Merge branch '3.0' of github.com:taosdata/TDengine into 3.0

cmake/cmake.define

@@ -97,10 +97,10 @@ ELSE ()
         SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${GCC_COVERAGE_COMPILE_FLAGS} ${GCC_COVERAGE_LINK_FLAGS}")
     ENDIF ()
 
-    IF (${SANITIZER} MATCHES "true")
+    IF (${BUILD_SANITIZER})
         SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS}     -Werror -Werror=return-type -fPIC -gdwarf-2 -fsanitize=address -fsanitize=undefined -fsanitize-recover=all -fsanitize=float-divide-by-zero -fsanitize=float-cast-overflow -fno-sanitize=shift-base -fno-sanitize=alignment -g3 -Wformat=0")
         SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Werror -Wno-literal-suffix -Werror=return-type -fPIC -gdwarf-2 -fsanitize=address -fsanitize=undefined -fsanitize-recover=all -fsanitize=float-divide-by-zero -fsanitize=float-cast-overflow -fno-sanitize=shift-base -fno-sanitize=alignment -g3 -Wformat=0")
-	MESSAGE(STATUS "Will compile with Address Sanitizer!")
+	      MESSAGE(STATUS "Will compile with Address Sanitizer!")
     ELSE ()
         SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Werror -Werror=return-type -fPIC -gdwarf-2 -g3 -Wformat=0")
         SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Werror -Wno-literal-suffix -Werror=return-type -fPIC -gdwarf-2 -g3 -Wformat=0")

cmake/cmake.options

@@ -77,6 +77,12 @@ ELSE ()
     ENDIF ()
 ENDIF ()
 
+option(
+    BUILD_SANITIZER
+    "If build addr2line"
+    OFF
+    )
+
 option(
     BUILD_ADDR2LINE
     "If build addr2line"

docs/en/25-application/03-immigrate.md

@@ -379,11 +379,11 @@ We still use the hypothetical environment from Chapter 4. There are three measur
 
 ### Storage resource estimation
 
-Assuming that the number of sensor devices that generate data and need to be stored is `n`, the frequency of data generation is `t` per second, and the length of each record is `L` bytes, the scale of data generated per day is `n * t * L` bytes. Assuming the compression ratio is `C`, the daily data size is `(n * t * L)/C` bytes. The storage resources are estimated to accommodate the data scale for 1.5 years. In the production environment, the compression ratio C of TDengine is generally between 5 and 7.
+Assuming that the number of sensor devices that generate data and need to be stored is `n`, the frequency of data generation is `t` per second, and the length of each record is `L` bytes, the scale of data generated per day is `86400 * n * t * L` bytes. Assuming the compression ratio is `C`, the daily data size is `(86400 * n * t * L)/C` bytes. The storage resources are estimated to accommodate the data scale for 1.5 years. In the production environment, the compression ratio C of TDengine is generally between 5 and 7.
 With additional 20% redundancy, you can calculate the required storage resources:
 
 ```matlab
-(n * t * L) * (365 * 1.5) * (1+20%)/C
+(86400 * n * t * L) * (365 * 1.5) * (1+20%)/C
 ````
 Substituting in the above formula, the raw data generated every year is 11.8TB without considering the label information. Note that tag information is associated with each timeline in TDengine, not every record. The amount of data to be recorded is somewhat reduced relative to the generated data, and label data can be ignored as a whole. Assuming a compression ratio of 5, the size of the retained data ends up being 2.56 TB.
 

docs/zh/25-application/03-immigrate.md

@@ -367,10 +367,10 @@ WHERE ts>=1510560000 AND ts<=1515000009
 
 ### 存储资源估算
 
-假设产生数据并需要存储的传感器设备数量为 `n`，数据生成的频率为`t`条/秒，每条记录的长度为 `L` bytes，则每天产生的数据规模为 `n×t×L` bytes。假设压缩比为 C，则每日产生数据规模为 `(n×t×L)/C` bytes。存储资源预估为能够容纳 1.5 年的数据规模，生产环境下 TDengine 的压缩比 C 一般在 5 ~ 7 之间，同时为最后结果增加 20% 的冗余，可计算得到需要存储资源：
+假设产生数据并需要存储的传感器设备数量为 `n`，数据生成的频率为`t`条/秒，每条记录的长度为 `L` bytes，则每天产生的数据规模为 `86400×n×t×L` bytes。假设压缩比为 C，则每日产生数据规模为 `(86400×n×t×L)/C` bytes。存储资源预估为能够容纳 1.5 年的数据规模，生产环境下 TDengine 的压缩比 C 一般在 5 ~ 7 之间，同时为最后结果增加 20% 的冗余，可计算得到需要存储资源：
 
 ```matlab
-(n×t×L)×(365×1.5)×(1+20%)/C
+(86400×n×t×L)×(365×1.5)×(1+20%)/C
 ```
 
 结合以上的计算公式，将参数带入计算公式，在不考虑标签信息的情况下，每年产生的原始数据规模是 11.8TB。需要注意的是，由于标签信息在 TDengine 中关联到每个时间线，并不是每条记录。所以需要记录的数据量规模相对于产生的数据有一定的降低，而这部分标签数据整体上可以忽略不记。假设压缩比为 5，则保留的数据规模最终为 2.56 TB。

examples/c/tmq.c

@@ -241,7 +241,7 @@ int32_t create_topic() {
   taos_free_result(pRes);
 
   pRes = taos_query(pConn, "create topic topic_ctb_column with meta as database abc1");
-//  pRes = taos_query(pConn, "create topic topic_ctb_column as select ts, c1, c2, c3 from st1");
+  /*pRes = taos_query(pConn, "create topic topic_ctb_column as select ts, c1, c2, c3 from st1");*/
   if (taos_errno(pRes) != 0) {
     printf("failed to create topic topic_ctb_column, reason:%s\n", taos_errstr(pRes));
     return -1;
@@ -302,7 +302,7 @@ tmq_t* build_consumer() {
   tmq_conf_set(conf, "msg.with.table.name", "true");
   tmq_conf_set(conf, "enable.auto.commit", "true");
 
-  tmq_conf_set(conf, "experimental.snapshot.enable", "false");
+  /*tmq_conf_set(conf, "experimental.snapshot.enable", "true");*/
 
   tmq_conf_set_auto_commit_cb(conf, tmq_commit_cb_print, NULL);
   tmq_t* tmq = tmq_consumer_new(conf, NULL, 0);

include/common/tcommon.h

@@ -32,6 +32,18 @@ enum {
   TMQ_CONF__RESET_OFFSET__LATEST = -1,
 };
 
+// clang-format off
+#define IS_META_MSG(x) ( \
+     x == TDMT_VND_CREATE_STB     \
+  || x == TDMT_VND_ALTER_STB      \
+  || x == TDMT_VND_DROP_STB       \
+  || x == TDMT_VND_CREATE_TABLE   \
+  || x == TDMT_VND_ALTER_TABLE    \
+  || x == TDMT_VND_DROP_TABLE     \
+  || x == TDMT_VND_DROP_TTL_TABLE \
+)
+// clang-format on
+
 enum {
   TMQ_MSG_TYPE__DUMMY = 0,
   TMQ_MSG_TYPE__POLL_RSP,
@@ -76,8 +88,6 @@ typedef struct {
 #pragma pack(push, 1)
 typedef struct SColumnDataAgg {
   int16_t colId;
-  int16_t minIndex;
-  int16_t maxIndex;
   int16_t numOfNull;
   int64_t sum;
   int64_t max;
@@ -105,6 +115,20 @@ typedef struct SSDataBlock {
   SDataBlockInfo   info;
 } SSDataBlock;
 
+enum {
+  FETCH_TYPE__DATA = 1,
+  FETCH_TYPE__META,
+  FETCH_TYPE__NONE,
+};
+
+typedef struct {
+  int8_t fetchType;
+  union {
+    SSDataBlock data;
+    void*       meta;
+  };
+} SFetchRet;
+
 typedef struct SVarColAttr {
   int32_t* offset;    // start position for each entry in the list
   uint32_t length;    // used buffer size that contain the valid data

include/common/tmsg.h

@@ -57,8 +57,8 @@ extern int32_t tMsgDict[];
 #define TMSG_SEG_SEQ(TYPE)  ((TYPE)&0xff)
 #define TMSG_INFO(TYPE)                                                                                             \
   ((TYPE) >= 0 &&                                                                                                   \
-   ((TYPE) < TDMT_DND_MAX_MSG | (TYPE) < TDMT_MND_MAX_MSG | (TYPE) < TDMT_VND_MAX_MSG | (TYPE) < TDMT_SCH_MAX_MSG | \
+   ((TYPE) < TDMT_DND_MAX_MSG || (TYPE) < TDMT_MND_MAX_MSG || (TYPE) < TDMT_VND_MAX_MSG || (TYPE) < TDMT_SCH_MAX_MSG || \
-    (TYPE) < TDMT_STREAM_MAX_MSG | (TYPE) < TDMT_MON_MAX_MSG | (TYPE) < TDMT_SYNC_MAX_MSG))                         \
+    (TYPE) < TDMT_STREAM_MAX_MSG || (TYPE) < TDMT_MON_MAX_MSG || (TYPE) < TDMT_SYNC_MAX_MSG))                         \
       ? tMsgInfo[tMsgDict[TMSG_SEG_CODE(TYPE)] + TMSG_SEG_SEQ(TYPE)]                                                \
       : 0
 #define TMSG_INDEX(TYPE) (tMsgDict[TMSG_SEG_CODE(TYPE)] + TMSG_SEG_SEQ(TYPE))
@@ -665,6 +665,7 @@ typedef struct {
   char    tbFName[TSDB_TABLE_FNAME_LEN];
   int32_t sversion;
   int32_t tversion;
+  int64_t affectedRows;
 } SQueryTableRsp;
 
 int32_t tSerializeSQueryTableRsp(void* buf, int32_t bufLen, SQueryTableRsp* pRsp);
@@ -1510,6 +1511,7 @@ typedef struct SSubQueryMsg {
   int32_t  execId;
   int8_t   taskType;
   int8_t   explain;
+  int8_t   needFetch;
   uint32_t sqlLen;  // the query sql,
   uint32_t phyLen;
   char     msg[];
@@ -2826,8 +2828,8 @@ typedef struct {
 
 static FORCE_INLINE int32_t tEncodeSMqMetaRsp(void** buf, const SMqMetaRsp* pRsp) {
   int32_t tlen = 0;
-  tlen += taosEncodeFixedI64(buf, pRsp->reqOffset);
+  // tlen += taosEncodeFixedI64(buf, pRsp->reqOffset);
-  tlen += taosEncodeFixedI64(buf, pRsp->rspOffset);
+  // tlen += taosEncodeFixedI64(buf, pRsp->rspOffset);
   tlen += taosEncodeFixedI16(buf, pRsp->resMsgType);
   tlen += taosEncodeFixedI32(buf, pRsp->metaRspLen);
   tlen += taosEncodeBinary(buf, pRsp->metaRsp, pRsp->metaRspLen);
@@ -2835,8 +2837,8 @@ static FORCE_INLINE int32_t tEncodeSMqMetaRsp(void** buf, const SMqMetaRsp* pRsp
 }
 
 static FORCE_INLINE void* tDecodeSMqMetaRsp(const void* buf, SMqMetaRsp* pRsp) {
-  buf = taosDecodeFixedI64(buf, &pRsp->reqOffset);
+  // buf = taosDecodeFixedI64(buf, &pRsp->reqOffset);
-  buf = taosDecodeFixedI64(buf, &pRsp->rspOffset);
+  // buf = taosDecodeFixedI64(buf, &pRsp->rspOffset);
   buf = taosDecodeFixedI16(buf, &pRsp->resMsgType);
   buf = taosDecodeFixedI32(buf, &pRsp->metaRspLen);
   buf = taosDecodeBinary(buf, &pRsp->metaRsp, pRsp->metaRspLen);

include/common/ttokendef.h

@@ -79,195 +79,196 @@
 #define TK_EXISTS         61
 #define TK_BUFFER         62
 #define TK_CACHELAST      63
-#define TK_COMP           64
+#define TK_CACHELASTSIZE  64
-#define TK_DURATION       65
+#define TK_COMP           65
-#define TK_NK_VARIABLE    66
+#define TK_DURATION       66
-#define TK_FSYNC          67
+#define TK_NK_VARIABLE    67
-#define TK_MAXROWS        68
+#define TK_FSYNC          68
-#define TK_MINROWS        69
+#define TK_MAXROWS        69
-#define TK_KEEP           70
+#define TK_MINROWS        70
-#define TK_PAGES          71
+#define TK_KEEP           71
-#define TK_PAGESIZE       72
+#define TK_PAGES          72
-#define TK_PRECISION      73
+#define TK_PAGESIZE       73
-#define TK_REPLICA        74
+#define TK_PRECISION      74
-#define TK_STRICT         75
+#define TK_REPLICA        75
-#define TK_WAL            76
+#define TK_STRICT         76
-#define TK_VGROUPS        77
+#define TK_WAL            77
-#define TK_SINGLE_STABLE  78
+#define TK_VGROUPS        78
-#define TK_RETENTIONS     79
+#define TK_SINGLE_STABLE  79
-#define TK_SCHEMALESS     80
+#define TK_RETENTIONS     80
-#define TK_NK_COLON       81
+#define TK_SCHEMALESS     81
-#define TK_TABLE          82
+#define TK_NK_COLON       82
-#define TK_NK_LP          83
+#define TK_TABLE          83
-#define TK_NK_RP          84
+#define TK_NK_LP          84
-#define TK_STABLE         85
+#define TK_NK_RP          85
-#define TK_ADD            86
+#define TK_STABLE         86
-#define TK_COLUMN         87
+#define TK_ADD            87
-#define TK_MODIFY         88
+#define TK_COLUMN         88
-#define TK_RENAME         89
+#define TK_MODIFY         89
-#define TK_TAG            90
+#define TK_RENAME         90
-#define TK_SET            91
+#define TK_TAG            91
-#define TK_NK_EQ          92
+#define TK_SET            92
-#define TK_USING          93
+#define TK_NK_EQ          93
-#define TK_TAGS           94
+#define TK_USING          94
-#define TK_COMMENT        95
+#define TK_TAGS           95
-#define TK_BOOL           96
+#define TK_COMMENT        96
-#define TK_TINYINT        97
+#define TK_BOOL           97
-#define TK_SMALLINT       98
+#define TK_TINYINT        98
-#define TK_INT            99
+#define TK_SMALLINT       99
-#define TK_INTEGER        100
+#define TK_INT            100
-#define TK_BIGINT         101
+#define TK_INTEGER        101
-#define TK_FLOAT          102
+#define TK_BIGINT         102
-#define TK_DOUBLE         103
+#define TK_FLOAT          103
-#define TK_BINARY         104
+#define TK_DOUBLE         104
-#define TK_TIMESTAMP      105
+#define TK_BINARY         105
-#define TK_NCHAR          106
+#define TK_TIMESTAMP      106
-#define TK_UNSIGNED       107
+#define TK_NCHAR          107
-#define TK_JSON           108
+#define TK_UNSIGNED       108
-#define TK_VARCHAR        109
+#define TK_JSON           109
-#define TK_MEDIUMBLOB     110
+#define TK_VARCHAR        110
-#define TK_BLOB           111
+#define TK_MEDIUMBLOB     111
-#define TK_VARBINARY      112
+#define TK_BLOB           112
-#define TK_DECIMAL        113
+#define TK_VARBINARY      113
-#define TK_MAX_DELAY      114
+#define TK_DECIMAL        114
-#define TK_WATERMARK      115
+#define TK_MAX_DELAY      115
-#define TK_ROLLUP         116
+#define TK_WATERMARK      116
-#define TK_TTL            117
+#define TK_ROLLUP         117
-#define TK_SMA            118
+#define TK_TTL            118
-#define TK_FIRST          119
+#define TK_SMA            119
-#define TK_LAST           120
+#define TK_FIRST          120
-#define TK_SHOW           121
+#define TK_LAST           121
-#define TK_DATABASES      122
+#define TK_SHOW           122
-#define TK_TABLES         123
+#define TK_DATABASES      123
-#define TK_STABLES        124
+#define TK_TABLES         124
-#define TK_MNODES         125
+#define TK_STABLES        125
-#define TK_MODULES        126
+#define TK_MNODES         126
-#define TK_QNODES         127
+#define TK_MODULES        127
-#define TK_FUNCTIONS      128
+#define TK_QNODES         128
-#define TK_INDEXES        129
+#define TK_FUNCTIONS      129
-#define TK_ACCOUNTS       130
+#define TK_INDEXES        130
-#define TK_APPS           131
+#define TK_ACCOUNTS       131
-#define TK_CONNECTIONS    132
+#define TK_APPS           132
-#define TK_LICENCE        133
+#define TK_CONNECTIONS    133
-#define TK_GRANTS         134
+#define TK_LICENCE        134
-#define TK_QUERIES        135
+#define TK_GRANTS         135
-#define TK_SCORES         136
+#define TK_QUERIES        136
-#define TK_TOPICS         137
+#define TK_SCORES         137
-#define TK_VARIABLES      138
+#define TK_TOPICS         138
-#define TK_BNODES         139
+#define TK_VARIABLES      139
-#define TK_SNODES         140
+#define TK_BNODES         140
-#define TK_CLUSTER        141
+#define TK_SNODES         141
-#define TK_TRANSACTIONS   142
+#define TK_CLUSTER        142
-#define TK_DISTRIBUTED    143
+#define TK_TRANSACTIONS   143
-#define TK_CONSUMERS      144
+#define TK_DISTRIBUTED    144
-#define TK_SUBSCRIPTIONS  145
+#define TK_CONSUMERS      145
-#define TK_LIKE           146
+#define TK_SUBSCRIPTIONS  146
-#define TK_INDEX          147
+#define TK_LIKE           147
-#define TK_FUNCTION       148
+#define TK_INDEX          148
-#define TK_INTERVAL       149
+#define TK_FUNCTION       149
-#define TK_TOPIC          150
+#define TK_INTERVAL       150
-#define TK_AS             151
+#define TK_TOPIC          151
-#define TK_WITH           152
+#define TK_AS             152
-#define TK_META           153
+#define TK_WITH           153
-#define TK_CONSUMER       154
+#define TK_META           154
-#define TK_GROUP          155
+#define TK_CONSUMER       155
-#define TK_DESC           156
+#define TK_GROUP          156
-#define TK_DESCRIBE       157
+#define TK_DESC           157
-#define TK_RESET          158
+#define TK_DESCRIBE       158
-#define TK_QUERY          159
+#define TK_RESET          159
-#define TK_CACHE          160
+#define TK_QUERY          160
-#define TK_EXPLAIN        161
+#define TK_CACHE          161
-#define TK_ANALYZE        162
+#define TK_EXPLAIN        162
-#define TK_VERBOSE        163
+#define TK_ANALYZE        163
-#define TK_NK_BOOL        164
+#define TK_VERBOSE        164
-#define TK_RATIO          165
+#define TK_NK_BOOL        165
-#define TK_NK_FLOAT       166
+#define TK_RATIO          166
-#define TK_COMPACT        167
+#define TK_NK_FLOAT       167
-#define TK_VNODES         168
+#define TK_COMPACT        168
-#define TK_IN             169
+#define TK_VNODES         169
-#define TK_OUTPUTTYPE     170
+#define TK_IN             170
-#define TK_AGGREGATE      171
+#define TK_OUTPUTTYPE     171
-#define TK_BUFSIZE        172
+#define TK_AGGREGATE      172
-#define TK_STREAM         173
+#define TK_BUFSIZE        173
-#define TK_INTO           174
+#define TK_STREAM         174
-#define TK_TRIGGER        175
+#define TK_INTO           175
-#define TK_AT_ONCE        176
+#define TK_TRIGGER        176
-#define TK_WINDOW_CLOSE   177
+#define TK_AT_ONCE        177
-#define TK_IGNORE         178
+#define TK_WINDOW_CLOSE   178
-#define TK_EXPIRED        179
+#define TK_IGNORE         179
-#define TK_KILL           180
+#define TK_EXPIRED        180
-#define TK_CONNECTION     181
+#define TK_KILL           181
-#define TK_TRANSACTION    182
+#define TK_CONNECTION     182
-#define TK_BALANCE        183
+#define TK_TRANSACTION    183
-#define TK_VGROUP         184
+#define TK_BALANCE        184
-#define TK_MERGE          185
+#define TK_VGROUP         185
-#define TK_REDISTRIBUTE   186
+#define TK_MERGE          186
-#define TK_SPLIT          187
+#define TK_REDISTRIBUTE   187
-#define TK_SYNCDB         188
+#define TK_SPLIT          188
-#define TK_DELETE         189
+#define TK_SYNCDB         189
-#define TK_INSERT         190
+#define TK_DELETE         190
-#define TK_NULL           191
+#define TK_INSERT         191
-#define TK_NK_QUESTION    192
+#define TK_NULL           192
-#define TK_NK_ARROW       193
+#define TK_NK_QUESTION    193
-#define TK_ROWTS          194
+#define TK_NK_ARROW       194
-#define TK_TBNAME         195
+#define TK_ROWTS          195
-#define TK_QSTARTTS       196
+#define TK_TBNAME         196
-#define TK_QENDTS         197
+#define TK_QSTARTTS       197
-#define TK_WSTARTTS       198
+#define TK_QENDTS         198
-#define TK_WENDTS         199
+#define TK_WSTARTTS       199
-#define TK_WDURATION      200
+#define TK_WENDTS         200
-#define TK_CAST           201
+#define TK_WDURATION      201
-#define TK_NOW            202
+#define TK_CAST           202
-#define TK_TODAY          203
+#define TK_NOW            203
-#define TK_TIMEZONE       204
+#define TK_TODAY          204
-#define TK_CLIENT_VERSION 205
+#define TK_TIMEZONE       205
-#define TK_SERVER_VERSION 206
+#define TK_CLIENT_VERSION 206
-#define TK_SERVER_STATUS  207
+#define TK_SERVER_VERSION 207
-#define TK_CURRENT_USER   208
+#define TK_SERVER_STATUS  208
-#define TK_COUNT          209
+#define TK_CURRENT_USER   209
-#define TK_LAST_ROW       210
+#define TK_COUNT          210
-#define TK_BETWEEN        211
+#define TK_LAST_ROW       211
-#define TK_IS             212
+#define TK_BETWEEN        212
-#define TK_NK_LT          213
+#define TK_IS             213
-#define TK_NK_GT          214
+#define TK_NK_LT          214
-#define TK_NK_LE          215
+#define TK_NK_GT          215
-#define TK_NK_GE          216
+#define TK_NK_LE          216
-#define TK_NK_NE          217
+#define TK_NK_GE          217
-#define TK_MATCH          218
+#define TK_NK_NE          218
-#define TK_NMATCH         219
+#define TK_MATCH          219
-#define TK_CONTAINS       220
+#define TK_NMATCH         220
-#define TK_JOIN           221
+#define TK_CONTAINS       221
-#define TK_INNER          222
+#define TK_JOIN           222
-#define TK_SELECT         223
+#define TK_INNER          223
-#define TK_DISTINCT       224
+#define TK_SELECT         224
-#define TK_WHERE          225
+#define TK_DISTINCT       225
-#define TK_PARTITION      226
+#define TK_WHERE          226
-#define TK_BY             227
+#define TK_PARTITION      227
-#define TK_SESSION        228
+#define TK_BY             228
-#define TK_STATE_WINDOW   229
+#define TK_SESSION        229
-#define TK_SLIDING        230
+#define TK_STATE_WINDOW   230
-#define TK_FILL           231
+#define TK_SLIDING        231
-#define TK_VALUE          232
+#define TK_FILL           232
-#define TK_NONE           233
+#define TK_VALUE          233
-#define TK_PREV           234
+#define TK_NONE           234
-#define TK_LINEAR         235
+#define TK_PREV           235
-#define TK_NEXT           236
+#define TK_LINEAR         236
-#define TK_HAVING         237
+#define TK_NEXT           237
-#define TK_RANGE          238
+#define TK_HAVING         238
-#define TK_EVERY          239
+#define TK_RANGE          239
-#define TK_ORDER          240
+#define TK_EVERY          240
-#define TK_SLIMIT         241
+#define TK_ORDER          241
-#define TK_SOFFSET        242
+#define TK_SLIMIT         242
-#define TK_LIMIT          243
+#define TK_SOFFSET        243
-#define TK_OFFSET         244
+#define TK_LIMIT          244
-#define TK_ASC            245
+#define TK_OFFSET         245
-#define TK_NULLS          246
+#define TK_ASC            246
-#define TK_ID             247
+#define TK_NULLS          247
-#define TK_NK_BITNOT      248
+#define TK_ID             248
-#define TK_VALUES         249
+#define TK_NK_BITNOT      249
-#define TK_IMPORT         250
+#define TK_VALUES         250
-#define TK_NK_SEMI        251
+#define TK_IMPORT         251
-#define TK_FILE           252
+#define TK_NK_SEMI        252
+#define TK_FILE           253
 
