSnap {
+  SMemTable *pMem;
+  SMemTable *pIMem;
+  STsdbFS    fs;
+};
+
 #ifdef __cplusplus
 }
 #endif

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

@@ -146,7 +146,7 @@ int32_t tqCheckColModifiable(STQ* pTq, int32_t colId);
 int32_t tqProcessVgChangeReq(STQ* pTq, char* msg, int32_t msgLen);
 int32_t tqProcessVgDeleteReq(STQ* pTq, char* msg, int32_t msgLen);
 int32_t tqProcessOffsetCommitReq(STQ* pTq, char* msg, int32_t msgLen);
-int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId);
+int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg);
 int32_t tqProcessTaskDeployReq(STQ* pTq, char* msg, int32_t msgLen);
 int32_t tqProcessTaskDropReq(STQ* pTq, char* msg, int32_t msgLen);
 int32_t tqProcessStreamTrigger(STQ* pTq, SSubmitReq* data);

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

@@ -438,12 +438,15 @@ int metaDropTable(SMeta *pMeta, int64_t version, SVDropTbReq *pReq, SArray *tbUi
 }
 
 int metaTtlDropTable(SMeta *pMeta, int64_t ttl, SArray *tbUids) {
-  metaWLock(pMeta);
   int ret = metaTtlSmaller(pMeta, ttl, tbUids);
   if (ret != 0) {
-    metaULock(pMeta);
     return ret;
   }
+  if (taosArrayGetSize(tbUids) == 0){
+    return 0;
+  }
+
+  metaWLock(pMeta);
   for (int i = 0; i < taosArrayGetSize(tbUids); ++i) {
     tb_uid_t *uid = (tb_uid_t *)taosArrayGet(tbUids, i);
     metaDropTableByUid(pMeta, *uid, NULL);

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

@@ -582,7 +582,7 @@ static int32_t tdRSmaFetchAndSubmitResult(SRSmaInfoItem *pItem, STSchema *pTSche
 
     int32_t code = qExecTask(pItem->taskInfo, &output, &ts);
     if (code < 0) {
-      smaError("vgId:%d, qExecTask for rsma table %" PRIi64 "l evel %" PRIi8 " failed since %s", SMA_VID(pSma), suid,
+      smaError("vgId:%d, qExecTask for rsma table %" PRIi64 " level %" PRIi8 " failed since %s", SMA_VID(pSma), suid,
                pItem->level, terrstr(code));
       goto _err;
     }

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

@@ -215,10 +215,10 @@ int32_t tqCheckColModifiable(STQ* pTq, int32_t colId) {
     if (pIter == NULL) break;
     STqHandle* pExec = (STqHandle*)pIter;
     if (pExec->execHandle.subType == TOPIC_SUB_TYPE__COLUMN) {
-      int32_t sz = taosArrayGetSize(pExec->colIdList);
+      int32_t sz = pExec->execHandle.pSchemaWrapper->nCols;
       for (int32_t i = 0; i < sz; i++) {
-        int32_t forbidColId = *(int32_t*)taosArrayGet(pExec->colIdList, i);
-        if (forbidColId == colId) {
+        SSchema* pSchema = &pExec->execHandle.pSchemaWrapper->pSchema[i];
+        if (pSchema->colId == colId) {
           taosHashCancelIterate(pTq->handles, pIter);
           return -1;
         }
@@ -262,7 +262,7 @@ static int32_t tqInitDataRsp(SMqDataRsp* pRsp, const SMqPollReq* pReq, int8_t su
 
 static int32_t tqInitMetaRsp(SMqMetaRsp* pRsp, const SMqPollReq* pReq) { return 0; }
 
-int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
+int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg) {
   SMqPollReq*  pReq = pMsg->pCont;
   int64_t      consumerId = pReq->consumerId;
   int64_t      timeout = pReq->timeout;
@@ -271,9 +271,6 @@ int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
   STqOffsetVal reqOffset = pReq->reqOffset;
   STqOffsetVal fetchOffsetNew;
 
-  // todo
-  workerId = 0;
-
   // 1.find handle
   STqHandle* pHandle = taosHashGet(pTq->handles, pReq->subKey, strlen(pReq->subKey));
   /*ASSERT(pHandle);*/
@@ -405,7 +402,7 @@ int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
       if (pHead->msgType == TDMT_VND_SUBMIT) {
         SSubmitReq* pCont = (SSubmitReq*)&pHead->body;
 
-        if (tqLogScanExec(pTq, &pHandle->execHandle, pCont, &dataRsp, workerId) < 0) {
+        if (tqLogScanExec(pTq, &pHandle->execHandle, pCont, &dataRsp) < 0) {
           /*ASSERT(0);*/
         }
         // TODO batch optimization:
@@ -518,27 +515,24 @@ int32_t tqProcessVgChangeReq(STQ* pTq, char* msg, int32_t msgLen) {
       pHandle->execHandle.execCol.qmsg = req.qmsg;
       pHandle->snapshotVer = ver;
       req.qmsg = NULL;
-      for (int32_t i = 0; i < 5; i++) {
-        SReadHandle handle = {
-            .meta = pTq->pVnode->pMeta,
-            .vnode = pTq->pVnode,
-            .initTableReader = true,
-            .initTqReader = true,
-            .version = ver,
-        };
-        pHandle->execHandle.execCol.task[i] = qCreateQueueExecTaskInfo(pHandle->execHandle.execCol.qmsg, &handle, &pHandle->execHandle.numOfCols,
-            &pHandle->execHandle.pSchemaWrapper);
-        ASSERT(pHandle->execHandle.execCol.task[i]);
-        void* scanner = NULL;
-        qExtractStreamScanner(pHandle->execHandle.execCol.task[i], &scanner);
-        ASSERT(scanner);
-        pHandle->execHandle.pExecReader[i] = qExtractReaderFromStreamScanner(scanner);
-        ASSERT(pHandle->execHandle.pExecReader[i]);
-      }
+      SReadHandle handle = {
+          .meta = pTq->pVnode->pMeta,
+          .vnode = pTq->pVnode,
+          .initTableReader = true,
+          .initTqReader = true,
+          .version = ver,
+      };
+      pHandle->execHandle.execCol.task =
+          qCreateQueueExecTaskInfo(pHandle->execHandle.execCol.qmsg, &handle, &pHandle->execHandle.numOfCols,
+                                   &pHandle->execHandle.pSchemaWrapper);
+      ASSERT(pHandle->execHandle.execCol.task);
+      void* scanner = NULL;
+      qExtractStreamScanner(pHandle->execHandle.execCol.task, &scanner);
+      ASSERT(scanner);
+      pHandle->execHandle.pExecReader = qExtractReaderFromStreamScanner(scanner);
+      ASSERT(pHandle->execHandle.pExecReader);
     } else if (pHandle->execHandle.subType == TOPIC_SUB_TYPE__DB) {
-      for (int32_t i = 0; i < 5; i++) {
-        pHandle->execHandle.pExecReader[i] = tqOpenReader(pTq->pVnode);
-      }
+      pHandle->execHandle.pExecReader = tqOpenReader(pTq->pVnode);
       pHandle->execHandle.execDb.pFilterOutTbUid =
           taosHashInit(64, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BIGINT), false, HASH_NO_LOCK);
     } else if (pHandle->execHandle.subType == TOPIC_SUB_TYPE__TABLE) {
@@ -550,10 +544,8 @@ int32_t tqProcessVgChangeReq(STQ* pTq, char* msg, int32_t msgLen) {
         int64_t tbUid = *(int64_t*)taosArrayGet(tbUidList, i);
         tqDebug("vgId:%d, idx %d, uid:%" PRId64, TD_VID(pTq->pVnode), i, tbUid);
       }
-      for (int32_t i = 0; i < 5; i++) {
-        pHandle->execHandle.pExecReader[i] = tqOpenReader(pTq->pVnode);
-        tqReaderSetTbUidList(pHandle->execHandle.pExecReader[i], tbUidList);
-      }
+      pHandle->execHandle.pExecReader = tqOpenReader(pTq->pVnode);
+      tqReaderSetTbUidList(pHandle->execHandle.pExecReader, tbUidList);
       taosArrayDestroy(tbUidList);
     }
     taosHashPut(pTq->handles, req.subKey, strlen(req.subKey), pHandle, sizeof(STqHandle));

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

@@ -37,8 +37,8 @@ static int32_t tqAddBlockDataToRsp(const SSDataBlock* pBlock, SMqDataRsp* pRsp,
   return 0;
 }
 
-static int32_t tqAddBlockSchemaToRsp(const STqExecHandle* pExec, int32_t workerId, SMqDataRsp* pRsp) {
-  SSchemaWrapper* pSW = tCloneSSchemaWrapper(pExec->pExecReader[workerId]->pSchemaWrapper);
+static int32_t tqAddBlockSchemaToRsp(const STqExecHandle* pExec, SMqDataRsp* pRsp) {
+  SSchemaWrapper* pSW = tCloneSSchemaWrapper(pExec->pExecReader->pSchemaWrapper);
   if (pSW == NULL) {
     return -1;
   }
@@ -51,6 +51,7 @@ static int32_t tqAddTbNameToRsp(const STQ* pTq, int64_t uid, SMqDataRsp* pRsp) {
   metaReaderInit(&mr, pTq->pVnode->pMeta, 0);
   // TODO add reference to gurantee success
   if (metaGetTableEntryByUid(&mr, uid) < 0) {
+    metaReaderClear(&mr);
     return -1;
   }
   char* tbName = strdup(mr.me.name);
@@ -61,7 +62,7 @@ static int32_t tqAddTbNameToRsp(const STQ* pTq, int64_t uid, SMqDataRsp* pRsp) {
 
 int64_t tqScan(STQ* pTq, const STqHandle* pHandle, SMqDataRsp* pRsp, STqOffsetVal* pOffset) {
   const STqExecHandle* pExec = &pHandle->execHandle;
-  qTaskInfo_t          task = pExec->execCol.task[0];
+  qTaskInfo_t          task = pExec->execCol.task;
 
   if (qStreamPrepareScan(task, pOffset) < 0) {
     if (pOffset->type == TMQ_OFFSET__LOG) {
@@ -89,7 +90,7 @@ int64_t tqScan(STQ* pTq, const STqHandle* pHandle, SMqDataRsp* pRsp, STqOffsetVa
     if (pDataBlock != NULL) {
       if (pRsp->withTbName) {
         if (pOffset->type == TMQ_OFFSET__LOG) {
-          int64_t uid = pExec->pExecReader[0]->msgIter.uid;
+          int64_t uid = pExec->pExecReader->msgIter.uid;
           if (tqAddTbNameToRsp(pTq, uid, pRsp) < 0) {
             continue;
           }
@@ -108,6 +109,7 @@ int64_t tqScan(STQ* pTq, const STqHandle* pHandle, SMqDataRsp* pRsp, STqOffsetVa
     }
 
     if (pRsp->blockNum == 0 && pOffset->type == TMQ_OFFSET__SNAPSHOT_DATA) {
+      tqDebug("vgId: %d, tsdb consume over, switch to wal, ver %ld", TD_VID(pTq->pVnode), pHandle->snapshotVer + 1);
       tqOffsetResetToLog(pOffset, pHandle->snapshotVer);
       qStreamPrepareScan(task, pOffset);
       continue;
@@ -184,12 +186,12 @@ int32_t tqScanSnapshot(STQ* pTq, const STqExecHandle* pExec, SMqDataRsp* pRsp, S
 }
 #endif
 
-int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataRsp* pRsp, int32_t workerId) {
+int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataRsp* pRsp) {
   ASSERT(pExec->subType != TOPIC_SUB_TYPE__COLUMN);
 
   if (pExec->subType == TOPIC_SUB_TYPE__TABLE) {
     pRsp->withSchema = 1;
-    STqReader* pReader = pExec->pExecReader[workerId];
+    STqReader* pReader = pExec->pExecReader;
     tqReaderSetDataMsg(pReader, pReq, 0);
     while (tqNextDataBlock(pReader)) {
       SSDataBlock block = {0};
@@ -197,18 +199,18 @@ int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataR
         if (terrno == TSDB_CODE_TQ_TABLE_SCHEMA_NOT_FOUND) continue;
       }
       if (pRsp->withTbName) {
-        int64_t uid = pExec->pExecReader[workerId]->msgIter.uid;
+        int64_t uid = pExec->pExecReader->msgIter.uid;
         if (tqAddTbNameToRsp(pTq, uid, pRsp) < 0) {
           continue;
         }
       }
       tqAddBlockDataToRsp(&block, pRsp, taosArrayGetSize(block.pDataBlock));
-      tqAddBlockSchemaToRsp(pExec, workerId, pRsp);
+      tqAddBlockSchemaToRsp(pExec, pRsp);
       pRsp->blockNum++;
     }
   } else if (pExec->subType == TOPIC_SUB_TYPE__DB) {
     pRsp->withSchema = 1;
-    STqReader* pReader = pExec->pExecReader[workerId];
+    STqReader* pReader = pExec->pExecReader;
     tqReaderSetDataMsg(pReader, pReq, 0);
     while (tqNextDataBlockFilterOut(pReader, pExec->execDb.pFilterOutTbUid)) {
       SSDataBlock block = {0};
@@ -216,13 +218,13 @@ int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataR
         if (terrno == TSDB_CODE_TQ_TABLE_SCHEMA_NOT_FOUND) continue;
       }
       if (pRsp->withTbName) {
-        int64_t uid = pExec->pExecReader[workerId]->msgIter.uid;
+        int64_t uid = pExec->pExecReader->msgIter.uid;
         if (tqAddTbNameToRsp(pTq, uid, pRsp) < 0) {
           continue;
         }
       }
       tqAddBlockDataToRsp(&block, pRsp, taosArrayGetSize(block.pDataBlock));
-      tqAddBlockSchemaToRsp(pExec, workerId, pRsp);
+      tqAddBlockSchemaToRsp(pExec, pRsp);
       pRsp->blockNum++;
     }
   }