 #define TK_NK_SPACE   300
 #define TK_NK_COMMENT 301

include/libs/executor/dataSinkMgt.h

@@ -45,6 +45,10 @@ typedef struct SDeleterParam {
   SArray*  pUidList;
 } SDeleterParam;
 
+typedef struct SInserterParam {
+  SReadHandle* readHandle;
+} SInserterParam;
+
 typedef struct SDataSinkStat {
   uint64_t cachedSize;
 } SDataSinkStat;
@@ -96,7 +100,7 @@ void dsEndPut(DataSinkHandle handle, uint64_t useconds);
  * @param handle
  * @param pLen data length
  */
-void dsGetDataLength(DataSinkHandle handle, int32_t* pLen, bool* pQueryEnd);
+void dsGetDataLength(DataSinkHandle handle, int64_t* pLen, bool* pQueryEnd);
 
 /**
  * Get data, the caller needs to allocate data memory.

include/libs/executor/executor.h

@@ -30,15 +30,15 @@ struct SRpcMsg;
 struct SSubplan;
 
 typedef struct SReadHandle {
-  void*   reader;
+  void*   tqReader;
   void*   meta;
   void*   config;
   void*   vnode;
   void*   mnd;
   SMsgCb* pMsgCb;
-
+  bool    initMetaReader;
-//  int8_t  initTsdbReader;
+  bool    initTableReader;
-  bool    tqReader;
+  bool    initTqReader;
 } SReadHandle;
 
 typedef enum {
@@ -52,7 +52,7 @@ typedef enum {
  * @param streamReadHandle
  * @return
  */
-qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, void* streamReadHandle);
+qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, SReadHandle* readers);
 
 /**
  * Switch the stream scan to snapshot mode
@@ -157,7 +157,7 @@ int64_t qGetQueriedTableUid(qTaskInfo_t tinfo);
  */
 int32_t qGetQualifiedTableIdList(void* pTableList, const char* tagCond, int32_t tagCondLen, SArray* pTableIdList);
 
-void qProcessFetchRsp(void* parent, struct SRpcMsg* pMsg, struct SEpSet* pEpSet);
+void qProcessRspMsg(void* parent, struct SRpcMsg* pMsg, struct SEpSet* pEpSet);
 
 int32_t qGetExplainExecInfo(qTaskInfo_t tinfo, int32_t* resNum, SExplainExecInfo** pRes);
 
@@ -176,6 +176,9 @@ int32_t qGetStreamScanStatus(qTaskInfo_t tinfo, uint64_t* uid, int64_t* ts);
 
 int32_t qStreamPrepareScan(qTaskInfo_t tinfo, uint64_t uid, int64_t ts);
 
+void*   qExtractReaderFromStreamScanner(void* scanner);
+int32_t qExtractStreamScanner(qTaskInfo_t tinfo, void** scanner);
+
 #ifdef __cplusplus
 }
 #endif

include/libs/nodes/cmdnodes.h

@@ -51,7 +51,8 @@ extern "C" {
 typedef struct SDatabaseOptions {
   ENodeType   type;
   int32_t     buffer;
-  int8_t      cachelast;
+  int8_t      cacheLast;
+  int32_t     cacheLastSize;
   int8_t      compressionLevel;
   int32_t     daysPerFile;
   SValueNode* pDaysPerFile;

include/libs/qworker/qworker.h

@@ -67,7 +67,7 @@ int32_t qWorkerProcessCQueryMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, in
 
 int32_t qWorkerProcessFetchMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts);
 
-int32_t qWorkerProcessFetchRsp(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts);
+int32_t qWorkerProcessRspMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts);
 
 int32_t qWorkerProcessCancelMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts);
 

include/libs/stream/tstream.h

@@ -223,7 +223,7 @@ typedef struct {
   SEpSet  epSet;
 } SStreamChildEpInfo;
 
-struct SStreamTask {
+typedef struct SStreamTask {
   int64_t streamId;
   int32_t taskId;
   int8_t  isDataScan;
@@ -277,7 +277,7 @@ struct SStreamTask {
 
   // msg handle
   SMsgCb* pMsgCb;
-};
+} SStreamTask;
 
 int32_t tEncodeStreamEpInfo(SEncoder* pEncoder, const SStreamChildEpInfo* pInfo);
 int32_t tDecodeStreamEpInfo(SDecoder* pDecoder, SStreamChildEpInfo* pInfo);
@@ -288,6 +288,7 @@ int32_t      tDecodeSStreamTask(SDecoder* pDecoder, SStreamTask* pTask);
 void         tFreeSStreamTask(SStreamTask* pTask);
 
 static FORCE_INLINE int32_t streamTaskInput(SStreamTask* pTask, SStreamQueueItem* pItem) {
+#if 0
   while (1) {
     int8_t inputStatus =
         atomic_val_compare_exchange_8(&pTask->inputStatus, TASK_INPUT_STATUS__NORMAL, TASK_INPUT_STATUS__PROCESSING);
@@ -296,6 +297,7 @@ static FORCE_INLINE int32_t streamTaskInput(SStreamTask* pTask, SStreamQueueItem
     }
     ASSERT(0);
   }
+#endif
 
   if (pItem->type == STREAM_INPUT__DATA_SUBMIT) {
     SStreamDataSubmit* pSubmitClone = streamSubmitRefClone((SStreamDataSubmit*)pItem);
@@ -316,8 +318,10 @@ static FORCE_INLINE int32_t streamTaskInput(SStreamTask* pTask, SStreamQueueItem
     atomic_val_compare_exchange_8(&pTask->triggerStatus, TASK_TRIGGER_STATUS__IN_ACTIVE, TASK_TRIGGER_STATUS__ACTIVE);
   }
 
+#if 0
   // TODO: back pressure
   atomic_store_8(&pTask->inputStatus, TASK_INPUT_STATUS__NORMAL);
+#endif
   return 0;
 }
 

include/libs/sync/sync.h

@@ -163,9 +163,6 @@ typedef struct SSyncLogStore {
   // return commit index of log
   SyncIndex (*getCommitIndex)(struct SSyncLogStore* pLogStore);
 
-  // refactor, log[0 .. n] ==> log[m .. n]
-  // int32_t (*syncLogSetBeginIndex)(struct SSyncLogStore* pLogStore, SyncIndex beginIndex);
-
   SyncIndex (*syncLogBeginIndex)(struct SSyncLogStore* pLogStore);
   SyncIndex (*syncLogEndIndex)(struct SSyncLogStore* pLogStore);
   bool (*syncLogIsEmpty)(struct SSyncLogStore* pLogStore);

include/libs/wal/wal.h

@@ -88,7 +88,7 @@ typedef struct {
   EWalType level;  // wal level
 } SWalCfg;
 
-typedef struct SWalVer {
+typedef struct {
   int64_t firstVer;
   int64_t verInSnapshotting;
   int64_t snapshotVer;
@@ -149,17 +149,22 @@ typedef struct SWal {
   SWalCkHead writeHead;
 } SWal;  // WAL HANDLE
 
-typedef struct SWalReadHandle {
+typedef struct {
-  SWal         *pWal;
+  int8_t scanUncommited;
-  TdFilePtr     pReadLogTFile;
+  int8_t scanMeta;
-  TdFilePtr     pReadIdxTFile;
+} SWalFilterCond;
-  int64_t       curFileFirstVer;
+
-  int64_t       curVersion;
+typedef struct {
-  int64_t       capacity;
+  SWal          *pWal;
-  int64_t       status;  // if cursor valid
+  TdFilePtr      pLogFile;
-  TdThreadMutex mutex;
+  TdFilePtr      pIdxFile;
-  SWalCkHead   *pHead;
+  int64_t        curFileFirstVer;
-} SWalReadHandle;
+  int64_t        curVersion;
+  int64_t        capacity;
+  TdThreadMutex  mutex;
+  SWalFilterCond cond;
+  SWalCkHead    *pHead;
+} SWalReader;
 
 // module initialization
 int32_t walInit();
@@ -178,7 +183,6 @@ void    walFsync(SWal *, bool force);
 
 // apis for lifecycle management
 int32_t walCommit(SWal *, int64_t ver);
-// truncate after
 int32_t walRollback(SWal *, int64_t ver);
 // notify that previous logs can be pruned safely
 int32_t walBeginSnapshot(SWal *, int64_t ver);
@@ -187,15 +191,16 @@ int32_t walRestoreFromSnapshot(SWal *, int64_t ver);
 // int32_t  walDataCorrupted(SWal*);
 
 // read
-SWalReadHandle *walOpenReadHandle(SWal *);
+SWalReader *walOpenReader(SWal *, SWalFilterCond *pCond);
-void            walCloseReadHandle(SWalReadHandle *);
+void        walCloseReader(SWalReader *pRead);
-int32_t         walReadWithHandle(SWalReadHandle *pRead, int64_t ver);
+int32_t     walReadVer(SWalReader *pRead, int64_t ver);
+int32_t     walNextValidMsg(SWalReader *pRead);
 
 // only for tq usage
-void    walSetReaderCapacity(SWalReadHandle *pRead, int32_t capacity);
+void    walSetReaderCapacity(SWalReader *pRead, int32_t capacity);
-int32_t walFetchHead(SWalReadHandle *pRead, int64_t ver, SWalCkHead *pHead);
+int32_t walFetchHead(SWalReader *pRead, int64_t ver, SWalCkHead *pHead);
-int32_t walFetchBody(SWalReadHandle *pRead, SWalCkHead **ppHead);
+int32_t walFetchBody(SWalReader *pRead, SWalCkHead **ppHead);
-int32_t walSkipFetchBody(SWalReadHandle *pRead, const SWalCkHead *pHead);
+int32_t walSkipFetchBody(SWalReader *pRead, const SWalCkHead *pHead);
 
 typedef struct {
   int64_t refId;
@@ -207,10 +212,11 @@ void     walCloseRef(SWalRef *);
 int32_t  walRefVer(SWalRef *, int64_t ver);
 int32_t  walUnrefVer(SWal *);
 
+// help function for raft
 bool walLogExist(SWal *, int64_t ver);
+bool walIsEmpty(SWal *);
 
 // lifecycle check
-bool    walIsEmpty(SWal *);
 int64_t walGetFirstVer(SWal *);
 int64_t walGetSnapshotVer(SWal *);
 int64_t walGetLastVer(SWal *);

include/util/tlog.h

@@ -60,7 +60,7 @@ extern int32_t tsdbDebugFlag;
 extern int32_t tqDebugFlag;
 extern int32_t fsDebugFlag;
 extern int32_t metaDebugFlag;
-extern int32_t fnDebugFlag;
+extern int32_t udfDebugFlag;
 extern int32_t smaDebugFlag;
 extern int32_t idxDebugFlag;
 

include/util/tutil.h

@@ -45,6 +45,7 @@ void     taosIp2String(uint32_t ip, char *str);
 void     taosIpPort2String(uint32_t ip, uint16_t port, char *str);
 
 void *tmemmem(const char *haystack, int hlen, const char *needle, int nlen);
+char *strDupUnquo(const char *src);
 
 static FORCE_INLINE void taosEncryptPass(uint8_t *inBuf, size_t inLen, char *target) {
   T_MD5_CTX context;

source/client/src/TMQConnector.c

@@ -324,9 +324,7 @@ JNIEXPORT jint JNICALL Java_com_taosdata_jdbc_tmq_TMQConnector_fetchRawBlockImp(
   (*env)->CallVoidMethod(env, rowobj, g_blockdataSetNumOfRowsFp, (jint)numOfRows);
   (*env)->CallVoidMethod(env, rowobj, g_blockdataSetNumOfColsFp, (jint)numOfFields);
 
-  char   *chars = (char *)data;
+  int32_t len = *(int32_t *)data;
-  int32_t len = chars[0] + (chars[1] << 8) + (chars[2] << 16) + (chars[3] << 24);
+  (*env)->CallVoidMethod(env, rowobj, g_blockdataSetByteArrayFp, jniFromNCharToByteArray(env, (char *)data, len));
-  (*env)->CallVoidMethod(env, rowobj, g_blockdataSetByteArrayFp, len, jniFromNCharToByteArray(env, (char *)data, len));
-
   return JNI_SUCCESS;
 }

source/client/src/TSDBJNIConnector.c

@@ -592,8 +592,7 @@ JNIEXPORT jint JNICALL Java_com_taosdata_jdbc_TSDBJNIConnector_fetchBlockImp(JNI
   (*env)->CallVoidMethod(env, rowobj, g_blockdataSetNumOfRowsFp, (jint)numOfRows);
   (*env)->CallVoidMethod(env, rowobj, g_blockdataSetNumOfColsFp, (jint)numOfFields);
 
-  char   *chars = (char *)data;
+  int32_t len = *(int32_t *)data;
-  int32_t len = chars[0] + (chars[1] << 8) + (chars[2] << 16) + (chars[3] << 24);
   (*env)->CallVoidMethod(env, rowobj, g_blockdataSetByteArrayFp, jniFromNCharToByteArray(env, (char *)data, len));
 
   return JNI_SUCCESS;

source/client/src/tmq.c

@@ -50,19 +50,18 @@ struct tmq_list_t {
 };
 
 struct tmq_conf_t {
-  char     clientId[256];
+  char           clientId[256];
-  char     groupId[TSDB_CGROUP_LEN];
+  char           groupId[TSDB_CGROUP_LEN];
-  int8_t   autoCommit;
+  int8_t         autoCommit;
-  int8_t   resetOffset;
+  int8_t         resetOffset;
-  int8_t   withTbName;
+  int8_t         withTbName;
-  int8_t   spEnable;
+  int8_t         spEnable;
-  int32_t  spBatchSize;
+  int32_t        spBatchSize;
-  uint16_t port;
+  uint16_t       port;
-  int32_t  autoCommitInterval;
+  int32_t        autoCommitInterval;
-  char*    ip;
+  char*          ip;
-  char*    user;
+  char*          user;
-  char*    pass;
+  char*          pass;
-  /*char*          db;*/
   tmq_commit_cb* commitCb;
   void*          commitCbUserParam;
 };
@@ -338,7 +337,7 @@ tmq_list_t* tmq_list_new() {
 
 int32_t tmq_list_append(tmq_list_t* list, const char* src) {
   SArray* container = &list->container;
-  char*   topic = strdup(src);
+  char*   topic = strDupUnquo(src);
   if (taosArrayPush(container, &topic) == NULL) return -1;
   return 0;
 }

source/client/test/clientTests.cpp

@@ -750,7 +750,6 @@ TEST(testCase, projection_query_stables) {
   taos_close(pConn);
 }
 
-
 TEST(testCase, agg_query_tables) {
   TAOS* pConn = taos_connect("localhost", "root", "taosdata", NULL, 0);
   ASSERT_NE(pConn, nullptr);
@@ -763,7 +762,7 @@ TEST(testCase, agg_query_tables) {
   }
   taos_free_result(pRes);
 
-  pRes = taos_query(pConn, "show table distributed st1");
+  pRes = taos_query(pConn, "show table distributed tup");
   if (taos_errno(pRes) != 0) {
     printf("failed to select from table, reason:%s\n", taos_errstr(pRes));
     taos_free_result(pRes);
@@ -822,13 +821,29 @@ TEST(testCase, async_api_test) {
 }
 #endif
 
+
 TEST(testCase, update_test) {
   TAOS* pConn = taos_connect("localhost", "root", "taosdata", NULL, 0);
   ASSERT_NE(pConn, nullptr);
 
-  taos_query(pConn, "use abc1");
+  TAOS_RES* pRes = taos_query(pConn, "create database if not exists abc1");
+  if (taos_errno(pRes) != TSDB_CODE_SUCCESS) {
+    printf("failed to create database, code:%s", taos_errstr(pRes));
+    taos_free_result(pRes);
+    return;
+  }
 
-  TAOS_RES* pRes = taos_query(pConn, "create table tup (ts timestamp, k int);");
+  taos_free_result(pRes);
+
+  pRes = taos_query(pConn, "use abc1");
+  if (taos_errno(pRes) != TSDB_CODE_SUCCESS) {
+    printf("failed to use db, code:%s", taos_errstr(pRes));
+    taos_free_result(pRes);
+    return;
+  }
+  taos_free_result(pRes);
+
+  pRes = taos_query(pConn, "create table tup (ts timestamp, k int);");
   if (taos_errno(pRes) != 0) {
     printf("failed to create table, reason:%s", taos_errstr(pRes));
   }
@@ -836,11 +851,10 @@ TEST(testCase, update_test) {
   taos_free_result(pRes);
 
   char s[256]  = {0};
-  for(int32_t i = 0; i < 7000; ++i) {
+  for(int32_t i = 0; i < 17000; ++i) {
-    sprintf(s, "insert into tup values('2020-1-1 1:1:1', %d)", i);
+    sprintf(s, "insert into tup values(now+%da, %d)", i, i);
     pRes = taos_query(pConn, s);
     taos_free_result(pRes);
   }
 }
-
 #pragma GCC diagnostic pop

source/common/src/tdata.c

@@ -1,14 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */

source/common/src/tdatablock.c

@@ -228,7 +228,7 @@ int32_t colDataMergeCol(SColumnInfoData* pColumnInfoData, uint32_t numOfRow1, ui
   uint32_t finalNumOfRows = numOfRow1 + numOfRow2;
   if (IS_VAR_DATA_TYPE(pColumnInfoData->info.type)) {
     // Handle the bitmap
-    if (finalNumOfRows > *capacity) {
+    if (finalNumOfRows > *capacity || numOfRow1 == 0) {
       char* p = taosMemoryRealloc(pColumnInfoData->varmeta.offset, sizeof(int32_t) * (numOfRow1 + numOfRow2));
       if (p == NULL) {
         return TSDB_CODE_OUT_OF_MEMORY;
@@ -262,7 +262,7 @@ int32_t colDataMergeCol(SColumnInfoData* pColumnInfoData, uint32_t numOfRow1, ui
     memcpy(pColumnInfoData->pData + oldLen, pSource->pData, len);
     pColumnInfoData->varmeta.length = len + oldLen;
   } else {
-    if (finalNumOfRows > *capacity) {
+    if (finalNumOfRows > *capacity || numOfRow1 == 0) {
       ASSERT(finalNumOfRows * pColumnInfoData->info.bytes);
       char* tmp = taosMemoryRealloc(pColumnInfoData->pData, finalNumOfRows * pColumnInfoData->info.bytes);
       if (tmp == NULL) {
@@ -2119,3 +2119,4 @@ const char* blockDecode(SSDataBlock* pBlock, int32_t numOfCols, int32_t numOfRow
   ASSERT(pStart - pData == dataLen);
   return pStart;
 }
+

source/common/src/tglobal.c

@@ -314,7 +314,7 @@ static int32_t taosAddServerLogCfg(SConfig *pCfg) {
   if (cfgAddInt32(pCfg, "tsdbDebugFlag", tsdbDebugFlag, 0, 255, 0) != 0) return -1;
   if (cfgAddInt32(pCfg, "tqDebugFlag", tqDebugFlag, 0, 255, 0) != 0) return -1;
   if (cfgAddInt32(pCfg, "fsDebugFlag", fsDebugFlag, 0, 255, 0) != 0) return -1;
-  if (cfgAddInt32(pCfg, "fnDebugFlag", fnDebugFlag, 0, 255, 0) != 0) return -1;
+  if (cfgAddInt32(pCfg, "udfDebugFlag", udfDebugFlag, 0, 255, 0) != 0) return -1;
   if (cfgAddInt32(pCfg, "smaDebugFlag", smaDebugFlag, 0, 255, 0) != 0) return -1;
   if (cfgAddInt32(pCfg, "idxDebugFlag", idxDebugFlag, 0, 255, 0) != 0) return -1;
   return 0;
@@ -504,7 +504,7 @@ static void taosSetServerLogCfg(SConfig *pCfg) {
   tsdbDebugFlag = cfgGetItem(pCfg, "tsdbDebugFlag")->i32;
   tqDebugFlag = cfgGetItem(pCfg, "tqDebugFlag")->i32;
   fsDebugFlag = cfgGetItem(pCfg, "fsDebugFlag")->i32;
-  fnDebugFlag = cfgGetItem(pCfg, "fnDebugFlag")->i32;
+  udfDebugFlag = cfgGetItem(pCfg, "udfDebugFlag")->i32;
   smaDebugFlag = cfgGetItem(pCfg, "smaDebugFlag")->i32;
   idxDebugFlag = cfgGetItem(pCfg, "idxDebugFlag")->i32;
 }
@@ -715,8 +715,6 @@ int32_t taosSetCfg(SConfig *pCfg, char* name) {
         cfgSetItem(pCfg, "firstEp", tsFirst, pFirstEpItem->stype);
       } else if (strcasecmp("fsDebugFlag", name) == 0) {
         fsDebugFlag = cfgGetItem(pCfg, "fsDebugFlag")->i32;
-      } else if (strcasecmp("fnDebugFlag", name) == 0) {
-        fnDebugFlag = cfgGetItem(pCfg, "fnDebugFlag")->i32;
       }
       break;
     }
@@ -817,6 +815,8 @@ int32_t taosSetCfg(SConfig *pCfg, char* name) {
         case 'u': {
           if (strcasecmp("multiProcess", name) == 0) {
             tsMultiProcess = cfgGetItem(pCfg, "multiProcess")->bval;
+          } else if (strcasecmp("udfDebugFlag", name) == 0) {
+            udfDebugFlag = cfgGetItem(pCfg, "udfDebugFlag")->i32;
           }
           break;
         }

source/common/src/tmsgtype.c

@@ -1,18 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define _DEFAULT_SOURCE
-#define TSDB_SQL_C
-#include "tmsgtype.h"

source/dnode/mgmt/exe/dmMain.c

@@ -216,7 +216,7 @@ int main(int argc, char const *argv[]) {
     return -1;
   }
 
-  dInfo("start to open dnode");
+  dInfo("start to init service");
   dmSetSignalHandle();
   int32_t code = dmRun();
   dInfo("shutting down the service");

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

@@ -238,10 +238,12 @@ SArray *mmGetMsgHandles() {
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_PING, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_PING_REPLY, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST_BATCH, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST_REPLY, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_REQUEST_VOTE, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_REQUEST_VOTE_REPLY, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES_BATCH, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES_REPLY, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_SNAPSHOT_SEND, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_SNAPSHOT_RSP, mmPutMsgToSyncQueue, 1) == NULL) goto _OVER;

source/dnode/mgmt/mgmt_vnode/src/vmHandle.c

@@ -377,10 +377,12 @@ SArray *vmGetMsgHandles() {
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_PING, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_PING_REPLY, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST_BATCH, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_CLIENT_REQUEST_REPLY, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_REQUEST_VOTE, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_REQUEST_VOTE_REPLY, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES_BATCH, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_APPEND_ENTRIES_REPLY, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
   if (dmSetMgmtHandle(pArray, TDMT_SYNC_SET_VNODE_STANDBY, vmPutMsgToSyncQueue, 0) == NULL) goto _OVER;
 

source/dnode/mgmt/mgmt_vnode/src/vmInt.c

@@ -173,7 +173,7 @@ static int32_t vmOpenVnodes(SVnodeMgmt *pMgmt) {
     pThread->pCfgs[pThread->vnodeNum++] = pCfgs[v];
   }
 
-  dInfo("start %d threads to open %d vnodes", threadNum, numOfVnodes);
+  dInfo("open %d vnodes with %d threads", numOfVnodes, threadNum);
 
   for (int32_t t = 0; t < threadNum; ++t) {
     SVnodeThread *pThread = &threads[t];
@@ -204,7 +204,7 @@ static int32_t vmOpenVnodes(SVnodeMgmt *pMgmt) {
     dError("there are total vnodes:%d, opened:%d", pMgmt->state.totalVnodes, pMgmt->state.openVnodes);
     return -1;
   } else {
-    dInfo("total vnodes:%d open successfully", pMgmt->state.totalVnodes);
+    dInfo("successfully opened %d vnodes", pMgmt->state.totalVnodes);
     return 0;
   }
 }

source/dnode/mgmt/node_mgmt/src/dmMgmt.c

@@ -128,7 +128,7 @@ static void dmClearVars(SDnode *pDnode) {
 }
 
 int32_t dmInitDnode(SDnode *pDnode, EDndNodeType rtype) {
-  dInfo("start to create dnode");
+  dDebug("start to create dnode");
   int32_t code = -1;
   char    path[PATH_MAX + 100] = {0};
 

source/dnode/mgmt/node_mgmt/src/dmTransport.c

@@ -89,7 +89,8 @@ static void dmProcessRpcMsg(SDnode *pDnode, SRpcMsg *pRpc, SEpSet *pEpSet) {
     case TDMT_DND_SYSTABLE_RETRIEVE_RSP:
     case TDMT_SCH_FETCH_RSP:
     case TDMT_SCH_MERGE_FETCH_RSP:
-      qWorkerProcessFetchRsp(NULL, NULL, pRpc, 0);
+    case TDMT_VND_SUBMIT_RSP:
+      qWorkerProcessRspMsg(NULL, NULL, pRpc, 0);
       return;
     case TDMT_MND_STATUS_RSP:
       if (pEpSet != NULL) {

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

@@ -188,7 +188,7 @@ int32_t mndInitSync(SMnode *pMnode) {
     SNodeInfo *pNode = &pCfg->nodeInfo[0];
     tstrncpy(pNode->nodeFqdn, pMgmt->replica.fqdn, sizeof(pNode->nodeFqdn));
     pNode->nodePort = pMgmt->replica.port;
-    mInfo("fqdn:%s port:%u", pNode->nodeFqdn, pNode->nodePort);
+    mInfo("mnode ep:%s:%u", pNode->nodeFqdn, pNode->nodePort);
   }
 
   tsem_init(&pMgmt->syncSem, 0, 0);

source/dnode/qnode/src/qnode.c

@@ -89,9 +89,6 @@ int32_t qndProcessQueryMsg(SQnode *pQnode, int64_t ts, SRpcMsg *pMsg) {
     case TDMT_SCH_MERGE_FETCH:
       code = qWorkerProcessFetchMsg(pQnode, pQnode->pQuery, pMsg, ts);
       break;
-    case TDMT_SCH_FETCH_RSP:
-      code = qWorkerProcessFetchRsp(pQnode, pQnode->pQuery, pMsg, ts);
-      break;
     case TDMT_SCH_CANCEL_TASK:
       code = qWorkerProcessCancelMsg(pQnode, pQnode->pQuery, pMsg, ts);
       break;

source/dnode/vnode/CMakeLists.txt

@@ -9,7 +9,6 @@ target_sources(
     "src/vnd/vnodeCfg.c"
     "src/vnd/vnodeCommit.c"
     "src/vnd/vnodeQuery.c"
-    "src/vnd/vnodeStateMgr.c"
     "src/vnd/vnodeModule.c"
     "src/vnd/vnodeSvr.c"
     "src/vnd/vnodeSync.c"
@@ -32,7 +31,6 @@ target_sources(
     "src/sma/smaUtil.c"
     "src/sma/smaOpen.c"
     "src/sma/smaCommit.c"
-    "src/sma/smaSnapshot.c"
     "src/sma/smaRollup.c"
     "src/sma/smaTimeRange.c"
 
@@ -43,7 +41,6 @@ target_sources(
     "src/tsdb/tsdbOpen.c"
     "src/tsdb/tsdbMemTable.c"
     "src/tsdb/tsdbRead.c"
-    "src/tsdb/tsdbReadImpl.c"
     "src/tsdb/tsdbCache.c"
     "src/tsdb/tsdbWrite.c"
     "src/tsdb/tsdbReaderWriter.c"

source/dnode/vnode/inc/vnode.h

@@ -64,8 +64,8 @@ int32_t vnodeSnapshotRead(SVSnapshotReader *pReader, const void **ppData, uint32
 int32_t vnodeProcessCreateTSma(SVnode *pVnode, void *pCont, uint32_t contLen);
 int32_t vnodeGetAllTableList(SVnode *pVnode, uint64_t uid, SArray *list);
 int32_t vnodeGetCtbIdList(SVnode *pVnode, int64_t suid, SArray *list);
-void *  vnodeGetIdx(SVnode *pVnode);
+void   *vnodeGetIdx(SVnode *pVnode);
-void *  vnodeGetIvtIdx(SVnode *pVnode);
+void   *vnodeGetIvtIdx(SVnode *pVnode);
 
 int32_t vnodeGetLoad(SVnode *pVnode, SVnodeLoad *pLoad);
 int32_t vnodeValidateTableHash(SVnode *pVnode, char *tableFName);
@@ -95,7 +95,7 @@ typedef struct SMetaFltParam {
   tb_uid_t suid;
   int16_t  cid;
   int16_t  type;
-  char *   val;
+  char    *val;
   bool     reverse;
   int (*filterFunc)(void *a, void *b, int16_t type);
 
@@ -131,34 +131,53 @@ int32_t tsdbReaderOpen(SVnode *pVnode, SQueryTableDataCond *pCond, SArray *pTabl
 void    tsdbReaderClose(STsdbReader *pReader);
 bool    tsdbNextDataBlock(STsdbReader *pReader);
 void    tsdbRetrieveDataBlockInfo(STsdbReader *pReader, SDataBlockInfo *pDataBlockInfo);
-int32_t tsdbRetrieveDataBlockStatisInfo(STsdbReader *pReader, SColumnDataAgg ***pBlockStatis, bool *allHave);
+int32_t tsdbRetrieveDatablockSMA(STsdbReader *pReader, SColumnDataAgg ***pBlockStatis, bool *allHave);
 SArray *tsdbRetrieveDataBlock(STsdbReader *pTsdbReadHandle, SArray *pColumnIdList);
 int32_t tsdbReaderReset(STsdbReader *pReader, SQueryTableDataCond *pCond, int32_t tWinIdx);
 int32_t tsdbGetFileBlocksDistInfo(STsdbReader *pReader, STableBlockDistInfo *pTableBlockInfo);
 int64_t tsdbGetNumOfRowsInMemTable(STsdbReader *pHandle);
-void *  tsdbGetIdx(SMeta *pMeta);
+void   *tsdbGetIdx(SMeta *pMeta);
-void *  tsdbGetIvtIdx(SMeta *pMeta);
+void   *tsdbGetIvtIdx(SMeta *pMeta);
 
 int32_t tsdbLastRowReaderOpen(void *pVnode, int32_t type, SArray *pTableIdList, int32_t *colId, int32_t numOfCols,
                               void **pReader);
 int32_t tsdbRetrieveLastRow(void *pReader, SSDataBlock *pResBlock, const int32_t *slotIds);
 int32_t tsdbLastrowReaderClose(void *pReader);
+int32_t tsdbGetTableSchema(SVnode* pVnode, int64_t uid, STSchema** pSchema, int64_t* suid);
 
 // tq
 
-typedef struct STqReadHandle SStreamReader;
+typedef struct STqReader {
+  int64_t           ver;
+  const SSubmitReq *pMsg;
+  SSubmitBlk       *pBlock;
+  SSubmitMsgIter    msgIter;
+  SSubmitBlkIter    blkIter;
 