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

@@ -80,28 +80,23 @@ int32_t tqMetaOpen(STQ* pTq) {
     tDecoderInit(&decoder, (uint8_t*)pVal, vLen);
     tDecodeSTqHandle(&decoder, &handle);
     handle.pWalReader = walOpenReader(pTq->pVnode->pWal, NULL);
-    /*for (int32_t i = 0; i < 5; i++) {*/
-    /*handle.execHandle.pExecReader[i] = tqOpenReader(pTq->pVnode);*/
-    /*}*/
     if (handle.execHandle.subType == TOPIC_SUB_TYPE__COLUMN) {
-      for (int32_t i = 0; i < 5; i++) {
-        SReadHandle reader = {
-            .meta = pTq->pVnode->pMeta,
-            .vnode = pTq->pVnode,
-            .initTableReader = true,
-            .initTqReader = true,
-            .version = handle.snapshotVer,
-        };
-
-        handle.execHandle.execCol.task[i] = qCreateQueueExecTaskInfo(handle.execHandle.execCol.qmsg, &reader, &handle.execHandle.numOfCols,
-            &handle.execHandle.pSchemaWrapper);
-        ASSERT(handle.execHandle.execCol.task[i]);
-        void* scanner = NULL;
-        qExtractStreamScanner(handle.execHandle.execCol.task[i], &scanner);
-        ASSERT(scanner);
-        handle.execHandle.pExecReader[i] = qExtractReaderFromStreamScanner(scanner);
-        ASSERT(handle.execHandle.pExecReader[i]);
-      }
+      SReadHandle reader = {
+          .meta = pTq->pVnode->pMeta,
+          .vnode = pTq->pVnode,
+          .initTableReader = true,
+          .initTqReader = true,
+          .version = handle.snapshotVer,
+      };
+
+      handle.execHandle.execCol.task =
+          qCreateQueueExecTaskInfo(handle.execHandle.execCol.qmsg, &reader, &handle.execHandle.numOfCols, &handle.execHandle.pSchemaWrapper);
+      ASSERT(handle.execHandle.execCol.task);
+      void* scanner = NULL;
+      qExtractStreamScanner(handle.execHandle.execCol.task, &scanner);
+      ASSERT(scanner);
+      handle.execHandle.pExecReader = qExtractReaderFromStreamScanner(scanner);
+      ASSERT(handle.execHandle.pExecReader);
     } else {
       handle.execHandle.execDb.pFilterOutTbUid =
           taosHashInit(64, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BIGINT), false, HASH_NO_LOCK);

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

@@ -394,10 +394,8 @@ int32_t tqUpdateTbUidList(STQ* pTq, const SArray* tbUidList, bool isAdd) {
     if (pIter == NULL) break;
     STqHandle* pExec = (STqHandle*)pIter;
     if (pExec->execHandle.subType == TOPIC_SUB_TYPE__COLUMN) {
-      for (int32_t i = 0; i < 5; i++) {
-        int32_t code = qUpdateQualifiedTableId(pExec->execHandle.execCol.task[i], tbUidList, isAdd);
-        ASSERT(code == 0);
-      }
+      int32_t code = qUpdateQualifiedTableId(pExec->execHandle.execCol.task, tbUidList, isAdd);
+      ASSERT(code == 0);
     } else if (pExec->execHandle.subType == TOPIC_SUB_TYPE__DB) {
       if (!isAdd) {
         int32_t sz = taosArrayGetSize(tbUidList);

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

@@ -127,6 +127,8 @@ SSubmitReq* tdBlockToSubmit(const SArray* pBlocks, const STSchema* pTSchema, boo
 
     int32_t rows = pDataBlock->info.rows;
 
+    tqDebug("tq sink, convert block %d, rows: %d", i, rows);
+
     int32_t dataLen = 0;
 
     void* blkSchema = POINTER_SHIFT(blkHead, sizeof(SSubmitBlk));
@@ -178,11 +180,14 @@ void tqTableSink(SStreamTask* pTask, void* vnode, int64_t ver, void* data) {
   const SArray* pRes = (const SArray*)data;
   SVnode*       pVnode = (SVnode*)vnode;
 
-  tqDebug("task write into table, vgId %d, block num: %d", pVnode->config.vgId, (int32_t)pRes->size);
+  tqDebug("vgId:%d, task %d write into table, block num: %d", TD_VID(pVnode), pTask->taskId, (int32_t)pRes->size);
 
   ASSERT(pTask->tbSink.pTSchema);
   SSubmitReq* pReq = tdBlockToSubmit(pRes, pTask->tbSink.pTSchema, true, pTask->tbSink.stbUid,
                                      pTask->tbSink.stbFullName, pVnode->config.vgId);
+
+  tqDebug("vgId:%d, task %d convert blocks over, put into write-queue", TD_VID(pVnode), pTask->taskId);
+
   /*tPrintFixedSchemaSubmitReq(pReq, pTask->tbSink.pTSchema);*/
   // build write msg
   SRpcMsg msg = {

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

@@ -29,6 +29,7 @@ typedef struct {
   int32_t minRow;
   int32_t maxRow;
   int8_t  cmprAlg;
+  STsdbFS fs;
   // --------------
   TSKEY   nextKey;  // reset by each table commit
   int32_t commitFid;
@@ -119,9 +120,6 @@ int32_t tsdbCommit(STsdb *pTsdb) {
   code = tsdbCommitDel(&commith);
   if (code) goto _err;
 
-  code = tsdbCommitCache(&commith);
-  if (code) goto _err;
-
   // end commit
   code = tsdbEndCommit(&commith, 0);
   if (code) goto _err;
@@ -158,7 +156,7 @@ static int32_t tsdbCommitDelStart(SCommitter *pCommitter) {
     goto _err;
   }
 
-  SDelFile *pDelFileR = pTsdb->pFS->nState->pDelFile;
+  SDelFile *pDelFileR = pCommitter->fs.pDelFile;
   if (pDelFileR) {
     code = tsdbDelFReaderOpen(&pCommitter->pDelFReader, pDelFileR, pTsdb, NULL);
     if (code) goto _err;
@@ -247,7 +245,7 @@ static int32_t tsdbCommitDelEnd(SCommitter *pCommitter) {
   code = tsdbUpdateDelFileHdr(pCommitter->pDelFWriter);
   if (code) goto _err;
 
-  code = tsdbFSStateUpsertDelFile(pTsdb->pFS->nState, &pCommitter->pDelFWriter->fDel);
+  code = tsdbFSUpsertDelFile(&pCommitter->fs, &pCommitter->pDelFWriter->fDel);
   if (code) goto _err;
 
   code = tsdbDelFWriterClose(&pCommitter->pDelFWriter, 1);
@@ -273,7 +271,6 @@ static int32_t tsdbCommitFileDataStart(SCommitter *pCommitter) {
   int32_t    code = 0;
   STsdb     *pTsdb = pCommitter->pTsdb;
   SDFileSet *pRSet = NULL;
-  SDFileSet  wSet;
 
   // memory
   pCommitter->nextKey = TSKEY_MAX;
@@ -282,7 +279,8 @@ static int32_t tsdbCommitFileDataStart(SCommitter *pCommitter) {
   taosArrayClear(pCommitter->aBlockIdx);
   tMapDataReset(&pCommitter->oBlockMap);
   tBlockDataReset(&pCommitter->oBlockData);
-  pRSet = tsdbFSStateGetDFileSet(pTsdb->pFS->nState, pCommitter->commitFid, TD_EQ);
+  pRSet = (SDFileSet *)taosArraySearch(pCommitter->fs.aDFileSet, &(SDFileSet){.fid = pCommitter->commitFid},
+                                       tDFileSetCmprFn, TD_EQ);
   if (pRSet) {
     code = tsdbDataFReaderOpen(&pCommitter->pReader, pTsdb, pRSet);
     if (code) goto _err;
@@ -292,23 +290,29 @@ static int32_t tsdbCommitFileDataStart(SCommitter *pCommitter) {
   }
 
   // new
+  SHeadFile fHead;
+  SDataFile fData;
+  SLastFile fLast;
+  SSmaFile  fSma;
+  SDFileSet wSet = {.pHeadF = &fHead, .pDataF = &fData, .pLastF = &fLast, .pSmaF = &fSma};
+
   taosArrayClear(pCommitter->aBlockIdxN);
   tMapDataReset(&pCommitter->nBlockMap);
   tBlockDataReset(&pCommitter->nBlockData);
   if (pRSet) {
-    wSet = (SDFileSet){.diskId = pRSet->diskId,
-                       .fid = pCommitter->commitFid,
-                       .fHead = {.commitID = pCommitter->commitID, .offset = 0, .size = 0},
-                       .fData = pRSet->fData,
-                       .fLast = {.commitID = pCommitter->commitID, .size = 0},
-                       .fSma = pRSet->fSma};
+    wSet.diskId = pRSet->diskId;
+    wSet.fid = pCommitter->commitFid;
+    fHead = (SHeadFile){.commitID = pCommitter->commitID, .offset = 0, .size = 0};
+    fData = *pRSet->pDataF;
+    fLast = (SLastFile){.commitID = pCommitter->commitID, .size = 0};
+    fSma = *pRSet->pSmaF;
   } else {
-    wSet = (SDFileSet){.diskId = (SDiskID){.level = 0, .id = 0},
-                       .fid = pCommitter->commitFid,
-                       .fHead = {.commitID = pCommitter->commitID, .offset = 0, .size = 0},
-                       .fData = {.commitID = pCommitter->commitID, .size = 0},
-                       .fLast = {.commitID = pCommitter->commitID, .size = 0},
-                       .fSma = {.commitID = pCommitter->commitID, .size = 0}};
+    wSet.diskId = (SDiskID){.level = 0, .id = 0};
+    wSet.fid = pCommitter->commitFid;
+    fHead = (SHeadFile){.commitID = pCommitter->commitID, .offset = 0, .size = 0};
+    fData = (SDataFile){.commitID = pCommitter->commitID, .size = 0};
+    fLast = (SLastFile){.commitID = pCommitter->commitID, .size = 0};
+    fSma = (SSmaFile){.commitID = pCommitter->commitID, .size = 0};
   }
   code = tsdbDataFWriterOpen(&pCommitter->pWriter, pTsdb, &wSet);
   if (code) goto _err;
@@ -855,7 +859,7 @@ static int32_t tsdbCommitFileDataEnd(SCommitter *pCommitter) {
   if (code) goto _err;
 
   // upsert SDFileSet
-  code = tsdbFSStateUpsertDFileSet(pCommitter->pTsdb->pFS->nState, tsdbDataFWriterGetWSet(pCommitter->pWriter));
+  code = tsdbFSUpsertFSet(&pCommitter->fs, &pCommitter->pWriter->wSet);
   if (code) goto _err;
 
   // close and sync
@@ -973,7 +977,7 @@ static int32_t tsdbStartCommit(STsdb *pTsdb, SCommitter *pCommitter) {
   pCommitter->maxRow = pTsdb->pVnode->config.tsdbCfg.maxRows;
   pCommitter->cmprAlg = pTsdb->pVnode->config.tsdbCfg.compression;
 
-  code = tsdbFSBegin(pTsdb->pFS);
+  code = tsdbFSCopy(pTsdb, &pCommitter->fs);
   if (code) goto _err;
 
   return code;
@@ -1142,28 +1146,33 @@ _err:
   return code;
 }
 
-static int32_t tsdbCommitCache(SCommitter *pCommitter) {
-  int32_t code = 0;
-  // TODO
-  return code;
-}
-
 static int32_t tsdbEndCommit(SCommitter *pCommitter, int32_t eno) {
   int32_t    code = 0;
   STsdb     *pTsdb = pCommitter->pTsdb;
   SMemTable *pMemTable = pTsdb->imem;
 
-  if (eno == 0) {
-    code = tsdbFSCommit(pTsdb->pFS);
-  } else {
-    code = tsdbFSRollback(pTsdb->pFS);
-  }
+  ASSERT(eno == 0);
+
+  code = tsdbFSCommit1(pTsdb, &pCommitter->fs);
+  if (code) goto _err;
 