-SStreamReader *tqInitSubmitMsgScanner(SMeta *pMeta);
+  SWalReader *pWalReader;
 
-void    tqReadHandleSetColIdList(SStreamReader *pReadHandle, SArray *pColIdList);
+  SMeta    *pVnodeMeta;
-int32_t tqReadHandleSetTbUidList(SStreamReader *pHandle, const SArray *tbUidList);
+  SHashObj *tbIdHash;
-int32_t tqReadHandleAddTbUidList(SStreamReader *pHandle, const SArray *tbUidList);
+  SArray   *pColIdList;  // SArray<int16_t>
-int32_t tqReadHandleRemoveTbUidList(SStreamReader *pHandle, const SArray *tbUidList);
 
-int32_t tqReadHandleSetMsg(SStreamReader *pHandle, SSubmitReq *pMsg, int64_t ver);
+  int32_t         cachedSchemaVer;
-bool    tqNextDataBlock(SStreamReader *pHandle);
+  int64_t         cachedSchemaSuid;
-bool    tqNextDataBlockFilterOut(SStreamReader *pHandle, SHashObj *filterOutUids);
+  SSchemaWrapper *pSchemaWrapper;
-int32_t tqRetrieveDataBlock(SSDataBlock *pBlock, SStreamReader *pHandle);
+  STSchema       *pSchema;
+} STqReader;
+
+STqReader *tqOpenReader(SVnode *pVnode);
+void       tqCloseReader(STqReader *);
+
+void    tqReaderSetColIdList(STqReader *pReader, SArray *pColIdList);
+int32_t tqReaderSetTbUidList(STqReader *pReader, const SArray *tbUidList);
+int32_t tqReaderAddTbUidList(STqReader *pReader, const SArray *tbUidList);
+int32_t tqReaderRemoveTbUidList(STqReader *pReader, const SArray *tbUidList);
+
+int32_t tqReaderSetDataMsg(STqReader *pReader, SSubmitReq *pMsg, int64_t ver);
+bool    tqNextDataBlock(STqReader *pReader);
+bool    tqNextDataBlockFilterOut(STqReader *pReader, SHashObj *filterOutUids);
+int32_t tqRetrieveDataBlock(SSDataBlock *pBlock, STqReader *pReader);
 
 // sma
 int32_t smaGetTSmaDays(SVnodeCfg *pCfg, void *pCont, uint32_t contLen, int32_t *days);
@@ -214,7 +233,7 @@ struct SMetaEntry {
   int8_t   type;
   int8_t   flags;  // TODO: need refactor?
   tb_uid_t uid;
-  char *   name;
+  char    *name;
   union {
     struct {
       SSchemaWrapper schemaRow;
@@ -225,7 +244,7 @@ struct SMetaEntry {
       int64_t  ctime;
       int32_t  ttlDays;
       int32_t  commentLen;
-      char *   comment;
+      char    *comment;
       tb_uid_t suid;
       uint8_t *pTags;
     } ctbEntry;
@@ -233,7 +252,7 @@ struct SMetaEntry {
       int64_t        ctime;
       int32_t        ttlDays;
       int32_t        commentLen;
-      char *         comment;
+      char          *comment;
       int32_t        ncid;  // next column id
       SSchemaWrapper schemaRow;
     } ntbEntry;
@@ -247,17 +266,17 @@ struct SMetaEntry {
 
 struct SMetaReader {
   int32_t    flags;
-  SMeta *    pMeta;
+  SMeta     *pMeta;
   SDecoder   coder;
   SMetaEntry me;
-  void *     pBuf;
+  void      *pBuf;
   int32_t    szBuf;
 };
 
 struct SMTbCursor {
-  TBC *       pDbc;
+  TBC        *pDbc;
-  void *      pKey;
+  void       *pKey;
-  void *      pVal;
+  void       *pVal;
   int32_t     kLen;
   int32_t     vLen;
   SMetaReader mr;

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

@@ -40,38 +40,10 @@ extern "C" {
 #define tqDebug(...) do { if (tqDebugFlag & DEBUG_DEBUG) { taosPrintLog("TQ  ", DEBUG_DEBUG, tqDebugFlag, __VA_ARGS__); }} while(0)
 #define tqTrace(...) do { if (tqDebugFlag & DEBUG_TRACE) { taosPrintLog("TQ  ", DEBUG_TRACE, tqDebugFlag, __VA_ARGS__); }} while(0)
 
-#define IS_META_MSG(x) ( \
-     x == TDMT_VND_CREATE_STB     \
-  || x == TDMT_VND_ALTER_STB      \
-  || x == TDMT_VND_DROP_STB       \
-  || x == TDMT_VND_CREATE_TABLE   \
-  || x == TDMT_VND_ALTER_TABLE    \
-  || x == TDMT_VND_DROP_TABLE     \
-  || x == TDMT_VND_DROP_TTL_TABLE \
-)
 // clang-format on
 
 typedef struct STqOffsetStore STqOffsetStore;
 
-// tqRead
-
-struct STqReadHandle {
-  int64_t           ver;
-  const SSubmitReq* pMsg;
-  SSubmitBlk*       pBlock;
-  SSubmitMsgIter    msgIter;
-  SSubmitBlkIter    blkIter;
-
-  SMeta*    pVnodeMeta;
-  SHashObj* tbIdHash;
-  SArray*   pColIdList;  // SArray<int16_t>
-
-  int32_t         cachedSchemaVer;
-  int64_t         cachedSchemaSuid;
-  SSchemaWrapper* pSchemaWrapper;
-  STSchema*       pSchema;
-};
-
 // tqPush
 
 typedef struct {
@@ -111,7 +83,7 @@ typedef struct {
 typedef struct {
   int8_t subType;
 
-  SStreamReader* pExecReader[5];
+  STqReader* pExecReader[5];
   union {
     STqExecCol execCol;
     STqExecTb  execTb;
@@ -127,8 +99,8 @@ typedef struct {
   int32_t epoch;
   int8_t  fetchMeta;
 
-  // reader
+  // TODO remove
-  SWalReadHandle* pWalReader;
+  SWalReader* pWalReader;
 
   // push
   STqPushHandle pushHandle;

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

@@ -245,6 +245,8 @@ int32_t tsdbCacheRelease(SLRUCache *pCache, LRUHandle *h);
 
 int32_t tsdbCacheDelete(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey);
 
+int32_t tsdbCacheLastArray2Row(SArray *pLastArray, STSRow **ppRow, STSchema *pSchema);
+
 // structs =======================
 typedef struct {
   int   minFid;

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

@@ -439,6 +439,7 @@ int32_t metaGetTbTSchemaEx(SMeta *pMeta, tb_uid_t suid, tb_uid_t uid, int32_t sv
   tDecoderInit(&dc, pData, nData);
   tDecodeSSchemaWrapper(&dc, pSchemaWrapper);
   tDecoderClear(&dc);
+  tdbFree(pData);
 
   // convert
   STSchemaBuilder sb = {0};

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

@@ -16,6 +16,7 @@
 #include "meta.h"
 
 static int metaSaveJsonVarToIdx(SMeta *pMeta, const SMetaEntry *pCtbEntry, const SSchema *pSchema);
+static int metaDelJsonVarFromIdx(SMeta *pMeta, const SMetaEntry *pCtbEntry, const SSchema *pSchema);
 static int metaHandleEntry(SMeta *pMeta, const SMetaEntry *pME);
 static int metaSaveToTbDb(SMeta *pMeta, const SMetaEntry *pME);
 static int metaUpdateUidIdx(SMeta *pMeta, const SMetaEntry *pME);
@@ -92,7 +93,65 @@ static int metaSaveJsonVarToIdx(SMeta *pMeta, const SMetaEntry *pCtbEntry, const
     } else if (type == TSDB_DATA_TYPE_BOOL) {
       int val = *(int *)(&pTagVal->i64);
       int len = sizeof(val);
-      term = indexTermCreate(suid, ADD_VALUE, TSDB_DATA_TYPE_INT, key, nKey, (const char *)&val, len);
+      term = indexTermCreate(suid, ADD_VALUE, TSDB_DATA_TYPE_BOOL, key, nKey, (const char *)&val, len);
+    }
+    if (term != NULL) {
+      indexMultiTermAdd(terms, term);
+    }
+  }
+  indexJsonPut(pMeta->pTagIvtIdx, terms, tuid);
+  indexMultiTermDestroy(terms);
+#endif
+  return 0;
+}
+int metaDelJsonVarFromIdx(SMeta *pMeta, const SMetaEntry *pCtbEntry, const SSchema *pSchema) {
+#ifdef USE_INVERTED_INDEX
+  if (pMeta->pTagIvtIdx == NULL || pCtbEntry == NULL) {
+    return -1;
+  }
+  void *      data = pCtbEntry->ctbEntry.pTags;
+  const char *tagName = pSchema->name;
+
+  tb_uid_t    suid = pCtbEntry->ctbEntry.suid;
+  tb_uid_t    tuid = pCtbEntry->uid;
+  const void *pTagData = pCtbEntry->ctbEntry.pTags;
+  int32_t     nTagData = 0;
+
+  SArray *pTagVals = NULL;
+  if (tTagToValArray((const STag *)data, &pTagVals) != 0) {
+    return -1;
+  }
+
+  SIndexMultiTerm *terms = indexMultiTermCreate();
+  int16_t          nCols = taosArrayGetSize(pTagVals);
+  for (int i = 0; i < nCols; i++) {
+    STagVal *pTagVal = (STagVal *)taosArrayGet(pTagVals, i);
+    char     type = pTagVal->type;
+
+    char *  key = pTagVal->pKey;
+    int32_t nKey = strlen(key);
+
+    SIndexTerm *term = NULL;
+    if (type == TSDB_DATA_TYPE_NULL) {
+      term = indexTermCreate(suid, DEL_VALUE, TSDB_DATA_TYPE_VARCHAR, key, nKey, NULL, 0);
+    } else if (type == TSDB_DATA_TYPE_NCHAR) {
+      if (pTagVal->nData > 0) {
+        char *  val = taosMemoryCalloc(1, pTagVal->nData + VARSTR_HEADER_SIZE);
+        int32_t len = taosUcs4ToMbs((TdUcs4 *)pTagVal->pData, pTagVal->nData, val + VARSTR_HEADER_SIZE);
+        memcpy(val, (uint16_t *)&len, VARSTR_HEADER_SIZE);
+        type = TSDB_DATA_TYPE_VARCHAR;
+        term = indexTermCreate(suid, DEL_VALUE, type, key, nKey, val, len);
+      } else if (pTagVal->nData == 0) {
+        term = indexTermCreate(suid, DEL_VALUE, TSDB_DATA_TYPE_VARCHAR, key, nKey, pTagVal->pData, 0);
+      }
+    } else if (type == TSDB_DATA_TYPE_DOUBLE) {
+      double val = *(double *)(&pTagVal->i64);
+      int    len = sizeof(val);
+      term = indexTermCreate(suid, DEL_VALUE, type, key, nKey, (const char *)&val, len);
+    } else if (type == TSDB_DATA_TYPE_BOOL) {
+      int val = *(int *)(&pTagVal->i64);
+      int len = sizeof(val);
+      term = indexTermCreate(suid, DEL_VALUE, TSDB_DATA_TYPE_BOOL, key, nKey, (const char *)&val, len);
     }
     if (term != NULL) {
       indexMultiTermAdd(terms, term);
@@ -434,9 +493,33 @@ static int metaDropTableByUid(SMeta *pMeta, tb_uid_t uid, int *type) {
 
   if (type) *type = e.type;
 
+  if (e.type == TSDB_CHILD_TABLE) {
+    void *tData = NULL;
+    int   tLen = 0;
+
+    if (tdbTbGet(pMeta->pUidIdx, &e.ctbEntry.suid, sizeof(tb_uid_t), &tData, &tLen) == 0) {
+      version = *(int64_t *)tData;
+      STbDbKey tbDbKey = {.uid = e.ctbEntry.suid, .version = version};
+      if (tdbTbGet(pMeta->pTbDb, &tbDbKey, sizeof(tbDbKey), &tData, &tLen) == 0) {
+        SDecoder   tdc = {0};
+        SMetaEntry stbEntry = {0};
+
+        tDecoderInit(&tdc, tData, tLen);
+        metaDecodeEntry(&tdc, &stbEntry);
+        const SSchema *pTagColumn = &stbEntry.stbEntry.schemaTag.pSchema[0];
+        if (pTagColumn->type == TSDB_DATA_TYPE_JSON) {
+          metaDelJsonVarFromIdx(pMeta, &e, pTagColumn);
+        }
+        tDecoderClear(&tdc);
+      }
+      tdbFree(tData);
+    }
+  }
+
   tdbTbDelete(pMeta->pTbDb, &(STbDbKey){.version = version, .uid = uid}, sizeof(STbDbKey), &pMeta->txn);
   tdbTbDelete(pMeta->pNameIdx, e.name, strlen(e.name) + 1, &pMeta->txn);
   tdbTbDelete(pMeta->pUidIdx, &uid, sizeof(uid), &pMeta->txn);
+
   if (e.type != TSDB_SUPER_TABLE) metaDeleteTtlIdx(pMeta, &e);
 
   if (e.type == TSDB_CHILD_TABLE) {

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

@@ -277,6 +277,9 @@ static int32_t tdSetRSmaInfoItemParams(SSma *pSma, SRSmaParam *param, SRSmaInfo
       pItem->maxDelay = TSDB_MAX_ROLLUP_MAX_DELAY;
     }
     pItem->level = (idx == 0 ? TSDB_RETENTION_L1 : TSDB_RETENTION_L2);
+    smaInfo("vgId:%d table:%" PRIi64 " level:%" PRIi8 " maxdelay:%" PRIi64 " watermark:%" PRIi64
+            ", finally maxdelay:%" PRIi32,
+            SMA_VID(pSma), pRSmaInfo->suid, idx + 1, param->maxdelay[idx], param->watermark[idx], pItem->maxDelay);
   }
   return TSDB_CODE_SUCCESS;
 _err:
@@ -325,14 +328,14 @@ int32_t tdProcessRSmaCreateImpl(SSma *pSma, SRSmaParam *param, int64_t suid, con
     return TSDB_CODE_FAILED;
   }
 
-  SStreamReader *pReadHandle = tqInitSubmitMsgScanner(pMeta);
+  STqReader *pReader = tqOpenReader(pVnode);
-  if (!pReadHandle) {
+  if (!pReader) {
     terrno = TSDB_CODE_OUT_OF_MEMORY;
     goto _err;
   }
 
   SReadHandle handle = {
-      .reader = pReadHandle,
+      .tqReader = pReader,
       .meta = pMeta,
       .pMsgCb = pMsgCb,
       .vnode = pVnode,
@@ -364,7 +367,7 @@ int32_t tdProcessRSmaCreateImpl(SSma *pSma, SRSmaParam *param, int64_t suid, con
   return TSDB_CODE_SUCCESS;
 _err:
   tdFreeRSmaInfo(pRSmaInfo);
-  taosMemoryFree(pReadHandle);
+  taosMemoryFree(pReader);
   return TSDB_CODE_FAILED;
 }
 
@@ -570,11 +573,15 @@ static int32_t tdFetchAndSubmitRSmaResult(SRSmaInfoItem *pItem, int8_t blkType)
     SSubmitReq *pReq = NULL;
     // TODO: the schema update should be handled
     if (buildSubmitReqFromDataBlock(&pReq, pResult, pRSmaInfo->pTSchema, SMA_VID(pSma), pRSmaInfo->suid) < 0) {
+      smaError("vgId:%d, build submit req for rsma table %" PRIi64 "l evel %" PRIi8 " failed since %s", SMA_VID(pSma),
+               pRSmaInfo->suid, pItem->level, terrstr());
       goto _err;
     }
 
     if (pReq && tdProcessSubmitReq(sinkTsdb, atomic_add_fetch_64(&pRSmaInfo->pStat->submitVer, 1), pReq) < 0) {
       taosMemoryFreeClear(pReq);
+      smaError("vgId:%d, process submit req for rsma table %" PRIi64 " level %" PRIi8 " failed since %s", SMA_VID(pSma),
+               pRSmaInfo->suid, pItem->level, terrstr());
       goto _err;
     }
 

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

@@ -1,16 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "sma.h"

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

@@ -28,8 +28,12 @@ int32_t tqInit() {
       atomic_store_8(&tqMgmt.inited, 0);
       return -1;
     }
+    if (streamInit() < 0) {
+      return -1;
+    }
     atomic_store_8(&tqMgmt.inited, 1);
   }
+
   return 0;
 }
 
@@ -42,6 +46,7 @@ void tqCleanUp() {
 
   if (old == 1) {
     taosTmrCleanUp(tqMgmt.timer);
+    streamCleanUp();
     atomic_store_8(&tqMgmt.inited, 0);
   }
 }
@@ -144,7 +149,6 @@ int32_t tqSendDataRsp(STQ* pTq, const SRpcMsg* pMsg, const SMqPollReq* pReq, con
   SEncoder encoder;
   tEncoderInit(&encoder, abuf, len);
   tEncodeSMqDataRsp(&encoder, pRsp);
-  /*tEncodeSMqDataBlkRsp(&abuf, pRsp);*/
 
   SRpcMsg rsp = {
       .info = pMsg->info,
@@ -361,8 +365,11 @@ int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
         ASSERT(IS_META_MSG(pHead->msgType));
         tqInfo("fetch meta msg, ver: %ld, type: %d", pHead->version, pHead->msgType);
         SMqMetaRsp metaRsp = {0};
-        metaRsp.reqOffset = pReq->reqOffset.version;
+        /*metaRsp.reqOffset = pReq->reqOffset.version;*/
-        metaRsp.rspOffset = fetchVer;
+        /*metaRsp.rspOffset = fetchVer;*/
+        /*metaRsp.rspOffsetNew.version = fetchVer;*/
+        tqOffsetResetToLog(&metaRsp.reqOffsetNew, pReq->reqOffset.version);
+        tqOffsetResetToLog(&metaRsp.rspOffsetNew, fetchVer);
         metaRsp.resMsgType = pHead->msgType;
         metaRsp.metaRspLen = pHead->bodyLen;
         metaRsp.metaRsp = pHead->body;
@@ -439,27 +446,39 @@ int32_t tqProcessVgChangeReq(STQ* pTq, char* msg, int32_t msgLen) {
     pHandle->execHandle.subType = req.subType;
     pHandle->fetchMeta = req.withMeta;
 