+  // lock
   taosThreadRwlockWrlock(&pTsdb->rwLock);
+
+  // commit or rollback
+  code = tsdbFSCommit2(pTsdb, &pCommitter->fs);
+  if (code) {
+    taosThreadRwlockUnlock(&pTsdb->rwLock);
+    goto _err;
+  }
+
   pTsdb->imem = NULL;
+
+  // unlock
   taosThreadRwlockUnlock(&pTsdb->rwLock);
 
   tsdbUnrefMemTable(pMemTable);
+  tsdbFSDestroy(&pCommitter->fs);
 
   tsdbInfo("vgId:%d tsdb end commit", TD_VID(pTsdb->pVnode));
   return code;

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

@@ -15,7 +15,7 @@
 
 #include "tsdb.h"
 
-static int32_t tPutHeadFile(uint8_t *p, SHeadFile *pHeadFile) {
+int32_t tPutHeadFile(uint8_t *p, SHeadFile *pHeadFile) {
   int32_t n = 0;
 
   n += tPutI64v(p ? p + n : p, pHeadFile->commitID);
@@ -35,7 +35,7 @@ static int32_t tGetHeadFile(uint8_t *p, SHeadFile *pHeadFile) {
   return n;
 }
 
-static int32_t tPutDataFile(uint8_t *p, SDataFile *pDataFile) {
+int32_t tPutDataFile(uint8_t *p, SDataFile *pDataFile) {
   int32_t n = 0;
 
   n += tPutI64v(p ? p + n : p, pDataFile->commitID);
@@ -53,7 +53,7 @@ static int32_t tGetDataFile(uint8_t *p, SDataFile *pDataFile) {
   return n;
 }
 
-static int32_t tPutLastFile(uint8_t *p, SLastFile *pLastFile) {
+int32_t tPutLastFile(uint8_t *p, SLastFile *pLastFile) {
   int32_t n = 0;
 
   n += tPutI64v(p ? p + n : p, pLastFile->commitID);
@@ -71,7 +71,7 @@ static int32_t tGetLastFile(uint8_t *p, SLastFile *pLastFile) {
   return n;
 }
 
-static int32_t tPutSmaFile(uint8_t *p, SSmaFile *pSmaFile) {
+int32_t tPutSmaFile(uint8_t *p, SSmaFile *pSmaFile) {
   int32_t n = 0;
 
   n += tPutI64v(p ? p + n : p, pSmaFile->commitID);
@@ -90,123 +90,79 @@ static int32_t tGetSmaFile(uint8_t *p, SSmaFile *pSmaFile) {
 }
 
 // EXPOSED APIS ==================================================
-void tsdbDataFileName(STsdb *pTsdb, SDFileSet *pDFileSet, EDataFileT ftype, char fname[]) {
-  STfs *pTfs = pTsdb->pVnode->pTfs;
+void tsdbHeadFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SHeadFile *pHeadF, char fname[]) {
+  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTsdb->pVnode->pTfs, did),
+           TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), fid, pHeadF->commitID, ".head");
+}
 
-  switch (ftype) {
-    case TSDB_HEAD_FILE:
-      snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTfs, pDFileSet->diskId),
-               TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), pDFileSet->fid, pDFileSet->fHead.commitID,
-               ".head");
-      break;
-    case TSDB_DATA_FILE:
-      snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTfs, pDFileSet->diskId),
-               TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), pDFileSet->fid, pDFileSet->fData.commitID,
-               ".data");
-      break;
-    case TSDB_LAST_FILE:
-      snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTfs, pDFileSet->diskId),
-               TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), pDFileSet->fid, pDFileSet->fLast.commitID,
-               ".last");
-      break;
-    case TSDB_SMA_FILE:
-      snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTfs, pDFileSet->diskId),
-               TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), pDFileSet->fid, pDFileSet->fSma.commitID,
-               ".sma");
-      break;
-    default:
-      ASSERT(0);
-      break;
-  }
+void tsdbDataFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SDataFile *pDataF, char fname[]) {
+  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTsdb->pVnode->pTfs, did),
+           TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), fid, pDataF->commitID, ".data");
 }
 
-bool tsdbFileIsSame(SDFileSet *pDFileSet1, SDFileSet *pDFileSet2, EDataFileT ftype) {
-  if (pDFileSet1->diskId.level != pDFileSet2->diskId.level || pDFileSet1->diskId.id != pDFileSet2->diskId.id) {
-    return false;
-  }
+void tsdbLastFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SLastFile *pLastF, char fname[]) {
+  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTsdb->pVnode->pTfs, did),
+           TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), fid, pLastF->commitID, ".last");
+}
 
-  switch (ftype) {
-    case TSDB_HEAD_FILE:
-      return pDFileSet1->fHead.commitID == pDFileSet2->fHead.commitID;
-    case TSDB_DATA_FILE:
-      return pDFileSet1->fData.commitID == pDFileSet2->fData.commitID;
-    case TSDB_LAST_FILE:
-      return pDFileSet1->fLast.commitID == pDFileSet2->fLast.commitID;
-    case TSDB_SMA_FILE:
-      return pDFileSet1->fSma.commitID == pDFileSet2->fSma.commitID;
-    default:
-      ASSERT(0);
-      break;
-  }
+void tsdbSmaFileName(STsdb *pTsdb, SDiskID did, int32_t fid, SSmaFile *pSmaF, char fname[]) {
+  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%df%dver%" PRId64 "%s", tfsGetDiskPath(pTsdb->pVnode->pTfs, did),
+           TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), fid, pSmaF->commitID, ".sma");
 }
 
 bool tsdbDelFileIsSame(SDelFile *pDelFile1, SDelFile *pDelFile2) { return pDelFile1->commitID == pDelFile2->commitID; }
 
-int32_t tsdbUpdateDFileHdr(TdFilePtr pFD, SDFileSet *pSet, EDataFileT ftype) {
-  int32_t code = 0;
-  int64_t n;
-  char    hdr[TSDB_FHDR_SIZE];
-
-  memset(hdr, 0, TSDB_FHDR_SIZE);
-  tPutDataFileHdr(hdr, pSet, ftype);
-  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
-
-  n = taosLSeekFile(pFD, 0, SEEK_SET);
-  if (n < 0) {
-    code = TAOS_SYSTEM_ERROR(errno);
-    goto _exit;
-  }
-
-  n = taosWriteFile(pFD, hdr, TSDB_FHDR_SIZE);
-  if (n < 0) {
-    code = TAOS_SYSTEM_ERROR(errno);
-    goto _exit;
-  }
-
-_exit:
-  return code;
-}
-
 int32_t tsdbDFileRollback(STsdb *pTsdb, SDFileSet *pSet, EDataFileT ftype) {
   int32_t   code = 0;
   int64_t   size;
+  int64_t   n;
   TdFilePtr pFD;
   char      fname[TSDB_FILENAME_LEN];
-
-  tsdbDataFileName(pTsdb, pSet, ftype, fname);
-
-  // open
-  pFD = taosOpenFile(fname, TD_FILE_WRITE);
-  if (pFD == NULL) {
-    code = TAOS_SYSTEM_ERROR(errno);
-    goto _err;
-  }
+  char      hdr[TSDB_FHDR_SIZE] = {0};
 
   // truncate
   switch (ftype) {
-    case TSDB_HEAD_FILE:
-      size = pSet->fHead.size;
-      break;
     case TSDB_DATA_FILE:
-      size = pSet->fData.size;
-      break;
-    case TSDB_LAST_FILE:
-      size = pSet->fLast.size;
+      size = pSet->pDataF->size;
+      tsdbDataFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pDataF, fname);
+      tPutDataFile(hdr, pSet->pDataF);
       break;
     case TSDB_SMA_FILE:
-      size = pSet->fSma.size;
+      size = pSet->pSmaF->size;
+      tsdbSmaFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pSmaF, fname);
+      tPutSmaFile(hdr, pSet->pSmaF);
       break;
     default:
       ASSERT(0);
   }
+
+  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
+
+  // open
+  pFD = taosOpenFile(fname, TD_FILE_WRITE);
+  if (pFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  // ftruncate
   if (taosFtruncateFile(pFD, size) < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
   }
 
   // update header
-  code = tsdbUpdateDFileHdr(pFD, pSet, ftype);
-  if (code) goto _err;
+  n = taosLSeekFile(pFD, 0, SEEK_SET);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosWriteFile(pFD, hdr, TSDB_FHDR_SIZE);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
 
   // sync
   if (taosFsyncFile(pFD) < 0) {
@@ -220,42 +176,20 @@ int32_t tsdbDFileRollback(STsdb *pTsdb, SDFileSet *pSet, EDataFileT ftype) {
   return code;
 
 _err:
+  tsdbError("vgId:%d tsdb rollback file failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
   return code;
 }
 
-int32_t tPutDataFileHdr(uint8_t *p, SDFileSet *pSet, EDataFileT ftype) {
-  int32_t n = 0;
-
-  switch (ftype) {
-    case TSDB_HEAD_FILE:
-      n += tPutHeadFile(p ? p + n : p, &pSet->fHead);
-      break;
-    case TSDB_DATA_FILE:
-      n += tPutDataFile(p ? p + n : p, &pSet->fData);
-      break;
-    case TSDB_LAST_FILE:
-      n += tPutLastFile(p ? p + n : p, &pSet->fLast);
-      break;
-    case TSDB_SMA_FILE:
-      n += tPutSmaFile(p ? p + n : p, &pSet->fSma);
-      break;
-    default:
-      ASSERT(0);
-  }
-
-  return n;
-}
-
 int32_t tPutDFileSet(uint8_t *p, SDFileSet *pSet) {
   int32_t n = 0;
 
   n += tPutI32v(p ? p + n : p, pSet->diskId.level);
   n += tPutI32v(p ? p + n : p, pSet->diskId.id);
   n += tPutI32v(p ? p + n : p, pSet->fid);
-  n += tPutHeadFile(p ? p + n : p, &pSet->fHead);
-  n += tPutDataFile(p ? p + n : p, &pSet->fData);
-  n += tPutLastFile(p ? p + n : p, &pSet->fLast);
-  n += tPutSmaFile(p ? p + n : p, &pSet->fSma);
+  n += tPutHeadFile(p ? p + n : p, pSet->pHeadF);
+  n += tPutDataFile(p ? p + n : p, pSet->pDataF);
+  n += tPutLastFile(p ? p + n : p, pSet->pLastF);
+  n += tPutSmaFile(p ? p + n : p, pSet->pSmaF);
 
   return n;
 }
@@ -266,20 +200,18 @@ int32_t tGetDFileSet(uint8_t *p, SDFileSet *pSet) {
   n += tGetI32v(p + n, &pSet->diskId.level);
   n += tGetI32v(p + n, &pSet->diskId.id);
   n += tGetI32v(p + n, &pSet->fid);
-  n += tGetHeadFile(p + n, &pSet->fHead);
-  n += tGetDataFile(p + n, &pSet->fData);
-  n += tGetLastFile(p + n, &pSet->fLast);
-  n += tGetSmaFile(p + n, &pSet->fSma);
+  n += tGetHeadFile(p + n, pSet->pHeadF);
+  n += tGetDataFile(p + n, pSet->pDataF);
+  n += tGetLastFile(p + n, pSet->pLastF);
+  n += tGetSmaFile(p + n, pSet->pSmaF);
 
   return n;
 }
 
 // SDelFile ===============================================
 void tsdbDelFileName(STsdb *pTsdb, SDelFile *pFile, char fname[]) {
-  STfs *pTfs = pTsdb->pVnode->pTfs;
-
-  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%dver%" PRId64 "%s", tfsGetPrimaryPath(pTfs), TD_DIRSEP, pTsdb->path,
-           TD_DIRSEP, TD_VID(pTsdb->pVnode), pFile->commitID, ".del");
+  snprintf(fname, TSDB_FILENAME_LEN - 1, "%s%s%s%sv%dver%" PRId64 "%s", tfsGetPrimaryPath(pTsdb->pVnode->pTfs),
+           TD_DIRSEP, pTsdb->path, TD_DIRSEP, TD_VID(pTsdb->pVnode), pFile->commitID, ".del");
 }
 
 int32_t tPutDelFile(uint8_t *p, SDelFile *pDelFile) {

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

@@ -93,7 +93,11 @@ static int32_t tbDataPCmprFn(const void *p1, const void *p2) {
 }
 void tsdbGetTbDataFromMemTable(SMemTable *pMemTable, tb_uid_t suid, tb_uid_t uid, STbData **ppTbData) {
   STbData *pTbData = &(STbData){.suid = suid, .uid = uid};
-  void    *p = taosArraySearch(pMemTable->aTbData, &pTbData, tbDataPCmprFn, TD_EQ);
+
+  taosRLockLatch(&pMemTable->latch);
+  void *p = taosArraySearch(pMemTable->aTbData, &pTbData, tbDataPCmprFn, TD_EQ);
+  taosRUnLockLatch(&pMemTable->latch);
+
   *ppTbData = p ? *(STbData **)p : NULL;
 }
 