-    pHandle->pWalReader = walOpenReadHandle(pTq->pVnode->pWal);
+    pHandle->pWalReader = walOpenReader(pTq->pVnode->pWal, NULL);
-    for (int32_t i = 0; i < 5; i++) {
+    /*for (int32_t i = 0; i < 5; i++) {*/
-      pHandle->execHandle.pExecReader[i] = tqInitSubmitMsgScanner(pTq->pVnode->pMeta);
+    /*pHandle->execHandle.pExecReader[i] = tqOpenReader(pTq->pVnode);*/
-    }
+    /*}*/
     if (pHandle->execHandle.subType == TOPIC_SUB_TYPE__COLUMN) {
       pHandle->execHandle.execCol.qmsg = req.qmsg;
       req.qmsg = NULL;
       for (int32_t i = 0; i < 5; i++) {
         SReadHandle handle = {
-            .reader = pHandle->execHandle.pExecReader[i],
+            .tqReader = pHandle->execHandle.pExecReader[i],
             .meta = pTq->pVnode->pMeta,
             .vnode = pTq->pVnode,
-            .tqReader = true,
+            .initTableReader = true,
+            .initTqReader = true,
         };
         pHandle->execHandle.execCol.task[i] = qCreateStreamExecTaskInfo(pHandle->execHandle.execCol.qmsg, &handle);
         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]);
       }
     } 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.execDb.pFilterOutTbUid =
           taosHashInit(64, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BIGINT), false, HASH_NO_LOCK);
     } else if (pHandle->execHandle.subType == TOPIC_SUB_TYPE__TABLE) {
+      for (int32_t i = 0; i < 5; i++) {
+        pHandle->execHandle.pExecReader[i] = tqOpenReader(pTq->pVnode);
+      }
       pHandle->execHandle.execTb.suid = req.suid;
       SArray* tbUidList = taosArrayInit(0, sizeof(int64_t));
       vnodeGetCtbIdList(pTq->pVnode, req.suid, tbUidList);
@@ -469,7 +488,7 @@ int32_t tqProcessVgChangeReq(STQ* pTq, char* msg, int32_t msgLen) {
         tqDebug("vg %d, idx %d, uid: %ld", TD_VID(pTq->pVnode), i, tbUid);
       }
       for (int32_t i = 0; i < 5; i++) {
-        tqReadHandleSetTbUidList(pHandle->execHandle.pExecReader[i], tbUidList);
+        tqReaderSetTbUidList(pHandle->execHandle.pExecReader[i], tbUidList);
       }
       taosArrayDestroy(tbUidList);
     }
@@ -522,19 +541,16 @@ int32_t tqProcessTaskDeployReq(STQ* pTq, char* msg, int32_t msgLen) {
   if (pTask->execType != TASK_EXEC__NONE) {
     // expand runners
     if (pTask->isDataScan) {
-      SStreamReader* pStreamReader = tqInitSubmitMsgScanner(pTq->pVnode->pMeta);
+      SReadHandle handle = {
-      SReadHandle    handle = {
+          .meta = pTq->pVnode->pMeta,
-             .reader = pStreamReader,
+          .vnode = pTq->pVnode,
-             .meta = pTq->pVnode->pMeta,
+          .initTqReader = 1,
-             .vnode = pTq->pVnode,
       };
-      /*pTask->exec.inputHandle = pStreamReader;*/
       pTask->exec.executor = qCreateStreamExecTaskInfo(pTask->exec.qmsg, &handle);
-      ASSERT(pTask->exec.executor);
     } else {
       pTask->exec.executor = qCreateStreamExecTaskInfo(pTask->exec.qmsg, NULL);
-      ASSERT(pTask->exec.executor);
     }
+    ASSERT(pTask->exec.executor);
   }
 
   // sink

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

@@ -135,8 +135,8 @@ int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataR
     }
   } else if (pExec->subType == TOPIC_SUB_TYPE__TABLE) {
     pRsp->withSchema = 1;
-    SStreamReader* pReader = pExec->pExecReader[workerId];
+    STqReader* pReader = pExec->pExecReader[workerId];
-    tqReadHandleSetMsg(pReader, pReq, 0);
+    tqReaderSetDataMsg(pReader, pReq, 0);
     while (tqNextDataBlock(pReader)) {
       SSDataBlock block = {0};
       if (tqRetrieveDataBlock(&block, pReader) < 0) {
@@ -153,8 +153,8 @@ int32_t tqLogScanExec(STQ* pTq, STqExecHandle* pExec, SSubmitReq* pReq, SMqDataR
     }
   } else if (pExec->subType == TOPIC_SUB_TYPE__DB) {
     pRsp->withSchema = 1;
-    SStreamReader* pReader = pExec->pExecReader[workerId];
+    STqReader* pReader = pExec->pExecReader[workerId];
-    tqReadHandleSetMsg(pReader, pReq, 0);
+    tqReaderSetDataMsg(pReader, pReq, 0);
     while (tqNextDataBlockFilterOut(pReader, pExec->execDb.pFilterOutTbUid)) {
       SSDataBlock block = {0};
       if (tqRetrieveDataBlock(&block, pReader) < 0) {

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

@@ -77,14 +77,14 @@ int32_t tqMetaOpen(STQ* pTq) {
     STqHandle handle;
     tDecoderInit(&decoder, (uint8_t*)pVal, vLen);
     tDecodeSTqHandle(&decoder, &handle);
-    handle.pWalReader = walOpenReadHandle(pTq->pVnode->pWal);
+    handle.pWalReader = walOpenReader(pTq->pVnode->pWal, NULL);
     for (int32_t i = 0; i < 5; i++) {
-      handle.execHandle.pExecReader[i] = tqInitSubmitMsgScanner(pTq->pVnode->pMeta);
+      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 = {
-            .reader = handle.execHandle.pExecReader[i],
+            .tqReader = handle.execHandle.pExecReader[i],
             .meta = pTq->pVnode->pMeta,
             .pMsgCb = &pTq->pVnode->msgCb,
             .vnode = pTq->pVnode,

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

@@ -15,6 +15,11 @@
 
 #include "tq.h"
 
+int64_t tqScanLog(STQ* pTq, const STqExecHandle* pExec, SMqDataRsp* pRsp, STqOffsetVal offset) {
+  /*if ()*/
+  return 0;
+}
+
 int64_t tqFetchLog(STQ* pTq, STqHandle* pHandle, int64_t* fetchOffset, SWalCkHead** ppCkHead) {
   int32_t code = 0;
   taosThreadMutexLock(&pHandle->pWalReader->mutex);
@@ -73,53 +78,107 @@ END:
   return code;
 }
 
-SStreamReader* tqInitSubmitMsgScanner(SMeta* pMeta) {
+STqReader* tqOpenReader(SVnode* pVnode) {
-  SStreamReader* pReadHandle = taosMemoryMalloc(sizeof(SStreamReader));
+  STqReader* pReader = taosMemoryMalloc(sizeof(STqReader));
-  if (pReadHandle == NULL) {
+  if (pReader == NULL) {
     return NULL;
   }
-  pReadHandle->pVnodeMeta = pMeta;
+
-  pReadHandle->pMsg = NULL;
+  // TODO open
-  pReadHandle->ver = -1;
+  /*pReader->pWalReader = walOpenReader(pVnode->pWal, NULL);*/
-  pReadHandle->pColIdList = NULL;
+
-  pReadHandle->cachedSchemaVer = 0;
+  pReader->pVnodeMeta = pVnode->pMeta;
-  pReadHandle->cachedSchemaSuid = 0;
+  pReader->pMsg = NULL;
-  pReadHandle->pSchema = NULL;
+  pReader->ver = -1;
-  pReadHandle->pSchemaWrapper = NULL;
+  pReader->pColIdList = NULL;
-  pReadHandle->tbIdHash = NULL;
+  pReader->cachedSchemaVer = 0;
-  return pReadHandle;
+  pReader->cachedSchemaSuid = 0;
+  pReader->pSchema = NULL;
+  pReader->pSchemaWrapper = NULL;
+  pReader->tbIdHash = NULL;
+  return pReader;
 }
 
-int32_t tqReadHandleSetMsg(SStreamReader* pReadHandle, SSubmitReq* pMsg, int64_t ver) {
+void tqCloseReader(STqReader* pReader) {
-  pReadHandle->pMsg = pMsg;
+  // close wal reader
+  // free cached schema
+  // free hash
+  taosMemoryFree(pReader);
+}
 
-  if (tInitSubmitMsgIter(pMsg, &pReadHandle->msgIter) < 0) return -1;
+int32_t tqNextBlock(STqReader* pReader, SFetchRet* ret) {
+  bool fromProcessedMsg = pReader->pMsg != NULL;
+
+  while (1) {
+    if (!fromProcessedMsg) {
+      if (walNextValidMsg(pReader->pWalReader) < 0) {
+        ret->fetchType = FETCH_TYPE__NONE;
+        return -1;
+      }
+      void* body = pReader->pWalReader->pHead->head.body;
+      if (pReader->pWalReader->pHead->head.msgType != TDMT_VND_SUBMIT) {
+        // TODO do filter
+        ret->fetchType = FETCH_TYPE__META;
+        ret->meta = pReader->pWalReader->pHead->head.body;
+        return 0;
+      } else {
+        tqReaderSetDataMsg(pReader, body, pReader->pWalReader->pHead->head.version);
+      }
+    }
+
+    while (tqNextDataBlock(pReader)) {
+      memset(&ret->data, 0, sizeof(SSDataBlock));
+      int32_t code = tqRetrieveDataBlock(&ret->data, pReader);
+      if (code != 0 || ret->data.info.rows == 0) {
+        if (fromProcessedMsg) {
+          ret->fetchType = FETCH_TYPE__NONE;
+          return 0;
+        } else {
+          break;
+        }
+      }
+
+      ret->fetchType = FETCH_TYPE__DATA;
+      return 0;
+    }
+
+    if (fromProcessedMsg) {
+      ret->fetchType = FETCH_TYPE__NONE;
+      return 0;
+    }
+  }
+}
+
+int32_t tqReaderSetDataMsg(STqReader* pReader, SSubmitReq* pMsg, int64_t ver) {
+  pReader->pMsg = pMsg;
+
+  if (tInitSubmitMsgIter(pMsg, &pReader->msgIter) < 0) return -1;
   while (true) {
-    if (tGetSubmitMsgNext(&pReadHandle->msgIter, &pReadHandle->pBlock) < 0) return -1;
+    if (tGetSubmitMsgNext(&pReader->msgIter, &pReader->pBlock) < 0) return -1;
-    if (pReadHandle->pBlock == NULL) break;
+    if (pReader->pBlock == NULL) break;
   }
 
-  if (tInitSubmitMsgIter(pMsg, &pReadHandle->msgIter) < 0) return -1;
+  if (tInitSubmitMsgIter(pMsg, &pReader->msgIter) < 0) return -1;
-  pReadHandle->ver = ver;
+  pReader->ver = ver;
-  memset(&pReadHandle->blkIter, 0, sizeof(SSubmitBlkIter));
+  memset(&pReader->blkIter, 0, sizeof(SSubmitBlkIter));
   return 0;
 }
 
-bool tqNextDataBlock(SStreamReader* pHandle) {
+bool tqNextDataBlock(STqReader* pReader) {
-  if (pHandle->pMsg == NULL) return false;
+  if (pReader->pMsg == NULL) return false;
   while (1) {
-    if (tGetSubmitMsgNext(&pHandle->msgIter, &pHandle->pBlock) < 0) {
+    if (tGetSubmitMsgNext(&pReader->msgIter, &pReader->pBlock) < 0) {
       return false;
     }
-    if (pHandle->pBlock == NULL) {
+    if (pReader->pBlock == NULL) {
-      pHandle->pMsg = NULL;
+      pReader->pMsg = NULL;
       return false;
     }
 
-    if (pHandle->tbIdHash == NULL) {
+    if (pReader->tbIdHash == NULL) {
       return true;
     }
-    void* ret = taosHashGet(pHandle->tbIdHash, &pHandle->msgIter.uid, sizeof(int64_t));
+    void* ret = taosHashGet(pReader->tbIdHash, &pReader->msgIter.uid, sizeof(int64_t));
     /*tqDebug("search uid %ld", pHandle->msgIter.uid);*/
     if (ret != NULL) {
       /*tqDebug("find   uid %ld", pHandle->msgIter.uid);*/
@@ -129,7 +188,7 @@ bool tqNextDataBlock(SStreamReader* pHandle) {
   return false;
 }
 
-bool tqNextDataBlockFilterOut(SStreamReader* pHandle, SHashObj* filterOutUids) {
+bool tqNextDataBlockFilterOut(STqReader* pHandle, SHashObj* filterOutUids) {
   while (1) {
     if (tGetSubmitMsgNext(&pHandle->msgIter, &pHandle->pBlock) < 0) {
       return false;
@@ -145,38 +204,38 @@ bool tqNextDataBlockFilterOut(SStreamReader* pHandle, SHashObj* filterOutUids) {
   return false;
 }
 
-int32_t tqRetrieveDataBlock(SSDataBlock* pBlock, SStreamReader* pHandle) {
+int32_t tqRetrieveDataBlock(SSDataBlock* pBlock, STqReader* pReader) {
   // TODO: cache multiple schema
-  int32_t sversion = htonl(pHandle->pBlock->sversion);
+  int32_t sversion = htonl(pReader->pBlock->sversion);
-  if (pHandle->cachedSchemaSuid == 0 || pHandle->cachedSchemaVer != sversion ||
+  if (pReader->cachedSchemaSuid == 0 || pReader->cachedSchemaVer != sversion ||
-      pHandle->cachedSchemaSuid != pHandle->msgIter.suid) {
+      pReader->cachedSchemaSuid != pReader->msgIter.suid) {
-    if (pHandle->pSchema) taosMemoryFree(pHandle->pSchema);
+    if (pReader->pSchema) taosMemoryFree(pReader->pSchema);
-    pHandle->pSchema = metaGetTbTSchema(pHandle->pVnodeMeta, pHandle->msgIter.uid, sversion);
+    pReader->pSchema = metaGetTbTSchema(pReader->pVnodeMeta, pReader->msgIter.uid, sversion);
-    if (pHandle->pSchema == NULL) {
+    if (pReader->pSchema == NULL) {
       tqWarn("cannot found tsschema for table: uid: %ld (suid: %ld), version %d, possibly dropped table",
-             pHandle->msgIter.uid, pHandle->msgIter.suid, pHandle->cachedSchemaVer);
+             pReader->msgIter.uid, pReader->msgIter.suid, pReader->cachedSchemaVer);
       /*ASSERT(0);*/
       terrno = TSDB_CODE_TQ_TABLE_SCHEMA_NOT_FOUND;
       return -1;
     }
 
-    if (pHandle->pSchemaWrapper) tDeleteSSchemaWrapper(pHandle->pSchemaWrapper);
+    if (pReader->pSchemaWrapper) tDeleteSSchemaWrapper(pReader->pSchemaWrapper);
-    pHandle->pSchemaWrapper = metaGetTableSchema(pHandle->pVnodeMeta, pHandle->msgIter.uid, sversion, true);
+    pReader->pSchemaWrapper = metaGetTableSchema(pReader->pVnodeMeta, pReader->msgIter.uid, sversion, true);
-    if (pHandle->pSchemaWrapper == NULL) {
+    if (pReader->pSchemaWrapper == NULL) {
       tqWarn("cannot found schema wrapper for table: suid: %ld, version %d, possibly dropped table",
-             pHandle->msgIter.uid, pHandle->cachedSchemaVer);
+             pReader->msgIter.uid, pReader->cachedSchemaVer);
       /*ASSERT(0);*/
       terrno = TSDB_CODE_TQ_TABLE_SCHEMA_NOT_FOUND;
       return -1;
     }
-    pHandle->cachedSchemaVer = sversion;
+    pReader->cachedSchemaVer = sversion;
-    pHandle->cachedSchemaSuid = pHandle->msgIter.suid;
+    pReader->cachedSchemaSuid = pReader->msgIter.suid;
   }
 
-  STSchema*       pTschema = pHandle->pSchema;
+  STSchema*       pTschema = pReader->pSchema;
-  SSchemaWrapper* pSchemaWrapper = pHandle->pSchemaWrapper;
+  SSchemaWrapper* pSchemaWrapper = pReader->pSchemaWrapper;
 
-  int32_t colNumNeed = taosArrayGetSize(pHandle->pColIdList);
+  int32_t colNumNeed = taosArrayGetSize(pReader->pColIdList);
 
   if (colNumNeed == 0) {
     int32_t colMeta = 0;
@@ -199,7 +258,7 @@ int32_t tqRetrieveDataBlock(SSDataBlock* pBlock, SStreamReader* pHandle) {
     while (colMeta < pSchemaWrapper->nCols && colNeed < colNumNeed) {
       SSchema* pColSchema = &pSchemaWrapper->pSchema[colMeta];
       col_id_t colIdSchema = pColSchema->colId;
-      col_id_t colIdNeed = *(col_id_t*)taosArrayGet(pHandle->pColIdList, colNeed);
+      col_id_t colIdNeed = *(col_id_t*)taosArrayGet(pReader->pColIdList, colNeed);
       if (colIdSchema < colIdNeed) {
         colMeta++;
       } else if (colIdSchema > colIdNeed) {
@@ -216,7 +275,7 @@ int32_t tqRetrieveDataBlock(SSDataBlock* pBlock, SStreamReader* pHandle) {
     }
   }
 
-  if (blockDataEnsureCapacity(pBlock, pHandle->msgIter.numOfRows) < 0) {
+  if (blockDataEnsureCapacity(pBlock, pReader->msgIter.numOfRows) < 0) {
     goto FAIL;
   }
 
@@ -227,13 +286,12 @@ int32_t tqRetrieveDataBlock(SSDataBlock* pBlock, SStreamReader* pHandle) {
   STSRow* row;
   int32_t curRow = 0;
 
-  tInitSubmitBlkIter(&pHandle->msgIter, pHandle->pBlock, &pHandle->blkIter);
+  tInitSubmitBlkIter(&pReader->msgIter, pReader->pBlock, &pReader->blkIter);
 
-  pBlock->info.groupId = 0;
+  pBlock->info.uid = pReader->msgIter.uid;
-  pBlock->info.uid = pHandle->msgIter.uid;
+  pBlock->info.rows = pReader->msgIter.numOfRows;
-  pBlock->info.rows = pHandle->msgIter.numOfRows;
 
-  while ((row = tGetSubmitBlkNext(&pHandle->blkIter)) != NULL) {
+  while ((row = tGetSubmitBlkNext(&pReader->blkIter)) != NULL) {
     tdSTSRowIterReset(&iter, row);
     // get all wanted col of that block
     for (int32_t i = 0; i < colActual; i++) {
@@ -255,9 +313,9 @@ FAIL:
   return -1;
 }
 
-void tqReadHandleSetColIdList(SStreamReader* pReadHandle, SArray* pColIdList) { pReadHandle->pColIdList = pColIdList; }
+void tqReaderSetColIdList(STqReader* pReadHandle, SArray* pColIdList) { pReadHandle->pColIdList = pColIdList; }
 
-int tqReadHandleSetTbUidList(SStreamReader* pHandle, const SArray* tbUidList) {
+int tqReaderSetTbUidList(STqReader* pHandle, const SArray* tbUidList) {
   if (pHandle->tbIdHash) {
     taosHashClear(pHandle->tbIdHash);
   }
@@ -276,7 +334,7 @@ int tqReadHandleSetTbUidList(SStreamReader* pHandle, const SArray* tbUidList) {
   return 0;
 }
 
-int tqReadHandleAddTbUidList(SStreamReader* pHandle, const SArray* tbUidList) {
+int tqReaderAddTbUidList(STqReader* pHandle, const SArray* tbUidList) {
   if (pHandle->tbIdHash == NULL) {
     pHandle->tbIdHash = taosHashInit(64, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BIGINT), true, HASH_NO_LOCK);
     if (pHandle->tbIdHash == NULL) {
@@ -293,7 +351,7 @@ int tqReadHandleAddTbUidList(SStreamReader* pHandle, const SArray* tbUidList) {
   return 0;
 }
 
-int tqReadHandleRemoveTbUidList(SStreamReader* pHandle, const SArray* tbUidList) {
+int tqReaderRemoveTbUidList(STqReader* pHandle, const SArray* tbUidList) {
   ASSERT(pHandle->tbIdHash != NULL);
 
   for (int32_t i = 0; i < taosArrayGetSize(tbUidList); i++) {

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

@@ -59,6 +59,8 @@ static void getTableCacheKey(tb_uid_t uid, int cacheType, char *key, int *len) {
 
 static void deleteTableCacheLastrow(const void *key, size_t keyLen, void *value) { taosMemoryFree(value); }
 
+static void deleteTableCacheLast(const void *key, size_t keyLen, void *value) { taosArrayDestroy(value); }
+
 static int32_t tsdbCacheDeleteLastrow(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
   int32_t code = 0;
   char    key[32] = {0};
@@ -309,9 +311,11 @@ static int32_t getTableDelIdx(SDelFReader *pDelFReader, tb_uid_t suid, tb_uid_t
   if (code) goto _err;
 
   // code = tMapDataSearch(&delIdxMap, &idx, tGetDelIdx, tCmprDelIdx, pDelIdx);
-  pDelIdx = taosArraySearch(pDelIdxArray, &idx, tCmprDelIdx, TD_EQ);
+  SDelIdx *pIdx = taosArraySearch(pDelIdxArray, &idx, tCmprDelIdx, TD_EQ);
   if (code) goto _err;
 
+  *pDelIdx = *pIdx;
+
   if (pDelIdxArray) {
     taosArrayDestroy(pDelIdxArray);
   }
@@ -759,7 +763,6 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo
     for (int i = 0; i < nMax; ++i) {
       TSDBKEY maxKey = TSDBROW_KEY(max[i]);
 
-      // bool deleted = false;
       bool deleted = tsdbKeyDeleted(&maxKey, pSkyline, &iSkyline);
       if (!deleted) {
         // iMerge[nMerge] = i;
@@ -816,12 +819,22 @@ _err:
   return code;
 }
 
-static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
+typedef struct {
-  int32_t code = 0;
+  TSKEY   ts;
+  SColVal colVal;
+} SLastCol;
+
+// static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
+static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, SArray **ppLastArray) {
+  int32_t  code = 0;
+  SArray  *pSkyline = NULL;
+  STSRow  *pRow = NULL;
+  STSRow **ppRow = &pRow;
 
   STSchema *pTSchema = metaGetTbTSchema(pTsdb->pVnode->pMeta, uid, -1);
   int16_t   nCol = pTSchema->numOfCols;
-  SArray   *pColArray = taosArrayInit(nCol, sizeof(SColVal));
+  //  SArray   *pColArray = taosArrayInit(nCol, sizeof(SColVal));
+  SArray *pColArray = taosArrayInit(nCol, sizeof(SLastCol));
 
   tb_uid_t suid = getTableSuidByUid(uid, pTsdb);
 
@@ -835,9 +848,9 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
     tsdbGetTbDataFromMemTable(pTsdb->imem, suid, uid, &pIMem);
   }
 
-  *ppRow = NULL;
+  *ppLastArray = NULL;
 
-  SArray *pSkyline = taosArrayInit(32, sizeof(TSDBKEY));
+  pSkyline = taosArrayInit(32, sizeof(TSDBKEY));
 
   SDelIdx delIdx;
 
@@ -941,7 +954,6 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
     for (int i = 0; i < nMax; ++i) {
       TSDBKEY maxKey = TSDBROW_KEY(max[i]);
 
-      // bool deleted = false;
       bool deleted = tsdbKeyDeleted(&maxKey, pSkyline, &iSkyline);
       if (!deleted) {
         iMerge[nMerge] = iMax[i];
@@ -968,8 +980,9 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
         tRowMergerClear(&merger);
       }
     } else {
-      *ppRow = NULL;
+      /* *ppRow = NULL; */
-      return code;
+      /* return code; */
+      continue;
     }
 
     if (iCol == 0) {
@@ -978,7 +991,8 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
 
       *pColVal = COL_VAL_VALUE(pTColumn->colId, pTColumn->type, (SValue){.ts = maxKey});
 
-      if (taosArrayPush(pColArray, pColVal) == NULL) {
+      // if (taosArrayPush(pColArray, pColVal) == NULL) {
+      if (taosArrayPush(pColArray, &(SLastCol){.ts = TSKEY_MAX, .colVal = *pColVal}) == NULL) {
         code = TSDB_CODE_OUT_OF_MEMORY;
         goto _err;
       }
@@ -989,7 +1003,8 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
       for (int16_t i = iCol; i < nCol; ++i) {
         // tsdbRowGetColVal(*ppRow, pTSchema, i, pColVal);
         tTSRowGetVal(*ppRow, pTSchema, i, pColVal);
-        if (taosArrayPush(pColArray, pColVal) == NULL) {
+        // if (taosArrayPush(pColArray, pColVal) == NULL) {
+        if (taosArrayPush(pColArray, &(SLastCol){.ts = maxKey, .colVal = *pColVal}) == NULL) {
           code = TSDB_CODE_OUT_OF_MEMORY;
           goto _err;
         }
@@ -1010,11 +1025,11 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
           --nilColCount;
         }
       }
-      /*
+
       if (*ppRow) {
         taosMemoryFreeClear(*ppRow);
       }
-      */
+
       continue;
     }
 
@@ -1022,12 +1037,16 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
     for (int16_t i = iCol; i < nCol; ++i) {
       SColVal colVal = {0};
       tTSRowGetVal(*ppRow, pTSchema, i, &colVal);
+      TSKEY rowTs = (*ppRow)->ts;
 
-      SColVal *tColVal = (SColVal *)taosArrayGet(pColArray, i);
+      // SColVal *tColVal = (SColVal *)taosArrayGet(pColArray, i);
+      SLastCol *tTsVal = (SLastCol *)taosArrayGet(pColArray, i);
+      SColVal  *tColVal = &tTsVal->colVal;
 
       if (!colVal.isNone && !colVal.isNull) {
         if (tColVal->isNull || tColVal->isNone) {
-          taosArraySet(pColArray, i, &colVal);
+          // taosArraySet(pColArray, i, &colVal);
+          taosArraySet(pColArray, i, &(SLastCol){.ts = rowTs, .colVal = colVal});
           --nilColCount;
         }
       } else {
@@ -1052,16 +1071,45 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, STSRow **ppRow) {
   } while (nilColCount > 0);
 
   // if () new ts row from pColArray if non empty
-  if (taosArrayGetSize(pColArray) == nCol) {
+  /* if (taosArrayGetSize(pColArray) == nCol) { */
-    code = tdSTSRowNew(pColArray, pTSchema, ppRow);
+  /*   code = tdSTSRowNew(pColArray, pTSchema, ppRow); */
-    if (code) goto _err;
+  /*   if (code) goto _err; */
+  /* } */
+  /* taosArrayDestroy(pColArray); */
+  if (taosArrayGetSize(pColArray) <= 0) {
+    *ppLastArray = NULL;
+    taosArrayDestroy(pColArray);
+  } else {
+    *ppLastArray = pColArray;
+  }
+  if (*ppRow) {
+    taosMemoryFreeClear(*ppRow);
+  }
+
+  for (int i = 0; i < 3; ++i) {
+    if (input[i].nextRowClearFn) {
+      input[i].nextRowClearFn(input[i].iter);
+    }
+  }
+  if (pSkyline) {
+    taosArrayDestroy(pSkyline);
   }
-  taosArrayDestroy(pColArray);
   taosMemoryFreeClear(pTSchema);
 
   return code;
 _err:
   taosArrayDestroy(pColArray);
+  if (*ppRow) {
+    taosMemoryFreeClear(*ppRow);
+  }
+  for (int i = 0; i < 3; ++i) {
+    if (input[i].nextRowClearFn) {
+      input[i].nextRowClearFn(input[i].iter);
+    }
+  }
+  if (pSkyline) {
+    taosArrayDestroy(pSkyline);
+  }
   taosMemoryFreeClear(pTSchema);
   tsdbError("vgId:%d merge last_row failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
   return code;
@@ -1101,6 +1149,30 @@ int32_t tsdbCacheGetLastrowH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUH
   return code;
 }
 
+int32_t tsdbCacheLastArray2Row(SArray *pLastArray, STSRow **ppRow, STSchema *pTSchema) {
+  int32_t code = 0;
+  int16_t nCol = taosArrayGetSize(pLastArray);
+  SArray *pColArray = taosArrayInit(nCol, sizeof(SColVal));
+
+  for (int16_t iCol = 0; iCol < nCol; ++iCol) {
+    SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLastArray, iCol);
+    SColVal  *tColVal = &tTsVal->colVal;
+    taosArrayPush(pColArray, tColVal);
+  }
+
+  code = tdSTSRowNew(pColArray, pTSchema, ppRow);
+  if (code) goto _err;
+
+  taosArrayDestroy(pColArray);
+
+  return code;
+
+_err:
+  taosArrayDestroy(pColArray);
+
+  return code;
+}
+
 int32_t tsdbCacheGetLastH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHandle **handle) {
   int32_t code = 0;
   char    key[32] = {0};
@@ -1113,17 +1185,20 @@ int32_t tsdbCacheGetLastH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHand
     //*ppRow = (STSRow *)taosLRUCacheValue(pCache, h);
 
   } else {
-    STSRow *pRow = NULL;
+    // STSRow *pRow = NULL;
-    code = mergeLast(uid, pTsdb, &pRow);
+    // code = mergeLast(uid, pTsdb, &pRow);
+    SArray *pLastArray = NULL;
+    code = mergeLast(uid, pTsdb, &pLastArray);
     // if table's empty or error, return code of -1
-    if (code < 0 || pRow == NULL) {
+    // if (code < 0 || pRow == NULL) {
+    if (code < 0 || pLastArray == NULL) {
       *handle = NULL;
       return 0;
     }
 
-    _taos_lru_deleter_t deleter = deleteTableCacheLastrow;
+    _taos_lru_deleter_t deleter = deleteTableCacheLast;
     LRUStatus           status =
-        taosLRUCacheInsert(pCache, key, keyLen, pRow, TD_ROW_LEN(pRow), deleter, NULL, TAOS_LRU_PRIORITY_LOW);
+        taosLRUCacheInsert(pCache, key, keyLen, pLastArray, pLastArray->capacity, deleter, NULL, TAOS_LRU_PRIORITY_LOW);
     if (status != TAOS_LRU_STATUS_OK) {
       code = -1;
     }

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

@@ -128,6 +128,8 @@ int32_t tsdbRetrieveLastRow(void* pReader, SSDataBlock* pResBlock, const int32_t
       }
 
       pRow = (STSRow*)taosLRUCacheValue(lruCache, h);
+      // SArray* pLast = (SArray*)taosLRUCacheValue(lruCache, h);
+      // tsdbCacheLastArray2Row(pLast, &pRow, pr->pSchema);
       if (pRow->ts > lastKey) {
         // Set result row into the same rowIndex repeatly, so we need to check if the internal result row has already
         // appended or not.
@@ -140,6 +142,7 @@ int32_t tsdbRetrieveLastRow(void* pReader, SSDataBlock* pResBlock, const int32_t
         lastKey = pRow->ts;
       }
 
+      // taosMemoryFree(pRow);
       tsdbCacheRelease(lruCache, h);
     }
   } else if (pr->type == LASTROW_RETRIEVE_TYPE_ALL) {
@@ -158,8 +161,12 @@ int32_t tsdbRetrieveLastRow(void* pReader, SSDataBlock* pResBlock, const int32_t
       }
 
       pRow = (STSRow*)taosLRUCacheValue(lruCache, h);
+      // SArray* pLast = (SArray*)taosLRUCacheValue(lruCache, h);
+      // tsdbCacheLastArray2Row(pLast, &pRow, pr->pSchema);
+
       saveOneRow(pRow, pResBlock, pr, slotIds);
 
+      // taosMemoryFree(pRow);
       tsdbCacheRelease(lruCache, h);
 
       pr->tableIndex += 1;

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

@@ -168,8 +168,6 @@ static int32_t tsdbCommitTableDel(SCommitter *pCommitter, STbData *pTbData, SDel
   tb_uid_t  suid;
   tb_uid_t  uid;
 
-  taosArrayClear(pCommitter->aDelData);
-
   if (pTbData) {
     suid = pTbData->suid;
     uid = pTbData->uid;
@@ -185,6 +183,8 @@ static int32_t tsdbCommitTableDel(SCommitter *pCommitter, STbData *pTbData, SDel
 
     code = tsdbReadDelData(pCommitter->pDelFReader, pDelIdx, pCommitter->aDelData, NULL);
     if (code) goto _err;
+  } else {
+    taosArrayClear(pCommitter->aDelData);
   }
 
   if (pTbData == NULL && pDelIdx == NULL) goto _exit;
@@ -205,7 +205,7 @@ static int32_t tsdbCommitTableDel(SCommitter *pCommitter, STbData *pTbData, SDel
   if (code) goto _err;
 
   // put delIdx
-  if (taosArrayPush(pCommitter->aDelIdx, &delIdx) == NULL) {
+  if (taosArrayPush(pCommitter->aDelIdxN, &delIdx) == NULL) {
     code = TSDB_CODE_OUT_OF_MEMORY;
     goto _err;
   }
@@ -602,7 +602,7 @@ static int32_t tsdbGetOvlpNRow(STbDataIter *pIter, SBlock *pBlock) {
 
   iter.pRow = NULL;
   while (true) {
-    pRow = tsdbTbDataIterGet(pIter);
+    pRow = tsdbTbDataIterGet(&iter);
 
     if (pRow == NULL) break;
     key = TSDBROW_KEY(pRow);
@@ -610,7 +610,7 @@ static int32_t tsdbGetOvlpNRow(STbDataIter *pIter, SBlock *pBlock) {
     c = tBlockCmprFn(&(SBlock){.maxKey = key, .minKey = key}, pBlock);
     if (c == 0) {
       nRow++;
-      tsdbTbDataIterNext(pIter);
+      tsdbTbDataIterNext(&iter);
     } else if (c > 0) {
       break;
     } else {
@@ -635,7 +635,7 @@ static int32_t tsdbMergeAsSubBlock(SCommitter *pCommitter, STbDataIter *pIter, S
   code = tsdbCommitterUpdateRowSchema(pCommitter, pBlockIdx->suid, pBlockIdx->uid, TSDBROW_SVERSION(pRow));
   if (code) goto _err;
   while (true) {
-    if (pRow) break;
+    if (pRow == NULL) break;
     code = tBlockDataAppendRow(pBlockData, pRow, pCommitter->skmRow.pTSchema);
     if (code) goto _err;
 

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

@@ -520,7 +520,7 @@ static int32_t tsdbScanAndTryFixFS(STsdbFS *pFS, int8_t deepScan) {
   return code;
 
 _err:
-  tsdbError("vgId:%d tsdb can and try fix fs failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
+  tsdbError("vgId:%d tsdb scan and try fix fs failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
   return code;
 }
 

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

@@ -105,7 +105,7 @@ int32_t tsdbInsertTableData(STsdb *pTsdb, int64_t version, SSubmitMsgIter *pMsgI
 
   // check if table exists (todo: refact)
   SMetaReader mr = {0};
-  SMetaEntry  me = {0};
+  // SMetaEntry  me = {0};
   metaReaderInit(&mr, pTsdb->pVnode->pMeta, 0);
   if (metaGetTableEntryByUid(&mr, pMsgIter->uid) < 0) {
     metaReaderClear(&mr);
@@ -117,6 +117,8 @@ int32_t tsdbInsertTableData(STsdb *pTsdb, int64_t version, SSubmitMsgIter *pMsgI
   if (mr.me.type == TSDB_NORMAL_TABLE) {
     sverNew = mr.me.ntbEntry.schemaRow.version;
   } else {
+    tDecoderClear(&mr.coder);
+
     metaGetTableEntryByUid(&mr, mr.me.ctbEntry.suid);
     sverNew = mr.me.stbEntry.schemaRow.version;
   }

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

@@ -1,16 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "tsdb.h"

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

@@ -49,7 +49,7 @@ int32_t tsdbDelFWriterOpen(SDelFWriter **ppWriter, SDelFile *pFile, STsdb *pTsdb
   }
 
   pDelFWriter->fDel.size = TSDB_FHDR_SIZE;
-  pDelFWriter->fDel.size = 0;
+  pDelFWriter->fDel.offset = 0;
 
   *ppWriter = pDelFWriter;
   return code;
@@ -969,6 +969,8 @@ int32_t tsdbReadColData(SDataFReader *pReader, SBlockIdx *pBlockIdx, SBlock *pBl
     SBlockData *pBlockData1 = &(SBlockData){0};
     SBlockData *pBlockData2 = &(SBlockData){0};
 
+    tBlockDataInit(pBlockData1);
+    tBlockDataInit(pBlockData2);
     for (int32_t iSubBlock = 1; iSubBlock < pBlock->nSubBlock; iSubBlock++) {
       code = tsdbReadSubColData(pReader, pBlockIdx, pBlock, iSubBlock, aColId, nCol, pBlockData1, ppBuf1, ppBuf2);
       if (code) goto _err;
@@ -1106,6 +1108,8 @@ int32_t tsdbReadBlockData(SDataFReader *pReader, SBlockIdx *pBlockIdx, SBlock *p
     SBlockData *pBlockData1 = &(SBlockData){0};
     SBlockData *pBlockData2 = &(SBlockData){0};
 