@@ -363,10 +367,13 @@ static int32_t tsdbGetOrCreateTbData(SMemTable *pMemTable, tb_uid_t suid, tb_uid
 
   void *p;
   if (idx < 0) {
-    p = taosArrayPush(pMemTable->aTbData, &pTbData);
-  } else {
-    p = taosArrayInsert(pMemTable->aTbData, idx, &pTbData);
+    idx = taosArrayGetSize(pMemTable->aTbData);
   }
+
+  taosWLockLatch(&pMemTable->latch);
+  p = taosArrayInsert(pMemTable->aTbData, idx, &pTbData);
+  taosWUnLockLatch(&pMemTable->latch);
+
   if (p == NULL) {
     code = TSDB_CODE_OUT_OF_MEMORY;
     goto _err;
@@ -605,46 +612,3 @@ void tsdbUnrefMemTable(SMemTable *pMemTable) {
     tsdbMemTableDestroy(pMemTable);
   }
 }
-
-int32_t tsdbTakeMemSnapshot(STsdb *pTsdb, SMemTable **ppMem, SMemTable **ppIMem) {
-  int32_t code = 0;
-
-  // lock
-  code = taosThreadRwlockRdlock(&pTsdb->rwLock);
-  if (code) {
-    code = TAOS_SYSTEM_ERROR(code);
-    goto _exit;
-  }
-
-  // take snapshot
-  *ppMem = pTsdb->mem;
-  *ppIMem = pTsdb->imem;
-
-  if (*ppMem) {
-    tsdbRefMemTable(*ppMem);
-  }
-
-  if (*ppIMem) {
-    tsdbRefMemTable(*ppIMem);
-  }
-
-  // unlock
-  code = taosThreadRwlockUnlock(&pTsdb->rwLock);
-  if (code) {
-    code = TAOS_SYSTEM_ERROR(code);
-    goto _exit;
-  }
-
-_exit:
-  return code;
-}
-
-void tsdbUntakeMemSnapshot(STsdb *pTsdb, SMemTable *pMem, SMemTable *pIMem) {
-  if (pMem) {
-    tsdbUnrefMemTable(pMem);
-  }
-
-  if (pIMem) {
-    tsdbUnrefMemTable(pIMem);
-  }
-}
\ No newline at end of file

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

@@ -66,7 +66,7 @@ int tsdbOpen(SVnode *pVnode, STsdb **ppTsdb, const char *dir, STsdbKeepCfg *pKee
   tfsMkdir(pVnode->pTfs, pTsdb->path);
 
   // open tsdb
-  if (tsdbFSOpen(pTsdb, &pTsdb->pFS) < 0) {
+  if (tsdbFSOpen(pTsdb) < 0) {
     goto _err;
   }
 
@@ -88,7 +88,7 @@ _err:
 int tsdbClose(STsdb **pTsdb) {
   if (*pTsdb) {
     taosThreadRwlockDestroy(&(*pTsdb)->rwLock);
-    tsdbFSClose((*pTsdb)->pFS);
+    tsdbFSClose(*pTsdb);
     tsdbCloseCache((*pTsdb)->lruCache);
     taosMemoryFreeClear(*pTsdb);
   }

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

@@ -118,8 +118,7 @@ struct STsdbReader {
   char*              idStr;  // query info handle, for debug purpose
   int32_t            type;   // query type: 1. retrieve all data blocks, 2. retrieve direct prev|next rows
   SBlockLoadSuppInfo suppInfo;
-  SMemTable*         pMem;
-  SMemTable*         pIMem;
+  STsdbReadSnap*     pReadSnap;
 
   SIOCostSummary cost;
   STSchema*      pSchema;
@@ -275,20 +274,18 @@ static void limitOutputBufferSize(const SQueryTableDataCond* pCond, int32_t* cap
 }
 
 // init file iterator
-static int32_t initFilesetIterator(SFilesetIter* pIter, const STsdbFSState* pFState, int32_t order, const char* idstr) {
-  size_t numOfFileset = taosArrayGetSize(pFState->aDFileSet);
+static int32_t initFilesetIterator(SFilesetIter* pIter, SArray* aDFileSet, int32_t order, const char* idstr) {
+  size_t numOfFileset = taosArrayGetSize(aDFileSet);
 
   pIter->index = ASCENDING_TRAVERSE(order) ? -1 : numOfFileset;
   pIter->order = order;
-  pIter->pFileList = taosArrayDup(pFState->aDFileSet);
+  pIter->pFileList = aDFileSet;
   pIter->numOfFiles = numOfFileset;
 
   tsdbDebug("init fileset iterator, total files:%d %s", pIter->numOfFiles, idstr);
   return TSDB_CODE_SUCCESS;
 }
 
-static void cleanupFilesetIterator(SFilesetIter* pIter) { taosArrayDestroy(pIter->pFileList); }
-
 static bool filesetIteratorNext(SFilesetIter* pIter, STsdbReader* pReader) {
   bool    asc = ASCENDING_TRAVERSE(pIter->order);
   int32_t step = asc ? 1 : -1;
@@ -788,11 +785,11 @@ static int32_t copyBlockDataToSDataBlock(STsdbReader* pReader, STableBlockScanIn
         doCopyColVal(pColData, rowIndex++, i, &cv, pSupInfo);
       }
       colIndex += 1;
+      ASSERT(rowIndex == remain);
     } else {  // the specified column does not exist in file block, fill with null data
       colDataAppendNNULL(pColData, 0, remain);
     }
 
-    ASSERT(rowIndex == remain);
     i += 1;
   }
 
@@ -1881,8 +1878,8 @@ static int32_t initMemDataIterator(STableBlockScanInfo* pBlockScanInfo, STsdbRea
   int32_t backward = (!ASCENDING_TRAVERSE(pReader->order));
 
   STbData* d = NULL;
-  if (pReader->pMem != NULL) {
-    tsdbGetTbDataFromMemTable(pReader->pMem, pReader->suid, pBlockScanInfo->uid, &d);
+  if (pReader->pReadSnap->pMem != NULL) {
+    tsdbGetTbDataFromMemTable(pReader->pReadSnap->pMem, pReader->suid, pBlockScanInfo->uid, &d);
     if (d != NULL) {
       code = tsdbTbDataIterCreate(d, &startKey, backward, &pBlockScanInfo->iter.iter);
       if (code == TSDB_CODE_SUCCESS) {
@@ -1902,8 +1899,8 @@ static int32_t initMemDataIterator(STableBlockScanInfo* pBlockScanInfo, STsdbRea
   }
 
   STbData* di = NULL;
-  if (pReader->pIMem != NULL) {
-    tsdbGetTbDataFromMemTable(pReader->pIMem, pReader->suid, pBlockScanInfo->uid, &di);
+  if (pReader->pReadSnap->pIMem != NULL) {
+    tsdbGetTbDataFromMemTable(pReader->pReadSnap->pIMem, pReader->suid, pBlockScanInfo->uid, &di);
     if (di != NULL) {
       code = tsdbTbDataIterCreate(di, &startKey, backward, &pBlockScanInfo->iiter.iter);
       if (code == TSDB_CODE_SUCCESS) {
@@ -1939,7 +1936,7 @@ int32_t initDelSkylineIterator(STableBlockScanInfo* pBlockScanInfo, STsdbReader*
 
   SArray* pDelData = taosArrayInit(4, sizeof(SDelData));
 
-  SDelFile* pDelFile = tsdbFSStateGetDelFile(pTsdb->pFS->cState);
+  SDelFile* pDelFile = pReader->pReadSnap->fs.pDelFile;
   if (pDelFile) {
     SDelFReader* pDelFReader = NULL;
     code = tsdbDelFReaderOpen(&pDelFReader, pDelFile, pTsdb, NULL);
@@ -2836,8 +2833,10 @@ int32_t tsdbReaderOpen(SVnode* pVnode, SQueryTableDataCond* pCond, SArray* pTabl
 
   SDataBlockIter* pBlockIter = &pReader->status.blockIter;
 
-  STsdbFSState* pFState = pReader->pTsdb->pFS->cState;
-  initFilesetIterator(&pReader->status.fileIter, pFState, pReader->order, pReader->idStr);
+  code = tsdbTakeReadSnap(pReader->pTsdb, &pReader->pReadSnap);
+  if (code) goto _err;
+
+  initFilesetIterator(&pReader->status.fileIter, (*ppReader)->pReadSnap->fs.aDFileSet, pReader->order, pReader->idStr);
   resetDataBlockIterator(&pReader->status.blockIter, pReader->order);
 
   // no data in files, let's try buffer in memory
@@ -2850,8 +2849,6 @@ int32_t tsdbReaderOpen(SVnode* pVnode, SQueryTableDataCond* pCond, SArray* pTabl
     }
   }
 
-  tsdbTakeMemSnapshot(pReader->pTsdb, &pReader->pMem, &pReader->pIMem);
-
   tsdbDebug("%p total numOfTable:%d in this query %s", pReader, numOfTables, pReader->idStr);
   return code;
 
@@ -2867,7 +2864,7 @@ void tsdbReaderClose(STsdbReader* pReader) {
 
   SBlockLoadSuppInfo* pSupInfo = &pReader->suppInfo;
 
-  tsdbUntakeMemSnapshot(pReader->pTsdb, pReader->pMem, pReader->pIMem);
+  tsdbUntakeReadSnap(pReader->pTsdb, pReader->pReadSnap);
 
   taosMemoryFreeClear(pSupInfo->plist);
   taosMemoryFree(pSupInfo->colIds);
@@ -2880,7 +2877,6 @@ void tsdbReaderClose(STsdbReader* pReader) {
   }
   taosMemoryFree(pSupInfo->buildBuf);
 
-  cleanupFilesetIterator(&pReader->status.fileIter);
   cleanupDataBlockIterator(&pReader->status.blockIter);
   destroyBlockScanInfo(pReader->status.pTableMap);
   blockDataDestroy(pReader->pResBlock);
@@ -3087,8 +3083,7 @@ int32_t tsdbReaderReset(STsdbReader* pReader, SQueryTableDataCond* pCond) {
 
   tsdbDataFReaderClose(&pReader->pFileReader);
 
-  STsdbFSState* pFState = pReader->pTsdb->pFS->cState;
-  initFilesetIterator(&pReader->status.fileIter, pFState, pReader->order, pReader->idStr);
+  initFilesetIterator(&pReader->status.fileIter, pReader->pReadSnap->fs.aDFileSet, pReader->order, pReader->idStr);
   resetDataBlockIterator(&pReader->status.blockIter, pReader->order);
   resetDataBlockScanInfo(pReader->status.pTableMap);
 
@@ -3250,3 +3245,68 @@ int32_t tsdbGetTableSchema(SVnode* pVnode, int64_t uid, STSchema** pSchema, int6
 
   return TSDB_CODE_SUCCESS;
 }
+
+int32_t tsdbTakeReadSnap(STsdb* pTsdb, STsdbReadSnap** ppSnap) {
+  int32_t code = 0;
+
+  // alloc
+  *ppSnap = (STsdbReadSnap*)taosMemoryCalloc(1, sizeof(STsdbReadSnap));
+  if (*ppSnap == NULL) {
+    code = TSDB_CODE_OUT_OF_MEMORY;
+    goto _exit;
+  }
+
+  // lock
+  code = taosThreadRwlockRdlock(&pTsdb->rwLock);
+  if (code) {
+    code = TAOS_SYSTEM_ERROR(code);
+    goto _exit;
+  }
+
+  // take snapshot
+  (*ppSnap)->pMem = pTsdb->mem;
+  (*ppSnap)->pIMem = pTsdb->imem;
+
+  if ((*ppSnap)->pMem) {
+    tsdbRefMemTable((*ppSnap)->pMem);
+  }
+
+  if ((*ppSnap)->pIMem) {
+    tsdbRefMemTable((*ppSnap)->pIMem);
+  }
+
+  // fs
+  code = tsdbFSRef(pTsdb, &(*ppSnap)->fs);
+  if (code) {
+    taosThreadRwlockUnlock(&pTsdb->rwLock);
+    goto _exit;
+  }
+
+  // unlock
+  code = taosThreadRwlockUnlock(&pTsdb->rwLock);
+  if (code) {
+    code = TAOS_SYSTEM_ERROR(code);
+    goto _exit;
+  }
+
+  tsdbTrace("vgId:%d take read snapshot", TD_VID(pTsdb->pVnode));
+_exit:
+  return code;
+}
+
+void tsdbUntakeReadSnap(STsdb* pTsdb, STsdbReadSnap* pSnap) {
+  if (pSnap) {
+    if (pSnap->pMem) {
+      tsdbUnrefMemTable(pSnap->pMem);
+    }
+
+    if (pSnap->pIMem) {
+      tsdbUnrefMemTable(pSnap->pIMem);
+    }
+
+    tsdbFSUnref(pTsdb, &pSnap->fs);
+    taosMemoryFree(pSnap);
+  }
+
+  tsdbTrace("vgId:%d untake read snapshot", TD_VID(pTsdb->pVnode));
+}