+    tBlockDataInit(pBlockData1);
+    tBlockDataInit(pBlockData2);
     for (iSubBlock = 1; iSubBlock < pBlock->nSubBlock; iSubBlock++) {
       code = tsdbReadSubBlockData(pReader, pBlockIdx, pBlock, iSubBlock, pBlockData1, ppBuf1, ppBuf2);
       if (code) {
@@ -1152,7 +1156,7 @@ _err:
 int32_t tsdbReadBlockSma(SDataFReader *pReader, SBlock *pBlock, SArray *aColumnDataAgg, uint8_t **ppBuf) {
   int32_t   code = 0;
   TdFilePtr pFD = pReader->pSmaFD;
-  int64_t   offset = pBlock->aSubBlock[0].offset;
+  int64_t   offset = pBlock->aSubBlock[0].sOffset;
   int64_t   size = pBlock->aSubBlock[0].nSma * sizeof(SColumnDataAgg) + sizeof(TSCKSUM);
   uint8_t  *pBuf = NULL;
   int64_t   n;
@@ -1175,10 +1179,13 @@ int32_t tsdbReadBlockSma(SDataFReader *pReader, SBlock *pBlock, SArray *aColumnD
   if (n < 0) {
     code = TAOS_SYSTEM_ERROR(errno);
     goto _err;
+  } else if (n < size) {
+    code = TSDB_CODE_FILE_CORRUPTED;
+    goto _err;
   }
 
   // check
-  if (!taosCheckChecksumWhole(NULL, size)) {
+  if (!taosCheckChecksumWhole(*ppBuf, size)) {
     code = TSDB_CODE_FILE_CORRUPTED;
     goto _err;
   }

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

@@ -821,16 +821,20 @@ int32_t tColDataCopy(SColData *pColDataSrc, SColData *pColDataDest) {
   int32_t code = 0;
   int32_t size;
 
+  ASSERT(pColDataSrc->nVal > 0);
+
   pColDataDest->cid = pColDataSrc->cid;
   pColDataDest->type = pColDataSrc->type;
   pColDataDest->smaOn = pColDataSrc->smaOn;
   pColDataDest->nVal = pColDataSrc->nVal;
   pColDataDest->flag = pColDataSrc->flag;
 
-  size = BIT2_SIZE(pColDataSrc->nVal);
+  if (pColDataSrc->flag != HAS_NONE && pColDataSrc->flag != HAS_NULL && pColDataSrc->flag != HAS_VALUE) {
-  code = tRealloc(&pColDataDest->pBitMap, size);
+    size = BIT2_SIZE(pColDataSrc->nVal);
-  if (code) goto _exit;
+    code = tRealloc(&pColDataDest->pBitMap, size);
-  memcpy(pColDataDest->pBitMap, pColDataSrc->pBitMap, size);
+    if (code) goto _exit;
+    memcpy(pColDataDest->pBitMap, pColDataSrc->pBitMap, size);
+  }
 
   if (IS_VAR_DATA_TYPE(pColDataDest->type)) {
     size = sizeof(int32_t) * pColDataSrc->nVal;
@@ -1230,10 +1234,26 @@ void tsdbCalcColDataSMA(SColData *pColData, SColumnDataAgg *pColAgg) {
           break;
         case TSDB_DATA_TYPE_SMALLINT:
           break;
-        case TSDB_DATA_TYPE_INT:
+        case TSDB_DATA_TYPE_INT: {
+          pColAgg->sum += colVal.value.i32;
+          if (pColAgg->min > colVal.value.i32) {
+            pColAgg->min = colVal.value.i32;
+          }
+          if (pColAgg->max < colVal.value.i32) {
+            pColAgg->max = colVal.value.i32;
+          }
           break;
-        case TSDB_DATA_TYPE_BIGINT:
+        }
+        case TSDB_DATA_TYPE_BIGINT: {
+          pColAgg->sum += colVal.value.i64;
+          if (pColAgg->min > colVal.value.i64) {
+            pColAgg->min = colVal.value.i64;
+          }
+          if (pColAgg->max < colVal.value.i64) {
+            pColAgg->max = colVal.value.i64;
+          }
           break;
+        }
         case TSDB_DATA_TYPE_FLOAT:
           break;
         case TSDB_DATA_TYPE_DOUBLE:

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

@@ -1,14 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */

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

@@ -296,7 +296,7 @@ int32_t vnodeProcessFetchMsg(SVnode *pVnode, SRpcMsg *pMsg, SQueueInfo *pInfo) {
     case TDMT_SCH_MERGE_FETCH:
       return qWorkerProcessFetchMsg(pVnode, pVnode->pQuery, pMsg, 0);
     case TDMT_SCH_FETCH_RSP:
-      return qWorkerProcessFetchRsp(pVnode, pVnode->pQuery, pMsg, 0);
+      return qWorkerProcessRspMsg(pVnode, pVnode->pQuery, pMsg, 0);
     case TDMT_SCH_CANCEL_TASK:
       return qWorkerProcessCancelMsg(pVnode, pVnode->pQuery, pMsg, 0);
     case TDMT_SCH_DROP_TASK:

source/libs/executor/inc/dataSinkInt.h

@@ -34,7 +34,7 @@ typedef struct SDataSinkManager {
 
 typedef int32_t (*FPutDataBlock)(struct SDataSinkHandle* pHandle, const SInputData* pInput, bool* pContinue);
 typedef void (*FEndPut)(struct SDataSinkHandle* pHandle, uint64_t useconds);
-typedef void (*FGetDataLength)(struct SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryEnd);
+typedef void (*FGetDataLength)(struct SDataSinkHandle* pHandle, int64_t* pLen, bool* pQueryEnd);
 typedef int32_t (*FGetDataBlock)(struct SDataSinkHandle* pHandle, SOutputData* pOutput);
 typedef int32_t (*FDestroyDataSinker)(struct SDataSinkHandle* pHandle);
 typedef int32_t (*FGetCacheSize)(struct SDataSinkHandle* pHandle, uint64_t* size);
@@ -50,6 +50,7 @@ typedef struct SDataSinkHandle {
 
 int32_t createDataDispatcher(SDataSinkManager* pManager, const SDataSinkNode* pDataSink, DataSinkHandle* pHandle);
 int32_t createDataDeleter(SDataSinkManager* pManager, const SDataSinkNode* pDataSink, DataSinkHandle* pHandle, void *pParam);
+int32_t createDataInserter(SDataSinkManager* pManager, const SDataSinkNode* pDataSink, DataSinkHandle* pHandle, void *pParam);
 
 #ifdef __cplusplus
 }

source/libs/executor/inc/executorimpl.h

@@ -348,7 +348,7 @@ typedef struct SessionWindowSupporter {
   uint8_t parentType;
 } SessionWindowSupporter;
 
-typedef struct SStreamBlockScanInfo {
+typedef struct SStreamScanInfo {
   uint64_t        tableUid;         // queried super table uid
   SExprInfo*      pPseudoExpr;
   int32_t         numOfPseudoExpr;
@@ -365,7 +365,7 @@ typedef struct SStreamBlockScanInfo {
   int32_t         blockType;        // current block type
   int32_t         validBlockIndex;  // Is current data has returned?
   uint64_t        numOfExec;        // execution times
-  void*           streamBlockReader;// stream block reader handle
+  STqReader*           tqReader;
 
   int32_t         tsArrayIndex;
   SArray*         tsArray;
@@ -374,7 +374,7 @@ typedef struct SStreamBlockScanInfo {
 
   EStreamScanMode scanMode;
   SOperatorInfo* pStreamScanOp;
-  SOperatorInfo* pSnapshotReadOp;
+  SOperatorInfo* pTableScanOp;
   SArray*        childIds;
   SessionWindowSupporter sessionSup;
   bool            assignBlockUid; // assign block uid to groupId, temporarily used for generating rollup SMA.
@@ -383,7 +383,12 @@ typedef struct SStreamBlockScanInfo {
   SSDataBlock*    pPullDataRes;             // pull data SSDataBlock
   SSDataBlock*    pDeleteDataRes;             // delete data SSDataBlock
   int32_t         deleteDataIndex;
-} SStreamBlockScanInfo;
+
+  // status for tmq
+  //SSchemaWrapper schema;
+  STqOffset offset;
+
+} SStreamScanInfo;
 
 typedef struct SSysTableScanInfo {
   SRetrieveMetaTableRsp* pRsp;
@@ -518,6 +523,7 @@ typedef struct SIndefOperatorInfo {
   SAggSupporter      aggSup;
   SArray*            pPseudoColInfo;
   SExprSupp          scalarSup;
+  SNode*             pCondition;
 } SIndefOperatorInfo;
 
 typedef struct SFillOperatorInfo {
@@ -528,6 +534,7 @@ typedef struct SFillOperatorInfo {
   SSDataBlock*      existNewGroupBlock;
   bool              multigroupResult;
   STimeWindow       win;
+  SNode*            pCondition;
 } SFillOperatorInfo;
 
 typedef struct SGroupbyOperatorInfo {
@@ -799,7 +806,7 @@ SOperatorInfo* createMergeIntervalOperatorInfo(SOperatorInfo* downstream, SExprI
 
 SOperatorInfo* createMergeAlignedIntervalOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
                                           SSDataBlock* pResBlock, SInterval* pInterval, int32_t primaryTsSlotId,
-                                          SExecTaskInfo* pTaskInfo);
+                                          SNode* pCondition, SExecTaskInfo* pTaskInfo);
 
 SOperatorInfo* createStreamFinalIntervalOperatorInfo(SOperatorInfo* downstream,
     SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo, int32_t numOfChild);
@@ -878,7 +885,7 @@ int32_t decodeOperator(SOperatorInfo* ops, const char* data, int32_t length);
 void    setTaskStatus(SExecTaskInfo* pTaskInfo, int8_t status);
 int32_t createExecTaskInfoImpl(SSubplan* pPlan, SExecTaskInfo** pTaskInfo, SReadHandle* pHandle, uint64_t taskId,
                                const char* sql, EOPTR_EXEC_MODEL model);
-int32_t createDataSinkParam(SDataSinkNode *pNode, void **pParam, qTaskInfo_t* pTaskInfo);                               
+int32_t createDataSinkParam(SDataSinkNode *pNode, void **pParam, qTaskInfo_t* pTaskInfo, SReadHandle* readHandle);                               
 int32_t getOperatorExplainExecInfo(SOperatorInfo* operatorInfo, SExplainExecInfo** pRes, int32_t* capacity,
                                    int32_t* resNum);
 

source/libs/executor/src/dataDeleter.c

@@ -154,7 +154,7 @@ static void endPut(struct SDataSinkHandle* pHandle, uint64_t useconds) {
   taosThreadMutexUnlock(&pDeleter->mutex);
 }
 
-static void getDataLength(SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryEnd) {
+static void getDataLength(SDataSinkHandle* pHandle, int64_t* pLen, bool* pQueryEnd) {
   SDataDeleterHandle* pDeleter = (SDataDeleterHandle*)pHandle;
   if (taosQueueEmpty(pDeleter->pDataBlocks)) {
     *pQueryEnd = pDeleter->queryEnd;
@@ -168,7 +168,7 @@ static void getDataLength(SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryE
   taosFreeQitem(pBuf);
   *pLen = ((SDataCacheEntry*)(pDeleter->nextOutput.pData))->dataLen;
   *pQueryEnd = pDeleter->queryEnd;
-  qDebug("got data len %d, row num %d in sink", *pLen, ((SDataCacheEntry*)(pDeleter->nextOutput.pData))->numOfRows);
+  qDebug("got data len %" PRId64 ", row num %d in sink", *pLen, ((SDataCacheEntry*)(pDeleter->nextOutput.pData))->numOfRows);
 }
 
 static int32_t getDataBlock(SDataSinkHandle* pHandle, SOutputData* pOutput) {

source/libs/executor/src/dataDispatcher.c

@@ -156,7 +156,7 @@ static void endPut(struct SDataSinkHandle* pHandle, uint64_t useconds) {
   taosThreadMutexUnlock(&pDispatcher->mutex);
 }
 
-static void getDataLength(SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryEnd) {
+static void getDataLength(SDataSinkHandle* pHandle, int64_t* pLen, bool* pQueryEnd) {
   SDataDispatchHandle* pDispatcher = (SDataDispatchHandle*)pHandle;
   if (taosQueueEmpty(pDispatcher->pDataBlocks)) {
     *pQueryEnd = pDispatcher->queryEnd;
@@ -170,7 +170,7 @@ static void getDataLength(SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryE
   taosFreeQitem(pBuf);
   *pLen = ((SDataCacheEntry*)(pDispatcher->nextOutput.pData))->dataLen;
   *pQueryEnd = pDispatcher->queryEnd;
-  qDebug("got data len %d, row num %d in sink", *pLen, ((SDataCacheEntry*)(pDispatcher->nextOutput.pData))->numOfRows);
+  qDebug("got data len %" PRId64 ", row num %d in sink", *pLen, ((SDataCacheEntry*)(pDispatcher->nextOutput.pData))->numOfRows);
 }
 
 static int32_t getDataBlock(SDataSinkHandle* pHandle, SOutputData* pOutput) {

source/libs/executor/src/dataInserter.c

@@ -24,195 +24,266 @@
 
 extern SDataSinkStat gDataSinkStat;
 
-typedef struct SDataInserterBuf {
+typedef struct SSubmitRes {
-  int32_t useSize;
+  int64_t     affectedRows;
-  int32_t allocSize;
+  int32_t     code;
-  char*   pData;
+  SSubmitRsp *pRsp;
-} SDataInserterBuf;
+} SSubmitRes;
-
-typedef struct SDataCacheEntry {
-  int32_t dataLen;
-  int32_t numOfRows;
-  int32_t numOfCols;
-  int8_t  compressed;
-  char    data[];
-} SDataCacheEntry;
 
 typedef struct SDataInserterHandle {
   SDataSinkHandle     sink;
   SDataSinkManager*   pManager;
-  SDataBlockDescNode* pSchema;
+  STSchema*           pSchema;
-  SDataDeleterNode*   pDeleter;
+  SQueryInserterNode* pNode;
-  SDeleterParam*      pParam;
+  SSubmitRes          submitRes;
-  STaosQueue*         pDataBlocks;
+  SInserterParam*     pParam;
-  SDataInserterBuf    nextOutput;
+  SArray*             pDataBlocks;
+  SHashObj*           pCols;
   int32_t             status;
   bool                queryEnd;
   uint64_t            useconds;
   uint64_t            cachedSize;
   TdThreadMutex       mutex;
+  tsem_t              ready;  
 } SDataInserterHandle;
 
-static bool needCompress(const SSDataBlock* pData, int32_t numOfCols) {
+typedef struct SSubmitRspParam {
-  if (tsCompressColData < 0 || 0 == pData->info.rows) {
+  SDataInserterHandle* pInserter;
-    return false;
+} SSubmitRspParam;
-  }
 
-  for (int32_t col = 0; col < numOfCols; ++col) {
+int32_t inserterCallback(void* param, SDataBuf* pMsg, int32_t code) {
-    SColumnInfoData* pColRes = taosArrayGet(pData->pDataBlock, col);
+  SSubmitRspParam* pParam = (SSubmitRspParam*)param;
-    int32_t          colSize = pColRes->info.bytes * pData->info.rows;
+  SDataInserterHandle* pInserter = pParam->pInserter;
-    if (NEEDTO_COMPRESS_QUERY(colSize)) {
-      return true;
-    }
-  }
 
-  return false;
+  pInserter->submitRes.code = code;
-}
-
-static void toDataCacheEntry(SDataInserterHandle* pHandle, const SInputData* pInput, SDataInserterBuf* pBuf) {
-  int32_t numOfCols = LIST_LENGTH(pHandle->pSchema->pSlots);
-
-  SDataCacheEntry* pEntry = (SDataCacheEntry*)pBuf->pData;
-  pEntry->compressed = 0;
-  pEntry->numOfRows = pInput->pData->info.rows;
-  pEntry->numOfCols = taosArrayGetSize(pInput->pData->pDataBlock);
-  pEntry->dataLen = sizeof(SDeleterRes);
-
-  ASSERT(1 == pEntry->numOfRows);
-  ASSERT(1 == pEntry->numOfCols);
-
-  pBuf->useSize = sizeof(SDataCacheEntry);
-
-  SColumnInfoData* pColRes = (SColumnInfoData*)taosArrayGet(pInput->pData->pDataBlock, 0);
-
-  SDeleterRes* pRes = (SDeleterRes*)pEntry->data;
-  pRes->suid = pHandle->pParam->suid;
-  pRes->uidList = pHandle->pParam->pUidList;
-  pRes->skey = pHandle->pDeleter->deleteTimeRange.skey;
-  pRes->ekey = pHandle->pDeleter->deleteTimeRange.ekey;
-  pRes->affectedRows = *(int64_t*)pColRes->pData;
-
-  pBuf->useSize += pEntry->dataLen;
   
-  atomic_add_fetch_64(&pHandle->cachedSize, pEntry->dataLen); 
+  if (code == TSDB_CODE_SUCCESS) {
-  atomic_add_fetch_64(&gDataSinkStat.cachedSize, pEntry->dataLen); 
+    pInserter->submitRes.pRsp = taosMemoryCalloc(1, sizeof(SSubmitRsp));
-}
+    SDecoder    coder = {0};
+    tDecoderInit(&coder, pMsg->pData, pMsg->len);
+    code = tDecodeSSubmitRsp(&coder, pInserter->submitRes.pRsp);
+    if (code) {
+      tFreeSSubmitRsp(pInserter->submitRes.pRsp);
+      pInserter->submitRes.code = code;
+      goto _return;
+    }
+    
+    if (pInserter->submitRes.pRsp->nBlocks > 0) {
+      for (int32_t i = 0; i < pInserter->submitRes.pRsp->nBlocks; ++i) {
+        SSubmitBlkRsp *blk = pInserter->submitRes.pRsp->pBlocks + i;
+        if (TSDB_CODE_SUCCESS != blk->code) {
+          code = blk->code;
+          tFreeSSubmitRsp(pInserter->submitRes.pRsp);
+          pInserter->submitRes.code = code;
+          goto _return;
+        }
+      }
+    }
+    
+    pInserter->submitRes.affectedRows += pInserter->submitRes.pRsp->affectedRows;
+    qDebug("submit rsp received, affectedRows:%d, total:%d", pInserter->submitRes.pRsp->affectedRows, pInserter->submitRes.affectedRows);
 
-static bool allocBuf(SDataInserterHandle* pDeleter, const SInputData* pInput, SDataInserterBuf* pBuf) {
+    tFreeSSubmitRsp(pInserter->submitRes.pRsp);
-  uint32_t capacity = pDeleter->pManager->cfg.maxDataBlockNumPerQuery;
-  if (taosQueueItemSize(pDeleter->pDataBlocks) > capacity) {
-    qError("SinkNode queue is full, no capacity, max:%d, current:%d, no capacity", capacity,
-           taosQueueItemSize(pDeleter->pDataBlocks));
-    return false;
   }
 