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

@@ -459,7 +459,7 @@ int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pS
 
   // open impl
   // head
-  tsdbDataFileName(pTsdb, pSet, TSDB_HEAD_FILE, fname);
+  tsdbHeadFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pHeadF, fname);
   pReader->pHeadFD = taosOpenFile(fname, TD_FILE_READ);
   if (pReader->pHeadFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -467,7 +467,7 @@ int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pS
   }
 
   // data
-  tsdbDataFileName(pTsdb, pSet, TSDB_DATA_FILE, fname);
+  tsdbDataFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pDataF, fname);
   pReader->pDataFD = taosOpenFile(fname, TD_FILE_READ);
   if (pReader->pDataFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -475,7 +475,7 @@ int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pS
   }
 
   // last
-  tsdbDataFileName(pTsdb, pSet, TSDB_LAST_FILE, fname);
+  tsdbLastFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pLastF, fname);
   pReader->pLastFD = taosOpenFile(fname, TD_FILE_READ);
   if (pReader->pLastFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -483,7 +483,7 @@ int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pS
   }
 
   // sma
-  tsdbDataFileName(pTsdb, pSet, TSDB_SMA_FILE, fname);
+  tsdbSmaFileName(pTsdb, pSet->diskId, pSet->fid, pSet->pSmaF, fname);
   pReader->pSmaFD = taosOpenFile(fname, TD_FILE_READ);
   if (pReader->pSmaFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -536,8 +536,8 @@ _err:
 
 int32_t tsdbReadBlockIdx(SDataFReader *pReader, SArray *aBlockIdx, uint8_t **ppBuf) {
   int32_t   code = 0;
-  int64_t   offset = pReader->pSet->fHead.offset;
-  int64_t   size = pReader->pSet->fHead.size - offset;
+  int64_t   offset = pReader->pSet->pHeadF->offset;
+  int64_t   size = pReader->pSet->pHeadF->size - offset;
   uint8_t  *pBuf = NULL;
   int64_t   n;
   uint32_t  delimiter;
@@ -1211,17 +1211,6 @@ _err:
 }
 
 // SDataFWriter ====================================================
-struct SDataFWriter {
-  STsdb    *pTsdb;
-  SDFileSet wSet;
-  TdFilePtr pHeadFD;
-  TdFilePtr pDataFD;
-  TdFilePtr pLastFD;
-  TdFilePtr pSmaFD;
-};
-
-SDFileSet *tsdbDataFWriterGetWSet(SDataFWriter *pWriter) { return &pWriter->wSet; }
-
 int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pSet) {
   int32_t       code = 0;
   int32_t       flag;
@@ -1237,12 +1226,20 @@ int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pS
     goto _err;
   }
   pWriter->pTsdb = pTsdb;
-  pWriter->wSet = *pSet;
-  pSet = &pWriter->wSet;
+  pWriter->wSet = (SDFileSet){.diskId = pSet->diskId,
+                              .fid = pSet->fid,
+                              .pHeadF = &pWriter->fHead,
+                              .pDataF = &pWriter->fData,
+                              .pLastF = &pWriter->fLast,
+                              .pSmaF = &pWriter->fSma};
+  pWriter->fHead = *pSet->pHeadF;
+  pWriter->fData = *pSet->pDataF;
+  pWriter->fLast = *pSet->pLastF;
+  pWriter->fSma = *pSet->pSmaF;
 
   // head
   flag = TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC;
-  tsdbDataFileName(pTsdb, pSet, TSDB_HEAD_FILE, fname);
+  tsdbHeadFileName(pTsdb, pWriter->wSet.diskId, pWriter->wSet.fid, &pWriter->fHead, fname);
   pWriter->pHeadFD = taosOpenFile(fname, flag);
   if (pWriter->pHeadFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -1257,28 +1254,28 @@ int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pS
 
   ASSERT(n == TSDB_FHDR_SIZE);
 
-  pSet->fHead.size += TSDB_FHDR_SIZE;
+  pWriter->fHead.size += TSDB_FHDR_SIZE;
 
   // data
-  if (pSet->fData.size == 0) {
+  if (pWriter->fData.size == 0) {
     flag = TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC;
   } else {
     flag = TD_FILE_WRITE;
   }
-  tsdbDataFileName(pTsdb, pSet, TSDB_DATA_FILE, fname);
+  tsdbDataFileName(pTsdb, pWriter->wSet.diskId, pWriter->wSet.fid, &pWriter->fData, fname);
   pWriter->pDataFD = taosOpenFile(fname, flag);
   if (pWriter->pDataFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
   }
-  if (pSet->fData.size == 0) {
+  if (pWriter->fData.size == 0) {
     n = taosWriteFile(pWriter->pDataFD, hdr, TSDB_FHDR_SIZE);
     if (n < 0) {
       code = TAOS_SYSTEM_ERROR(errno);
       goto _err;
     }
 
-    pSet->fData.size += TSDB_FHDR_SIZE;
+    pWriter->fData.size += TSDB_FHDR_SIZE;
   } else {
     n = taosLSeekFile(pWriter->pDataFD, 0, SEEK_END);
     if (n < 0) {
@@ -1286,29 +1283,29 @@ int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pS
       goto _err;
     }
 
-    ASSERT(n == pSet->fData.size);
+    ASSERT(n == pWriter->fData.size);
   }
 
   // last
-  if (pSet->fLast.size == 0) {
+  if (pWriter->fLast.size == 0) {
     flag = TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC;
   } else {
     flag = TD_FILE_WRITE;
   }
-  tsdbDataFileName(pTsdb, pSet, TSDB_LAST_FILE, fname);
+  tsdbLastFileName(pTsdb, pWriter->wSet.diskId, pWriter->wSet.fid, &pWriter->fLast, fname);
   pWriter->pLastFD = taosOpenFile(fname, flag);
   if (pWriter->pLastFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
   }
-  if (pSet->fLast.size == 0) {
+  if (pWriter->fLast.size == 0) {
     n = taosWriteFile(pWriter->pLastFD, hdr, TSDB_FHDR_SIZE);
     if (n < 0) {
       code = TAOS_SYSTEM_ERROR(errno);
       goto _err;
     }
 
-    pSet->fLast.size += TSDB_FHDR_SIZE;
+    pWriter->fLast.size += TSDB_FHDR_SIZE;
   } else {
     n = taosLSeekFile(pWriter->pLastFD, 0, SEEK_END);
     if (n < 0) {
@@ -1316,29 +1313,29 @@ int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pS
       goto _err;
     }
 
-    ASSERT(n == pSet->fLast.size);
+    ASSERT(n == pWriter->fLast.size);
   }
 
   // sma
-  if (pSet->fSma.size == 0) {
+  if (pWriter->fSma.size == 0) {
     flag = TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC;
   } else {
     flag = TD_FILE_WRITE;
   }
-  tsdbDataFileName(pTsdb, pSet, TSDB_SMA_FILE, fname);
+  tsdbSmaFileName(pTsdb, pWriter->wSet.diskId, pWriter->wSet.fid, &pWriter->fSma, fname);
   pWriter->pSmaFD = taosOpenFile(fname, flag);
   if (pWriter->pSmaFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
   }
-  if (pSet->fSma.size == 0) {
+  if (pWriter->fSma.size == 0) {
     n = taosWriteFile(pWriter->pSmaFD, hdr, TSDB_FHDR_SIZE);
     if (n < 0) {
       code = TAOS_SYSTEM_ERROR(errno);
       goto _err;
     }
 
-    pSet->fSma.size += TSDB_FHDR_SIZE;
+    pWriter->fSma.size += TSDB_FHDR_SIZE;
   } else {
     n = taosLSeekFile(pWriter->pSmaFD, 0, SEEK_END);
     if (n < 0) {
@@ -1346,7 +1343,7 @@ int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pS
       goto _err;
     }
 
-    ASSERT(n == pSet->fSma.size);
+    ASSERT(n == pWriter->fSma.size);
   }
 
   *ppWriter = pWriter;
@@ -1418,22 +1415,76 @@ _err:
 
 int32_t tsdbUpdateDFileSetHeader(SDataFWriter *pWriter) {
   int32_t code = 0;
+  int64_t n;
+  char    hdr[TSDB_FHDR_SIZE];
 
   // head ==============
-  code = tsdbUpdateDFileHdr(pWriter->pHeadFD, &pWriter->wSet, TSDB_HEAD_FILE);
-  if (code) goto _err;
+  memset(hdr, 0, TSDB_FHDR_SIZE);
+  tPutHeadFile(hdr, &pWriter->fHead);
+  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
+
+  n = taosLSeekFile(pWriter->pHeadFD, 0, SEEK_SET);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosWriteFile(pWriter->pHeadFD, hdr, TSDB_FHDR_SIZE);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
 
   // data ==============
-  code = tsdbUpdateDFileHdr(pWriter->pHeadFD, &pWriter->wSet, TSDB_DATA_FILE);
-  if (code) goto _err;
+  memset(hdr, 0, TSDB_FHDR_SIZE);
+  tPutDataFile(hdr, &pWriter->fData);
+  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
+
+  n = taosLSeekFile(pWriter->pDataFD, 0, SEEK_SET);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosWriteFile(pWriter->pDataFD, hdr, TSDB_FHDR_SIZE);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
 
   // last ==============
-  code = tsdbUpdateDFileHdr(pWriter->pHeadFD, &pWriter->wSet, TSDB_LAST_FILE);
-  if (code) goto _err;
+  memset(hdr, 0, TSDB_FHDR_SIZE);
+  tPutLastFile(hdr, &pWriter->fLast);
+  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
+
+  n = taosLSeekFile(pWriter->pLastFD, 0, SEEK_SET);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosWriteFile(pWriter->pLastFD, hdr, TSDB_FHDR_SIZE);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
 
   // sma ==============
-  code = tsdbUpdateDFileHdr(pWriter->pHeadFD, &pWriter->wSet, TSDB_SMA_FILE);
-  if (code) goto _err;
+  memset(hdr, 0, TSDB_FHDR_SIZE);
+  tPutSmaFile(hdr, &pWriter->fSma);
+  taosCalcChecksumAppend(0, hdr, TSDB_FHDR_SIZE);
+
+  n = taosLSeekFile(pWriter->pSmaFD, 0, SEEK_SET);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosWriteFile(pWriter->pSmaFD, hdr, TSDB_FHDR_SIZE);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
 
   return code;
 
@@ -1444,7 +1495,7 @@ _err:
 
 int32_t tsdbWriteBlockIdx(SDataFWriter *pWriter, SArray *aBlockIdx, uint8_t **ppBuf) {
   int32_t    code = 0;
-  SHeadFile *pHeadFile = &pWriter->wSet.fHead;
+  SHeadFile *pHeadFile = &pWriter->fHead;
   uint8_t   *pBuf = NULL;
   int64_t    size;
   int64_t    n;
@@ -1494,7 +1545,7 @@ _err:
 
 int32_t tsdbWriteBlock(SDataFWriter *pWriter, SMapData *mBlock, uint8_t **ppBuf, SBlockIdx *pBlockIdx) {
   int32_t       code = 0;
-  SHeadFile    *pHeadFile = &pWriter->wSet.fHead;
+  SHeadFile    *pHeadFile = &pWriter->fHead;
   SBlockDataHdr hdr = {.delimiter = TSDB_FILE_DLMT, .suid = pBlockIdx->suid, .uid = pBlockIdx->uid};
   uint8_t      *pBuf = NULL;
   int64_t       size;
@@ -1831,9 +1882,9 @@ int32_t tsdbWriteBlockData(SDataFWriter *pWriter, SBlockData *pBlockData, uint8_
   pSubBlock->nRow = pBlockData->nRow;
   pSubBlock->cmprAlg = cmprAlg;
   if (pBlock->last) {
-    pSubBlock->offset = pWriter->wSet.fLast.size;
+    pSubBlock->offset = pWriter->fLast.size;
   } else {
-    pSubBlock->offset = pWriter->wSet.fData.size;
+    pSubBlock->offset = pWriter->fData.size;
   }
 
   // ======================= BLOCK DATA =======================
@@ -1881,9 +1932,9 @@ int32_t tsdbWriteBlockData(SDataFWriter *pWriter, SBlockData *pBlockData, uint8_
 
   pSubBlock->szBlock = pSubBlock->szBlockCol + sizeof(TSCKSUM) + nData;
   if (pBlock->last) {
-    pWriter->wSet.fLast.size += pSubBlock->szBlock;
+    pWriter->fLast.size += pSubBlock->szBlock;
   } else {
-    pWriter->wSet.fData.size += pSubBlock->szBlock;
+    pWriter->fData.size += pSubBlock->szBlock;
   }
 
   // ======================= BLOCK SMA =======================
@@ -1896,8 +1947,8 @@ int32_t tsdbWriteBlockData(SDataFWriter *pWriter, SBlockData *pBlockData, uint8_
   if (code) goto _err;
 
   if (pSubBlock->nSma > 0) {
-    pSubBlock->sOffset = pWriter->wSet.fSma.size;
-    pWriter->wSet.fSma.size += (sizeof(SColumnDataAgg) * pSubBlock->nSma + sizeof(TSCKSUM));
+    pSubBlock->sOffset = pWriter->fSma.size;
+    pWriter->fSma.size += (sizeof(SColumnDataAgg) * pSubBlock->nSma + sizeof(TSCKSUM));
   }
 
 _exit:
@@ -1924,8 +1975,8 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
   char      fNameTo[TSDB_FILENAME_LEN];
 
   // head
-  tsdbDataFileName(pTsdb, pSetFrom, TSDB_HEAD_FILE, fNameFrom);
-  tsdbDataFileName(pTsdb, pSetTo, TSDB_HEAD_FILE, fNameTo);
+  tsdbHeadFileName(pTsdb, pSetFrom->diskId, pSetFrom->fid, pSetFrom->pHeadF, fNameFrom);
+  tsdbHeadFileName(pTsdb, pSetTo->diskId, pSetTo->fid, pSetTo->pHeadF, fNameTo);
 
   pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
   if (pOutFD == NULL) {
@@ -1939,7 +1990,7 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
     goto _err;
   }
 
-  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fHead.size);
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->pHeadF->size);
   if (n < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
@@ -1948,8 +1999,8 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
   taosCloseFile(&PInFD);
 
   // data
-  tsdbDataFileName(pTsdb, pSetFrom, TSDB_DATA_FILE, fNameFrom);
-  tsdbDataFileName(pTsdb, pSetTo, TSDB_DATA_FILE, fNameTo);
+  tsdbDataFileName(pTsdb, pSetFrom->diskId, pSetFrom->fid, pSetFrom->pDataF, fNameFrom);
+  tsdbDataFileName(pTsdb, pSetTo->diskId, pSetTo->fid, pSetTo->pDataF, fNameTo);
 
   pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
   if (pOutFD == NULL) {
@@ -1963,7 +2014,7 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
     goto _err;
   }
 
-  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fData.size);
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->pDataF->size);
   if (n < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
@@ -1972,8 +2023,9 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
   taosCloseFile(&PInFD);
 
   // last
-  tsdbDataFileName(pTsdb, pSetFrom, TSDB_LAST_FILE, fNameFrom);
-  tsdbDataFileName(pTsdb, pSetTo, TSDB_LAST_FILE, fNameTo);
+  tsdbLastFileName(pTsdb, pSetFrom->diskId, pSetFrom->fid, pSetFrom->pLastF, fNameFrom);
+  tsdbLastFileName(pTsdb, pSetTo->diskId, pSetTo->fid, pSetTo->pLastF, fNameTo);
+
   pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
   if (pOutFD == NULL) {
     code = TAOS_SYSTEM_ERROR(errno);
@@ -1986,7 +2038,7 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
     goto _err;
   }
 
-  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fLast.size);
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->pLastF->size);
   if (n < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
@@ -1995,8 +2047,8 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
   taosCloseFile(&PInFD);
 
   // sma
-  tsdbDataFileName(pTsdb, pSetFrom, TSDB_SMA_FILE, fNameFrom);
-  tsdbDataFileName(pTsdb, pSetTo, TSDB_SMA_FILE, fNameTo);
+  tsdbSmaFileName(pTsdb, pSetFrom->diskId, pSetFrom->fid, pSetFrom->pSmaF, fNameFrom);
+  tsdbSmaFileName(pTsdb, pSetTo->diskId, pSetTo->fid, pSetTo->pSmaF, fNameTo);
 
   pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
   if (pOutFD == NULL) {
@@ -2010,7 +2062,7 @@ int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
     goto _err;
   }
 
-  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fSma.size);
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->pSmaF->size);
   if (n < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;

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

@@ -15,90 +15,99 @@
 
 #include "tsdb.h"
 
-static int32_t tsdbDoRetentionImpl(STsdb *pTsdb, int64_t now, int8_t try, int8_t *canDo) {
-  int32_t       code = 0;
-  STsdbFSState *pState;
-
-  if (try) {
-    pState = pTsdb->pFS->cState;
-    *canDo = 0;
-  } else {
-    pState = pTsdb->pFS->nState;
-  }
-
-  for (int32_t iSet = 0; iSet < taosArrayGetSize(pState->aDFileSet); iSet++) {
-    SDFileSet *pDFileSet = (SDFileSet *)taosArrayGet(pState->aDFileSet, iSet);
-    int32_t    expLevel = tsdbFidLevel(pDFileSet->fid, &pTsdb->keepCfg, now);
+static bool tsdbShouldDoRetention(STsdb *pTsdb, int64_t now) {
+  for (int32_t iSet = 0; iSet < taosArrayGetSize(pTsdb->fs.aDFileSet); iSet++) {
+    SDFileSet *pSet = (SDFileSet *)taosArrayGet(pTsdb->fs.aDFileSet, iSet);
+    int32_t    expLevel = tsdbFidLevel(pSet->fid, &pTsdb->keepCfg, now);
     SDiskID    did;
 
-    // check
-    if (expLevel == pDFileSet->diskId.id) continue;
+    if (expLevel == pSet->diskId.level) continue;
 
-    // delete or move
     if (expLevel < 0) {
-      if (try) {
-        *canDo = 1;
-      } else {
-        tsdbFSStateDeleteDFileSet(pState, pDFileSet->fid);
-        iSet--;
-      }
+      return true;
     } else {
-      // alloc
       if (tfsAllocDisk(pTsdb->pVnode->pTfs, expLevel, &did) < 0) {
-        code = terrno;
-        goto _exit;
+        return false;
       }
 
-      if (did.level == pDFileSet->diskId.level) continue;
+      if (did.level == pSet->diskId.level) continue;
 
-      if (try) {
-        *canDo = 1;
-      } else {
-        // copy the file to new disk
-
-        SDFileSet nDFileSet = *pDFileSet;
-        nDFileSet.diskId = did;
-
-        tfsMkdirRecurAt(pTsdb->pVnode->pTfs, pTsdb->path, did);
-
-        code = tsdbDFileSetCopy(pTsdb, pDFileSet, &nDFileSet);
-        if (code) goto _exit;
-
-        code = tsdbFSStateUpsertDFileSet(pState, &nDFileSet);
-        if (code) goto _exit;
-      }
+      return true;
     }
   }
 
-_exit:
-  return code;
+  return false;
 }
 
 int32_t tsdbDoRetention(STsdb *pTsdb, int64_t now) {
   int32_t code = 0;
-  int8_t  canDo;
-
-  // try
-  tsdbDoRetentionImpl(pTsdb, now, 1, &canDo);
-  if (!canDo) goto _exit;
 
-  // begin
-  code = tsdbFSBegin(pTsdb->pFS);
-  if (code) goto _err;
+  if (!tsdbShouldDoRetention(pTsdb, now)) {
+    return code;
+  }
 
   // do retention
-  code = tsdbDoRetentionImpl(pTsdb, now, 0, NULL);
+  STsdbFS fs;
+
+  code = tsdbFSCopy(pTsdb, &fs);
   if (code) goto _err;
 
-  // commit
-  code = tsdbFSCommit(pTsdb->pFS);
+  for (int32_t iSet = 0; iSet < taosArrayGetSize(fs.aDFileSet); iSet++) {
+    SDFileSet *pSet = (SDFileSet *)taosArrayGet(pTsdb->fs.aDFileSet, iSet);
+    int32_t    expLevel = tsdbFidLevel(pSet->fid, &pTsdb->keepCfg, now);
+    SDiskID    did;
+
+    if (expLevel < 0) {
+      taosMemoryFree(pSet->pHeadF);
+      taosMemoryFree(pSet->pDataF);
+      taosMemoryFree(pSet->pLastF);
+      taosMemoryFree(pSet->pSmaF);
+      taosArrayRemove(fs.aDFileSet, iSet);
+      iSet--;
+    } else {
+      if (tfsAllocDisk(pTsdb->pVnode->pTfs, expLevel, &did) < 0) {
+        code = terrno;
+        goto _exit;
+      }
+
+      if (did.level == pSet->diskId.level) continue;
+
+      // copy file to new disk (todo)
+      SDFileSet fSet = *pSet;
+      fSet.diskId = did;
+
+      code = tsdbDFileSetCopy(pTsdb, pSet, &fSet);
+      if (code) goto _err;
+
+      code = tsdbFSUpsertFSet(&fs, &fSet);
+      if (code) goto _err;
+    }
+
+    /* code */
+  }
+
+  // do change fs
+  code = tsdbFSCommit1(pTsdb, &fs);
   if (code) goto _err;
 
+  taosThreadRwlockWrlock(&pTsdb->rwLock);
+
+  code = tsdbFSCommit2(pTsdb, &fs);
+  if (code) {
+    taosThreadRwlockUnlock(&pTsdb->rwLock);
+    goto _err;
+  }
+
+  taosThreadRwlockUnlock(&pTsdb->rwLock);
+
+  tsdbFSDestroy(&fs);
+
 _exit:
   return code;
 
 _err:
   tsdbError("vgId:%d tsdb do retention failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
-  tsdbFSRollback(pTsdb->pFS);
+  ASSERT(0);
+  // tsdbFSRollback(pTsdb->pFS);
   return code;
 }
\ No newline at end of file

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

@@ -20,6 +20,7 @@ struct STsdbSnapReader {
   STsdb*  pTsdb;
   int64_t sver;
   int64_t ever;
+  STsdbFS fs;
   // for data file
   int8_t        dataDone;
   int32_t       fid;
@@ -45,7 +46,8 @@ static int32_t tsdbSnapReadData(STsdbSnapReader* pReader, uint8_t** ppData) {
 
   while (true) {
     if (pReader->pDataFReader == NULL) {
-      SDFileSet* pSet = tsdbFSStateGetDFileSet(pTsdb->pFS->cState, pReader->fid, TD_GT);
+      SDFileSet* pSet =
+          taosArraySearch(pReader->fs.aDFileSet, &(SDFileSet){.fid = pReader->fid}, tDFileSetCmprFn, TD_GT);
 
       if (pSet == NULL) goto _exit;
 
@@ -159,7 +161,7 @@ _err:
 static int32_t tsdbSnapReadDel(STsdbSnapReader* pReader, uint8_t** ppData) {
   int32_t   code = 0;
   STsdb*    pTsdb = pReader->pTsdb;
-  SDelFile* pDelFile = pTsdb->pFS->cState->pDelFile;
+  SDelFile* pDelFile = pReader->fs.pDelFile;
 
   if (pReader->pDelFReader == NULL) {
     if (pDelFile == NULL) {
@@ -254,6 +256,24 @@ int32_t tsdbSnapReaderOpen(STsdb* pTsdb, int64_t sver, int64_t ever, STsdbSnapRe
   pReader->sver = sver;
   pReader->ever = ever;
 
+  code = taosThreadRwlockRdlock(&pTsdb->rwLock);
+  if (code) {
+    code = TAOS_SYSTEM_ERROR(code);
+    goto _err;
+  }
+
+  code = tsdbFSRef(pTsdb, &pReader->fs);
+  if (code) {
+    taosThreadRwlockUnlock(&pTsdb->rwLock);
+    goto _err;
+  }
+
+  code = taosThreadRwlockUnlock(&pTsdb->rwLock);
+  if (code) {
+    code = TAOS_SYSTEM_ERROR(code);
+    goto _err;
+  }
+
   pReader->fid = INT32_MIN;
   pReader->aBlockIdx = taosArrayInit(0, sizeof(SBlockIdx));
   if (pReader->aBlockIdx == NULL) {
@@ -305,6 +325,8 @@ int32_t tsdbSnapReaderClose(STsdbSnapReader** ppReader) {
   taosArrayDestroy(pReader->aDelIdx);
   taosArrayDestroy(pReader->aDelData);
 
+  tsdbFSUnref(pReader->pTsdb, &pReader->fs);
+
   tsdbInfo("vgId:%d vnode snapshot tsdb reader closed", TD_VID(pReader->pTsdb->pVnode));
 
   taosMemoryFree(pReader);
@@ -358,6 +380,7 @@ struct STsdbSnapWriter {
   STsdb*  pTsdb;
   int64_t sver;
   int64_t ever;
+  STsdbFS fs;
 
   // config
   int32_t minutes;
@@ -798,7 +821,7 @@ static int32_t tsdbSnapWriteDataEnd(STsdbSnapWriter* pWriter) {
   code = tsdbWriteBlockIdx(pWriter->pDataFWriter, pWriter->aBlockIdxW, NULL);
   if (code) goto _err;
 
-  code = tsdbFSStateUpsertDFileSet(pTsdb->pFS->nState, tsdbDataFWriterGetWSet(pWriter->pDataFWriter));
+  code = tsdbFSUpsertFSet(&pWriter->fs, &pWriter->pDataFWriter->wSet);
   if (code) goto _err;
 
   code = tsdbDataFWriterClose(&pWriter->pDataFWriter, 1);
@@ -843,7 +866,7 @@ static int32_t tsdbSnapWriteData(STsdbSnapWriter* pWriter, uint8_t* pData, uint3
     pWriter->fid = fid;
 
     // read
-    SDFileSet* pSet = tsdbFSStateGetDFileSet(pTsdb->pFS->nState, fid, TD_EQ);
+    SDFileSet* pSet = taosArraySearch(pWriter->fs.aDFileSet, &(SDFileSet){.fid = fid}, tDFileSetCmprFn, TD_EQ);
     if (pSet) {
       code = tsdbDataFReaderOpen(&pWriter->pDataFReader, pTsdb, pSet);
       if (code) goto _err;
@@ -863,22 +886,26 @@ static int32_t tsdbSnapWriteData(STsdbSnapWriter* pWriter, uint8_t* pData, uint3
     tBlockDataReset(&pWriter->bDataR);
 
     // write
-    SDFileSet wSet;
+    SHeadFile fHead;
+    SDataFile fData;
+    SLastFile fLast;
+    SSmaFile  fSma;
+    SDFileSet wSet = {.pHeadF = &fHead, .pDataF = &fData, .pLastF = &fLast, .pSmaF = &fSma};
 
     if (pSet) {
-      wSet = (SDFileSet){.diskId = pSet->diskId,
-                         .fid = fid,
-                         .fHead = {.commitID = pWriter->commitID, .offset = 0, .size = 0},
-                         .fData = pSet->fData,
-                         .fLast = {.commitID = pWriter->commitID, .size = 0},
-                         .fSma = pSet->fSma};
+      wSet.diskId = pSet->diskId;
+      wSet.fid = fid;
+      fHead = (SHeadFile){.commitID = pWriter->commitID, .offset = 0, .size = 0};
+      fData = *pSet->pDataF;
+      fLast = (SLastFile){.commitID = pWriter->commitID, .size = 0};
+      fSma = *pSet->pSmaF;
     } else {
-      wSet = (SDFileSet){.diskId = (SDiskID){.level = 0, .id = 0},
-                         .fid = fid,
-                         .fHead = {.commitID = pWriter->commitID, .offset = 0, .size = 0},
-                         .fData = {.commitID = pWriter->commitID, .size = 0},
-                         .fLast = {.commitID = pWriter->commitID, .size = 0},
-                         .fSma = {.commitID = pWriter->commitID, .size = 0}};
+      wSet.diskId = (SDiskID){.level = 0, .id = 0};
+      wSet.fid = fid;
+      fHead = (SHeadFile){.commitID = pWriter->commitID, .offset = 0, .size = 0};
+      fData = (SDataFile){.commitID = pWriter->commitID, .size = 0};
+      fLast = (SLastFile){.commitID = pWriter->commitID, .size = 0};
+      fSma = (SSmaFile){.commitID = pWriter->commitID, .size = 0};
     }
 
     code = tsdbDataFWriterOpen(&pWriter->pDataFWriter, pTsdb, &wSet);
@@ -907,7 +934,7 @@ static int32_t tsdbSnapWriteDel(STsdbSnapWriter* pWriter, uint8_t* pData, uint32
   STsdb*  pTsdb = pWriter->pTsdb;
 
   if (pWriter->pDelFWriter == NULL) {
-    SDelFile* pDelFile = tsdbFSStateGetDelFile(pTsdb->pFS->nState);
+    SDelFile* pDelFile = pWriter->fs.pDelFile;
 
     // reader
     if (pDelFile) {
@@ -1017,7 +1044,7 @@ static int32_t tsdbSnapWriteDelEnd(STsdbSnapWriter* pWriter) {
   code = tsdbUpdateDelFileHdr(pWriter->pDelFWriter);
   if (code) goto _err;
 
-  code = tsdbFSStateUpsertDelFile(pTsdb->pFS->nState, &pWriter->pDelFWriter->fDel);
+  code = tsdbFSUpsertDelFile(&pWriter->fs, &pWriter->pDelFWriter->fDel);
   if (code) goto _err;
 
   code = tsdbDelFWriterClose(&pWriter->pDelFWriter, 1);
@@ -1051,6 +1078,9 @@ int32_t tsdbSnapWriterOpen(STsdb* pTsdb, int64_t sver, int64_t ever, STsdbSnapWr
   pWriter->sver = sver;
   pWriter->ever = ever;
 
+  code = tsdbFSCopy(pTsdb, &pWriter->fs);
+  if (code) goto _err;
+
   // config
   pWriter->minutes = pTsdb->keepCfg.days;
   pWriter->precision = pTsdb->keepCfg.precision;
@@ -1096,9 +1126,6 @@ int32_t tsdbSnapWriterOpen(STsdb* pTsdb, int64_t sver, int64_t ever, STsdbSnapWr
     goto _err;
   }
 
-  code = tsdbFSBegin(pTsdb->pFS);
-  if (code) goto _err;
-
   *ppWriter = pWriter;
   return code;
 
@@ -1113,8 +1140,9 @@ int32_t tsdbSnapWriterClose(STsdbSnapWriter** ppWriter, int8_t rollback) {
   STsdbSnapWriter* pWriter = *ppWriter;
 
   if (rollback) {
-    code = tsdbFSRollback(pWriter->pTsdb->pFS);
-    if (code) goto _err;
+    ASSERT(0);
+    // code = tsdbFSRollback(pWriter->pTsdb->pFS);
+    // if (code) goto _err;
   } else {
     code = tsdbSnapWriteDataEnd(pWriter);
     if (code) goto _err;
@@ -1122,7 +1150,10 @@ int32_t tsdbSnapWriterClose(STsdbSnapWriter** ppWriter, int8_t rollback) {
     code = tsdbSnapWriteDelEnd(pWriter);
     if (code) goto _err;
 
-    code = tsdbFSCommit(pWriter->pTsdb->pFS);
+    code = tsdbFSCommit1(pWriter->pTsdb, &pWriter->fs);
+    if (code) goto _err;
+
+    code = tsdbFSCommit2(pWriter->pTsdb, &pWriter->fs);
     if (code) goto _err;
   }
 

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

@@ -316,7 +316,7 @@ int32_t vnodeProcessFetchMsg(SVnode *pVnode, SRpcMsg *pMsg, SQueueInfo *pInfo) {
     case TDMT_VND_TABLE_CFG:
       return vnodeGetTableCfg(pVnode, pMsg);
     case TDMT_VND_CONSUME:
-      return tqProcessPollReq(pVnode->pTq, pMsg, pInfo->workerId);
+      return tqProcessPollReq(pVnode->pTq, pMsg);
     case TDMT_STREAM_TASK_RUN:
       return tqProcessTaskRunReq(pVnode->pTq, pMsg);
     case TDMT_STREAM_TASK_DISPATCH:
@@ -773,6 +773,7 @@ static int32_t vnodeProcessSubmitReq(SVnode *pVnode, int64_t version, void *pReq
   terrno = TSDB_CODE_SUCCESS;
 
   pRsp->code = 0;
+  pSubmitReq->version = version;
 
 #ifdef TD_DEBUG_PRINT_ROW
   vnodeDebugPrintSubmitMsg(pVnode, pReq, __func__);
@@ -791,7 +792,7 @@ static int32_t vnodeProcessSubmitReq(SVnode *pVnode, int64_t version, void *pReq
 
   submitRsp.pArray = taosArrayInit(msgIter.numOfBlocks, sizeof(SSubmitBlkRsp));
   newTbUids = taosArrayInit(msgIter.numOfBlocks, sizeof(int64_t));
-  if (!submitRsp.pArray) {
+  if (!submitRsp.pArray || !newTbUids) {
     pRsp->code = TSDB_CODE_OUT_OF_MEMORY;
     goto _exit;
   }

source/libs/executor/inc/executorimpl.h

@@ -869,7 +869,7 @@ SOperatorInfo* createDataBlockInfoScanOperator(void* dataReader, SReadHandle* re
                                                SExecTaskInfo* pTaskInfo);
 
 SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhysiNode* pTableScanNode, SNode* pTagCond,
-                                            SExecTaskInfo* pTaskInfo);
+                                            STimeWindowAggSupp* pTwAggSup, SExecTaskInfo* pTaskInfo);
 
 SOperatorInfo* createFillOperatorInfo(SOperatorInfo* downstream, SFillPhysiNode* pPhyFillNode, SExecTaskInfo* pTaskInfo);
 

source/libs/executor/src/executor.c

@@ -120,7 +120,8 @@ int32_t qSetMultiStreamInput(qTaskInfo_t tinfo, const void* pBlocks, size_t numO
   return code;
 }
 
-qTaskInfo_t qCreateQueueExecTaskInfo(void* msg, SReadHandle* readers, int32_t* numOfCols, SSchemaWrapper** pSchemaWrapper) {
+qTaskInfo_t qCreateQueueExecTaskInfo(void* msg, SReadHandle* readers, int32_t* numOfCols,
+                                     SSchemaWrapper** pSchemaWrapper) {
   if (msg == NULL) {
     // TODO create raw scan
     return NULL;
@@ -146,7 +147,7 @@ qTaskInfo_t qCreateQueueExecTaskInfo(void* msg, SReadHandle* readers, int32_t* n
   SDataBlockDescNode* pDescNode = pPlan->pNode->pOutputDataBlockDesc;
   *numOfCols = 0;
 
-  SNode*  pNode;
+  SNode* pNode;
   FOREACH(pNode, pDescNode->pSlots) {
     SSlotDescNode* pSlotDesc = (SSlotDescNode*)pNode;
     if (pSlotDesc->output) {
@@ -249,9 +250,11 @@ int32_t qUpdateQualifiedTableId(qTaskInfo_t tinfo, const SArray* tableIdList, bo
 
     // add to qTaskInfo
     // todo refactor STableList
-    for(int32_t i = 0; i < taosArrayGetSize(qa); ++i) {
+    for (int32_t i = 0; i < taosArrayGetSize(qa); ++i) {
       uint64_t* uid = taosArrayGet(qa, i);
 
+      qDebug("table %ld added to task info", *uid);
+
       STableKeyInfo keyInfo = {.uid = *uid, .groupId = 0};
       taosArrayPush(pTaskInfo->tableqinfoList.pTableList, &keyInfo);
     }

source/libs/executor/src/executorMain.c

@@ -315,6 +315,9 @@ int32_t qStreamPrepareScan(qTaskInfo_t tinfo, const STqOffsetVal* pOffset) {
       if (type == QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN) {
         SStreamScanInfo* pInfo = pOperator->info;
         if (pOffset->type == TMQ_OFFSET__LOG) {
+          STableScanInfo* pTSInfo = pInfo->pTableScanOp->info;
+          tsdbReaderClose(pTSInfo->dataReader);
+          pTSInfo->dataReader = NULL;
 #if 0
           if (tOffsetEqual(pOffset, &pTaskInfo->streamInfo.lastStatus) &&
               pInfo->tqReader->pWalReader->curVersion != pOffset->version) {
@@ -341,11 +344,20 @@ int32_t qStreamPrepareScan(qTaskInfo_t tinfo, const STqOffsetVal* pOffset) {
               return -1;
             }
           }
+
           /*if (pTaskInfo->streamInfo.lastStatus.type != TMQ_OFFSET__SNAPSHOT_DATA ||*/
           /*pTaskInfo->streamInfo.lastStatus.uid != uid || pTaskInfo->streamInfo.lastStatus.ts != ts) {*/
           STableScanInfo* pTableScanInfo = pInfo->pTableScanOp->info;
           int32_t         tableSz = taosArrayGetSize(pTaskInfo->tableqinfoList.pTableList);
-          bool            found = false;
+
+#ifndef NDEBUG
+
+          qDebug("switch to next table %ld (cursor %d), %ld rows returned", uid, pTableScanInfo->currentTable,
+                 pInfo->pTableScanOp->resultInfo.totalRows);
+          pInfo->pTableScanOp->resultInfo.totalRows = 0;
+#endif
+
+          bool found = false;
           for (int32_t i = 0; i < tableSz; i++) {
             STableKeyInfo* pTableInfo = taosArrayGet(pTaskInfo->tableqinfoList.pTableList, i);
             if (pTableInfo->uid == uid) {
@@ -358,6 +370,14 @@ int32_t qStreamPrepareScan(qTaskInfo_t tinfo, const STqOffsetVal* pOffset) {
           // TODO after dropping table, table may be not found
           ASSERT(found);
 
+          if (pTableScanInfo->dataReader == NULL) {
+            if (tsdbReaderOpen(pTableScanInfo->readHandle.vnode, &pTableScanInfo->cond,
+                               pTaskInfo->tableqinfoList.pTableList, &pTableScanInfo->dataReader, NULL) < 0 ||
+                pTableScanInfo->dataReader == NULL) {
+              ASSERT(0);
+            }
+          }
+
           tsdbSetTableId(pTableScanInfo->dataReader, uid);
           int64_t oldSkey = pTableScanInfo->cond.twindows.skey;
           pTableScanInfo->cond.twindows.skey = ts + 1;

source/libs/executor/src/scanoperator.c

@@ -740,7 +740,7 @@ static SSDataBlock* doBlockInfoScan(SOperatorInfo* pOperator) {
 static void destroyBlockDistScanOperatorInfo(void* param, int32_t numOfOutput) {
   SBlockDistInfo* pDistInfo = (SBlockDistInfo*)param;
   blockDataDestroy(pDistInfo->pResBlock);
-
+  tsdbReaderClose(pDistInfo->pHandle);
   taosMemoryFreeClear(param);
 }
 
@@ -982,6 +982,9 @@ static SSDataBlock* doRangeScan(SStreamScanInfo* pInfo, SSDataBlock* pSDB, int32
     if (!pResult) {
       blockDataCleanup(pSDB);
       *pRowIndex = 0;
+      STableScanInfo* pTableScanInfo = pInfo->pTableScanOp->info;
+      tsdbReaderClose(pTableScanInfo->dataReader);
+      pTableScanInfo->dataReader = NULL;
       return NULL;
     }
 
@@ -1003,6 +1006,9 @@ static SSDataBlock* doDataScan(SStreamScanInfo* pInfo, SSDataBlock* pSDB, int32_
     }
     if (!pResult) {
       pInfo->updateWin = (STimeWindow){.skey = INT64_MIN, .ekey = INT64_MAX};
+      STableScanInfo* pTableScanInfo = pInfo->pTableScanOp->info;
+      tsdbReaderClose(pTableScanInfo->dataReader);
+      pTableScanInfo->dataReader = NULL;
       return NULL;
     }
 
@@ -1525,7 +1531,7 @@ static void destroyStreamScanOperatorInfo(void* param, int32_t numOfOutput) {
 }
 
 SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhysiNode* pTableScanNode, SNode* pTagCond,
-                                            SExecTaskInfo* pTaskInfo) {
+                                            STimeWindowAggSupp* pTwSup, SExecTaskInfo* pTaskInfo) {
   SStreamScanInfo* pInfo = taosMemoryCalloc(1, sizeof(SStreamScanInfo));
   SOperatorInfo*   pOperator = taosMemoryCalloc(1, sizeof(SOperatorInfo));
 
@@ -1539,11 +1545,7 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
 
   pInfo->pTagCond = pTagCond;
 
-  pInfo->twAggSup = (STimeWindowAggSupp){
-      .waterMark = pTableScanNode->watermark,
-      .calTrigger = pTableScanNode->triggerType,
-      .maxTs = INT64_MIN,
-  };
+  pInfo->twAggSup = *pTwSup;
 
   int32_t numOfCols = 0;
   pInfo->pColMatchInfo = extractColMatchInfo(pScanPhyNode->pScanCols, pDescNode, &numOfCols, COL_MATCH_FROM_COL_ID);
@@ -2051,8 +2053,8 @@ static SSDataBlock* sysTableScanUserTables(SOperatorInfo* pOperator) {
         uint64_t suid = pInfo->pCur->mr.me.ctbEntry.suid;
         int32_t  code = metaGetTableEntryByUid(&mr, suid);
         if (code != TSDB_CODE_SUCCESS) {
-          qError("failed to get super table meta, cname:%s, suid:0x%" PRIx64 ", code:%s, %s", 
-                 pInfo->pCur->mr.me.name, suid, tstrerror(terrno), GET_TASKID(pTaskInfo));
+          qError("failed to get super table meta, cname:%s, suid:0x%" PRIx64 ", code:%s, %s", pInfo->pCur->mr.me.name,
+                 suid, tstrerror(terrno), GET_TASKID(pTaskInfo));
           metaReaderClear(&mr);
           metaCloseTbCursor(pInfo->pCur);
           pInfo->pCur = NULL;
@@ -2158,7 +2160,6 @@ static SSDataBlock* sysTableScanUserTables(SOperatorInfo* pOperator) {
   }
 }
 
-
 static SSDataBlock* sysTableScanUserSTables(SOperatorInfo* pOperator) {
   SExecTaskInfo*     pTaskInfo = pOperator->pTaskInfo;
   SSysTableScanInfo* pInfo = pOperator->info;
@@ -2184,12 +2185,13 @@ static SSDataBlock* doSysTableScan(SOperatorInfo* pOperator) {
     getDBNameFromCondition(pInfo->pCondition, dbName);
     sprintf(pInfo->req.db, "%d.%s", pInfo->accountId, dbName);
   }
-  
+
   if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0) {
     return sysTableScanUserTables(pOperator);
   } else if (strncasecmp(name, TSDB_INS_TABLE_USER_TAGS, TSDB_TABLE_FNAME_LEN) == 0) {
     return sysTableScanUserTags(pOperator);
-  } else if (strncasecmp(name, TSDB_INS_TABLE_USER_STABLES, TSDB_TABLE_FNAME_LEN) == 0 && IS_SYS_DBNAME(pInfo->req.db)) {
+  } else if (strncasecmp(name, TSDB_INS_TABLE_USER_STABLES, TSDB_TABLE_FNAME_LEN) == 0 &&
+             IS_SYS_DBNAME(pInfo->req.db)) {
     return sysTableScanUserSTables(pOperator);
   } else {  // load the meta from mnode of the given epset
     if (pOperator->status == OP_EXEC_DONE) {

source/libs/function/inc/functionMgtInt.h

@@ -47,6 +47,7 @@ extern "C" {
 #define FUNC_MGT_SYSTEM_INFO_FUNC       FUNC_MGT_FUNC_CLASSIFICATION_MASK(18)
 #define FUNC_MGT_CLIENT_PC_FUNC         FUNC_MGT_FUNC_CLASSIFICATION_MASK(19)
 #define FUNC_MGT_MULTI_ROWS_FUNC        FUNC_MGT_FUNC_CLASSIFICATION_MASK(20)
+#define FUNC_MGT_KEEP_ORDER_FUNC        FUNC_MGT_FUNC_CLASSIFICATION_MASK(21)
 
 #define FUNC_MGT_TEST_MASK(val, mask) (((val) & (mask)) != 0)
 

source/libs/function/src/builtins.c

@@ -2088,7 +2088,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
     .classification = FUNC_MGT_AGG_FUNC,
     .translateFunc = translateApercentileMerge,
     .getEnvFunc   = getApercentileFuncEnv,
-    .initFunc     = functionSetup,
+    .initFunc     = apercentileFunctionSetup,
     .processFunc  = apercentileFunctionMerge,
     .finalizeFunc = apercentileFinalize,
     .invertFunc   = NULL,
@@ -2097,7 +2097,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
   {
     .name = "top",
     .type = FUNCTION_TYPE_TOP,
-    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
+    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_KEEP_ORDER_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
     .translateFunc = translateTopBot,
     .getEnvFunc   = getTopBotFuncEnv,
     .initFunc     = topBotFunctionSetup,
@@ -2112,7 +2112,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
   {
     .name = "bottom",
     .type = FUNCTION_TYPE_BOTTOM,
-    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
+    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_KEEP_ORDER_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
     .translateFunc = translateTopBot,
     .getEnvFunc   = getTopBotFuncEnv,
     .initFunc     = topBotFunctionSetup,
@@ -2480,7 +2480,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
   {
     .name = "sample",
     .type = FUNCTION_TYPE_SAMPLE,
-    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
+    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_MULTI_ROWS_FUNC | FUNC_MGT_KEEP_ORDER_FUNC | FUNC_MGT_FORBID_STREAM_FUNC,
     .translateFunc = translateSample,
     .getEnvFunc   = getSampleFuncEnv,
     .initFunc     = sampleFunctionSetup,
@@ -2906,7 +2906,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
   {
     .name = "_select_value",
     .type = FUNCTION_TYPE_SELECT_VALUE,
-    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC,
+    .classification = FUNC_MGT_AGG_FUNC | FUNC_MGT_SELECT_FUNC | FUNC_MGT_KEEP_ORDER_FUNC,
     .translateFunc = translateSelectValue,
     .getEnvFunc   = getSelectivityFuncEnv,  // todo remove this function later.
     .initFunc     = functionSetup,

source/libs/function/src/builtinsimpl.c

@@ -2592,6 +2592,7 @@ int32_t apercentileFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
   SAPercentileInfo*    pInfo = (SAPercentileInfo*)GET_ROWCELL_INTERBUF(pResInfo);
 
   if (pInfo->algo == APERCT_ALGO_TDIGEST) {
+    buildTDigestInfo(pInfo);
     if (pInfo->pTDigest->size > 0) {
       pInfo->result = tdigestQuantile(pInfo->pTDigest, pInfo->percent / 100);
     } else {  // no need to free
@@ -2599,6 +2600,7 @@ int32_t apercentileFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
       return TSDB_CODE_SUCCESS;
     }
   } else {
+    buildHistogramInfo(pInfo);
     if (pInfo->pHisto->numOfElems > 0) {
       qDebug("get the final res:%d, elements:%"PRId64", entry:%d", pInfo->pHisto->numOfElems, pInfo->pHisto->numOfEntries);
 

source/libs/function/src/functionMgt.c

@@ -183,6 +183,8 @@ bool fmIsClientPseudoColumnFunc(int32_t funcId) { return isSpecificClassifyFunc(
 
 bool fmIsMultiRowsFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MGT_MULTI_ROWS_FUNC); }
 
+bool fmIsKeepOrderFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MGT_KEEP_ORDER_FUNC); }
+
 bool fmIsInterpFunc(int32_t funcId) {
   if (funcId < 0 || funcId >= funcMgtBuiltinsNum) {
     return false;

source/libs/nodes/src/nodesCloneFuncs.c

@@ -332,6 +332,9 @@ static int32_t logicNodeCopy(const SLogicNode* pSrc, SLogicNode* pDst) {
   COPY_SCALAR_FIELD(precision);
   CLONE_NODE_FIELD(pLimit);
   CLONE_NODE_FIELD(pSlimit);
+  COPY_SCALAR_FIELD(requireDataOrder);
+  COPY_SCALAR_FIELD(resultDataOrder);
+  COPY_SCALAR_FIELD(groupAction);
   return TSDB_CODE_SUCCESS;
 }
 

source/libs/nodes/src/nodesCodeFuncs.c

@@ -504,6 +504,9 @@ static const char* jkLogicPlanConditions = "Conditions";
 static const char* jkLogicPlanChildren = "Children";
 static const char* jkLogicPlanLimit = "Limit";
 static const char* jkLogicPlanSlimit = "SLimit";
+static const char* jkLogicPlanRequireDataOrder = "RequireDataOrder";
+static const char* jkLogicPlanResultDataOrder = "ResultDataOrder";
+static const char* jkLogicPlanGroupAction = "GroupAction";
 
 static int32_t logicPlanNodeToJson(const void* pObj, SJson* pJson) {
   const SLogicNode* pNode = (const SLogicNode*)pObj;
@@ -521,6 +524,15 @@ static int32_t logicPlanNodeToJson(const void* pObj, SJson* pJson) {
   if (TSDB_CODE_SUCCESS == code) {
     code = tjsonAddObject(pJson, jkLogicPlanSlimit, nodeToJson, pNode->pSlimit);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkLogicPlanRequireDataOrder, pNode->requireDataOrder);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkLogicPlanResultDataOrder, pNode->resultDataOrder);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = tjsonAddIntegerToObject(pJson, jkLogicPlanGroupAction, pNode->groupAction);
+  }
 
   return code;
 }
@@ -541,6 +553,15 @@ static int32_t jsonToLogicPlanNode(const SJson* pJson, void* pObj) {
   if (TSDB_CODE_SUCCESS == code) {
     code = jsonToNodeObject(pJson, jkLogicPlanSlimit, &pNode->pSlimit);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    tjsonGetNumberValue(pJson, jkLogicPlanRequireDataOrder, pNode->requireDataOrder, code);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    tjsonGetNumberValue(pJson, jkLogicPlanResultDataOrder, pNode->resultDataOrder, code);
+  }
+  if (TSDB_CODE_SUCCESS == code) {
+    tjsonGetNumberValue(pJson, jkLogicPlanGroupAction, pNode->groupAction, code);
+  }
 
   return code;
 }

source/libs/parser/src/parTranslater.c

@@ -1089,7 +1089,7 @@ static int32_t translateScanPseudoColumnFunc(STranslateContext* pCxt, SFunctionN
     return TSDB_CODE_SUCCESS;
   }
   if (0 == LIST_LENGTH(pFunc->pParameterList)) {
-    if (!isSelectStmt(pCxt->pCurrStmt) ||
+    if (!isSelectStmt(pCxt->pCurrStmt) || NULL == ((SSelectStmt*)pCxt->pCurrStmt)->pFromTable ||
         QUERY_NODE_REAL_TABLE != nodeType(((SSelectStmt*)pCxt->pCurrStmt)->pFromTable)) {
       return generateSyntaxErrMsg(&pCxt->msgBuf, TSDB_CODE_PAR_INVALID_TBNAME);
     }

source/libs/parser/src/parser.c

@@ -36,7 +36,7 @@ bool qIsInsertValuesSql(const char* pStr, size_t length) {
     pStr += index;
     index = 0;
     t = tStrGetToken((char*)pStr, &index, false);
-    if (TK_USING == t.type || TK_VALUES == t.type) {
+    if (TK_USING == t.type || TK_VALUES == t.type || TK_FILE == t.type) {
       return true;
     } else if (TK_SELECT == t.type) {
       return false;

tests/script/tsim/parser/limit1_stb.sim

-sleep 100
 sql connect
 
 $dbPrefix = lm1_db