-  pBuf->allocSize = sizeof(SDataCacheEntry) + sizeof(SDeleterRes);
+_return:
 
-  pBuf->pData = taosMemoryMalloc(pBuf->allocSize);
+  tsem_post(&pInserter->ready);
-  if (pBuf->pData == NULL) {
+
-    qError("SinkNode failed to malloc memory, size:%d, code:%d", pBuf->allocSize, TAOS_SYSTEM_ERROR(errno));
+  taosMemoryFree(param);
+  
+  return TSDB_CODE_SUCCESS;
+}
+
+
+static int32_t sendSubmitRequest(SDataInserterHandle* pInserter, SSubmitReq* pMsg, void* pTransporter, SEpSet* pEpset) {
+  // send the fetch remote task result reques
+  SMsgSendInfo* pMsgSendInfo = taosMemoryCalloc(1, sizeof(SMsgSendInfo));
+  if (NULL == pMsgSendInfo) {
+    taosMemoryFreeClear(pMsg);
+    terrno = TSDB_CODE_QRY_OUT_OF_MEMORY;
+    return terrno;
   }
 
-  return NULL != pBuf->pData;
+  SSubmitRspParam* pParam = taosMemoryCalloc(1, sizeof(SSubmitRspParam));
+  pParam->pInserter = pInserter;
+
+  pMsgSendInfo->param = pParam;
+  pMsgSendInfo->msgInfo.pData = pMsg;
+  pMsgSendInfo->msgInfo.len = ntohl(pMsg->length);
+  pMsgSendInfo->msgType = TDMT_VND_SUBMIT;
+  pMsgSendInfo->fp = inserterCallback;
+
+  int64_t transporterId = 0;
+  return asyncSendMsgToServer(pTransporter, pEpset, &transporterId, pMsgSendInfo);
 }
 
-static int32_t updateStatus(SDataInserterHandle* pDeleter) {
+
-  taosThreadMutexLock(&pDeleter->mutex);
+int32_t dataBlockToSubmit(SDataInserterHandle* pInserter, SSubmitReq** pReq) {
-  int32_t blockNums = taosQueueItemSize(pDeleter->pDataBlocks);
+  const SArray* pBlocks = pInserter->pDataBlocks;
-  int32_t status =
+  const STSchema* pTSchema = pInserter->pSchema; 
-      (0 == blockNums ? DS_BUF_EMPTY
+  int64_t uid = pInserter->pNode->tableId; 
-                      : (blockNums < pDeleter->pManager->cfg.maxDataBlockNumPerQuery ? DS_BUF_LOW : DS_BUF_FULL));
+  int64_t suid = pInserter->pNode->stableId; 
-  pDeleter->status = status;
+  int32_t vgId = pInserter->pNode->vgId;
-  taosThreadMutexUnlock(&pDeleter->mutex);
+  bool fullCol = (pInserter->pNode->pCols->length == pTSchema->numOfCols);
-  return status;
+
+  SSubmitReq* ret = NULL;
+  int32_t sz = taosArrayGetSize(pBlocks);
+
+  // cal size
+  int32_t cap = sizeof(SSubmitReq);
+  for (int32_t i = 0; i < sz; i++) {
+    SSDataBlock* pDataBlock = taosArrayGetP(pBlocks, i);
+    int32_t      rows = pDataBlock->info.rows;
+    // TODO min
+    int32_t rowSize = pDataBlock->info.rowSize;
+    int32_t maxLen = TD_ROW_MAX_BYTES_FROM_SCHEMA(pTSchema);
+
+    cap += sizeof(SSubmitBlk) + rows * maxLen;
+  }
+
+  // assign data
+  // TODO
+  ret = taosMemoryCalloc(1, cap);
+  ret->header.vgId = htonl(vgId);
+  ret->version = htonl(pTSchema->version);
+  ret->length = sizeof(SSubmitReq);
+  ret->numOfBlocks = htonl(sz);
+
+  SSubmitBlk* blkHead = POINTER_SHIFT(ret, sizeof(SSubmitReq));
+  for (int32_t i = 0; i < sz; i++) {
+    SSDataBlock* pDataBlock = taosArrayGetP(pBlocks, i);
+
+    blkHead->sversion = htonl(pTSchema->version);
+    // TODO
+    blkHead->suid = htobe64(suid);
+    blkHead->uid = htobe64(uid);
+    blkHead->schemaLen = htonl(0);
+
+    int32_t rows = 0;
+    int32_t dataLen = 0;
+    STSRow* rowData = POINTER_SHIFT(blkHead, sizeof(SSubmitBlk));
+    int64_t lastTs =  TSKEY_MIN;
+    bool    ignoreRow = false;
+    for (int32_t j = 0; j < pDataBlock->info.rows; j++) {
+      SRowBuilder rb = {0};
+      tdSRowInit(&rb, pTSchema->version);
+      tdSRowSetTpInfo(&rb, pTSchema->numOfCols, pTSchema->flen);
+      tdSRowResetBuf(&rb, rowData);
+
+      ignoreRow = false;
+      for (int32_t k = 0; k < pTSchema->numOfCols; k++) {
+        const STColumn*  pColumn = &pTSchema->columns[k];
+        SColumnInfoData* pColData = NULL;
+        int16_t colIdx = k;
+        if (!fullCol) {
+          int16_t *slotId = taosHashGet(pInserter->pCols, &pColumn->colId, sizeof(pColumn->colId));
+          if (NULL == slotId) {
+            continue;
+          }
+          
+          colIdx = *slotId;
+        }
+
+        pColData = taosArrayGet(pDataBlock->pDataBlock, colIdx);
+        if (pColData->info.type != pColumn->type) {
+          qError("col type mis-match, schema type:%d, type in block:%d", pColumn->type, pColData->info.type);
+          terrno = TSDB_CODE_APP_ERROR;
+          return TSDB_CODE_APP_ERROR;
+        }
+        
+        if (colDataIsNull_s(pColData, j)) {
+          if (0 == k && TSDB_DATA_TYPE_TIMESTAMP == pColumn->type) {
+            ignoreRow = true;
+            break;
+          }
+          
+          tdAppendColValToRow(&rb, pColumn->colId, pColumn->type, TD_VTYPE_NULL, NULL, false, pColumn->offset, k);
+        } else {
+          void* data = colDataGetData(pColData, j);
+          if (0 == k && TSDB_DATA_TYPE_TIMESTAMP == pColumn->type) {
+            if (*(int64_t*)data == lastTs) {
+              ignoreRow = true;
+              break;
+            } else {
+              lastTs = *(int64_t*)data;
+            }
+          }
+          tdAppendColValToRow(&rb, pColumn->colId, pColumn->type, TD_VTYPE_NORM, data, true, pColumn->offset, k);
+        }
+      }
+
+      if (ignoreRow) {
+        continue;
+      }
+      
+      rows++;
+      int32_t rowLen = TD_ROW_LEN(rowData);
+      rowData = POINTER_SHIFT(rowData, rowLen);
+      dataLen += rowLen;
+    }
+    
+    blkHead->dataLen = htonl(dataLen);
+    blkHead->numOfRows = htons(rows);
+
+    ret->length += sizeof(SSubmitBlk) + dataLen;
+    blkHead = POINTER_SHIFT(blkHead, sizeof(SSubmitBlk) + dataLen);
+  }
+
+  ret->length = htonl(ret->length);
+
+  *pReq = ret;
+
+  return TSDB_CODE_SUCCESS;
 }
 
-static int32_t getStatus(SDataInserterHandle* pDeleter) {
-  taosThreadMutexLock(&pDeleter->mutex);
-  int32_t status = pDeleter->status;
-  taosThreadMutexUnlock(&pDeleter->mutex);
-  return status;
-}
 
 static int32_t putDataBlock(SDataSinkHandle* pHandle, const SInputData* pInput, bool* pContinue) {
-  SDataInserterHandle* pDeleter = (SDataInserterHandle*)pHandle;
+  SDataInserterHandle* pInserter = (SDataInserterHandle*)pHandle;
-  SDataInserterBuf*    pBuf = taosAllocateQitem(sizeof(SDataInserterBuf), DEF_QITEM);
+  taosArrayPush(pInserter->pDataBlocks, &pInput->pData);
-  if (NULL == pBuf || !allocBuf(pDeleter, pInput, pBuf)) {
+  SSubmitReq* pMsg = NULL;
-    return TSDB_CODE_QRY_OUT_OF_MEMORY;
+  int32_t code = dataBlockToSubmit(pInserter, &pMsg);
+  if (code) {
+    return code;
   }
-  toDataCacheEntry(pDeleter, pInput, pBuf);
+
-  taosWriteQitem(pDeleter->pDataBlocks, pBuf);
+  code = sendSubmitRequest(pInserter, pMsg, pInserter->pParam->readHandle->pMsgCb->clientRpc, &pInserter->pNode->epSet);
-  *pContinue = (DS_BUF_LOW == updateStatus(pDeleter) ? true : false);
+  if (code) {
+    return code;
+  }
+
+  tsem_wait(&pInserter->ready);
+
+  if (pInserter->submitRes.code) {
+    return pInserter->submitRes.code;
+  }
+
+  *pContinue = true;
+  
   return TSDB_CODE_SUCCESS;
 }
 
 static void endPut(struct SDataSinkHandle* pHandle, uint64_t useconds) {
-  SDataInserterHandle* pDeleter = (SDataInserterHandle*)pHandle;
+  SDataInserterHandle* pInserter = (SDataInserterHandle*)pHandle;
-  taosThreadMutexLock(&pDeleter->mutex);
+  taosThreadMutexLock(&pInserter->mutex);
-  pDeleter->queryEnd = true;
+  pInserter->queryEnd = true;
-  pDeleter->useconds = useconds;
+  pInserter->useconds = useconds;
-  taosThreadMutexUnlock(&pDeleter->mutex);
+  taosThreadMutexUnlock(&pInserter->mutex);
 }
 
-static void getDataLength(SDataSinkHandle* pHandle, int32_t* pLen, bool* pQueryEnd) {
+static void getDataLength(SDataSinkHandle* pHandle, int64_t* pLen, bool* pQueryEnd) {
-  SDataInserterHandle* pDeleter = (SDataInserterHandle*)pHandle;
+  SDataInserterHandle* pDispatcher = (SDataInserterHandle*)pHandle;
-  if (taosQueueEmpty(pDeleter->pDataBlocks)) {
+  *pLen = pDispatcher->submitRes.affectedRows;
-    *pQueryEnd = pDeleter->queryEnd;
+  qDebug("got total affectedRows %" PRId64 , *pLen);
-    *pLen = 0;
-    return;
-  }
-
-  SDataInserterBuf* pBuf = NULL;
-  taosReadQitem(pDeleter->pDataBlocks, (void**)&pBuf);
-  memcpy(&pDeleter->nextOutput, pBuf, sizeof(SDataInserterBuf));
-  taosFreeQitem(pBuf);
-  *pLen = ((SDataCacheEntry*)(pDeleter->nextOutput.pData))->dataLen;
-  *pQueryEnd = pDeleter->queryEnd;
-  qDebug("got data len %d, row num %d in sink", *pLen, ((SDataCacheEntry*)(pDeleter->nextOutput.pData))->numOfRows);
 }
 
-static int32_t getDataBlock(SDataSinkHandle* pHandle, SOutputData* pOutput) {
-  SDataInserterHandle* pDeleter = (SDataInserterHandle*)pHandle;
-  if (NULL == pDeleter->nextOutput.pData) {
-    assert(pDeleter->queryEnd);
-    pOutput->useconds = pDeleter->useconds;
-    pOutput->precision = pDeleter->pSchema->precision;
-    pOutput->bufStatus = DS_BUF_EMPTY;
-    pOutput->queryEnd = pDeleter->queryEnd;
-    return TSDB_CODE_SUCCESS;
-  }
-  SDataCacheEntry* pEntry = (SDataCacheEntry*)(pDeleter->nextOutput.pData);
-  memcpy(pOutput->pData, pEntry->data, pEntry->dataLen);
-  pOutput->numOfRows = pEntry->numOfRows;
-  pOutput->numOfCols = pEntry->numOfCols;
-  pOutput->compressed = pEntry->compressed;
-
-  atomic_sub_fetch_64(&pDeleter->cachedSize, pEntry->dataLen);  
-  atomic_sub_fetch_64(&gDataSinkStat.cachedSize, pEntry->dataLen); 
-
-  taosMemoryFreeClear(pDeleter->nextOutput.pData);  // todo persistent
-  pOutput->bufStatus = updateStatus(pDeleter);
-  taosThreadMutexLock(&pDeleter->mutex);
-  pOutput->queryEnd = pDeleter->queryEnd;
-  pOutput->useconds = pDeleter->useconds;
-  pOutput->precision = pDeleter->pSchema->precision;
-  taosThreadMutexUnlock(&pDeleter->mutex);
-  
-  return TSDB_CODE_SUCCESS;
-}
 
 static int32_t destroyDataSinker(SDataSinkHandle* pHandle) {
-  SDataInserterHandle* pDeleter = (SDataInserterHandle*)pHandle;
+  SDataInserterHandle* pInserter = (SDataInserterHandle*)pHandle;
-  atomic_sub_fetch_64(&gDataSinkStat.cachedSize, pDeleter->cachedSize);
+  atomic_sub_fetch_64(&gDataSinkStat.cachedSize, pInserter->cachedSize);
-  taosMemoryFreeClear(pDeleter->nextOutput.pData);
+  taosArrayDestroy(pInserter->pDataBlocks);
-  while (!taosQueueEmpty(pDeleter->pDataBlocks)) {
+  taosMemoryFree(pInserter->pSchema);
-    SDataInserterBuf* pBuf = NULL;
+  taosThreadMutexDestroy(&pInserter->mutex);
-    taosReadQitem(pDeleter->pDataBlocks, (void**)&pBuf);
-    taosMemoryFreeClear(pBuf->pData);
-    taosFreeQitem(pBuf);
-  }
-  taosCloseQueue(pDeleter->pDataBlocks);
-  taosThreadMutexDestroy(&pDeleter->mutex);
   return TSDB_CODE_SUCCESS;
 }
 
@@ -230,25 +301,46 @@ int32_t createDataInserter(SDataSinkManager* pManager, const SDataSinkNode* pDat
     return TSDB_CODE_QRY_OUT_OF_MEMORY;
   }
 
-  SDataDeleterNode* pDeleterNode = (SDataDeleterNode *)pDataSink;
+  SQueryInserterNode* pInserterNode = (SQueryInserterNode *)pDataSink;
   inserter->sink.fPut = putDataBlock;
   inserter->sink.fEndPut = endPut;
   inserter->sink.fGetLen = getDataLength;
-  inserter->sink.fGetData = getDataBlock;
+  inserter->sink.fGetData = NULL;
   inserter->sink.fDestroy = destroyDataSinker;
   inserter->sink.fGetCacheSize = getCacheSize;
   inserter->pManager = pManager;
-  inserter->pDeleter = pDeleterNode;
+  inserter->pNode = pInserterNode;
-  inserter->pSchema = pDataSink->pInputDataBlockDesc;
   inserter->pParam = pParam;
   inserter->status = DS_BUF_EMPTY;
   inserter->queryEnd = false;
-  inserter->pDataBlocks = taosOpenQueue();
+
+  int64_t suid = 0;
+  int32_t code = tsdbGetTableSchema(inserter->pParam->readHandle->vnode, pInserterNode->tableId, &inserter->pSchema, &suid);
+  if (code) {
+    return code;
+  }
+
+  if (pInserterNode->stableId != suid) {
+    terrno = TSDB_CODE_TDB_INVALID_TABLE_ID;
+    return terrno;
+  }
+
+  inserter->pDataBlocks = taosArrayInit(1, POINTER_BYTES);
   taosThreadMutexInit(&inserter->mutex, NULL);
   if (NULL == inserter->pDataBlocks) {
     terrno = TSDB_CODE_QRY_OUT_OF_MEMORY;
     return TSDB_CODE_QRY_OUT_OF_MEMORY;
   }
+
+  inserter->pCols = taosHashInit(pInserterNode->pCols->length, taosGetDefaultHashFunction(TSDB_DATA_TYPE_SMALLINT), false, HASH_NO_LOCK);
+  SNode* pNode = NULL;
+  FOREACH(pNode, pInserterNode->pCols) {
+    SColumnNode* pCol = (SColumnNode*)pNode;
+    taosHashPut(inserter->pCols, &pCol->colId, sizeof(pCol->colId), &pCol->slotId, sizeof(pCol->slotId));
+  }
+  
+  tsem_init(&inserter->ready, 0, 0);
+  
   *pHandle = inserter;
   return TSDB_CODE_SUCCESS;
 }

source/libs/executor/src/dataSinkMgt.c

@@ -40,6 +40,8 @@ int32_t dsCreateDataSinker(const SDataSinkNode *pDataSink, DataSinkHandle* pHand
       return createDataDispatcher(&gDataSinkManager, pDataSink, pHandle);
     case QUERY_NODE_PHYSICAL_PLAN_DELETE:
       return createDataDeleter(&gDataSinkManager, pDataSink, pHandle, pParam);
+    case QUERY_NODE_PHYSICAL_PLAN_QUERY_INSERT:
+      return createDataInserter(&gDataSinkManager, pDataSink, pHandle, pParam);
   }
   return TSDB_CODE_FAILED;
 }
@@ -54,7 +56,7 @@ void dsEndPut(DataSinkHandle handle, uint64_t useconds) {
   return pHandleImpl->fEndPut(pHandleImpl, useconds);
 }
 
-void dsGetDataLength(DataSinkHandle handle, int32_t* pLen, bool* pQueryEnd) {
+void dsGetDataLength(DataSinkHandle handle, int64_t* pLen, bool* pQueryEnd) {
   SDataSinkHandle* pHandleImpl = (SDataSinkHandle*)handle;
   pHandleImpl->fGetLen(pHandleImpl, pLen, pQueryEnd);
 }

source/libs/executor/src/executor.c

@@ -37,7 +37,7 @@ static int32_t doSetStreamBlock(SOperatorInfo* pOperator, void* input, size_t nu
   } else {
     pOperator->status = OP_NOT_OPENED;
 
-    SStreamBlockScanInfo* pInfo = pOperator->info;
+    SStreamScanInfo* pInfo = pOperator->info;
     pInfo->assignBlockUid = assignUid;
 
     // TODO: if a block was set but not consumed,
@@ -45,7 +45,7 @@ static int32_t doSetStreamBlock(SOperatorInfo* pOperator, void* input, size_t nu
     pInfo->blockType = type;
 
     if (type == STREAM_INPUT__DATA_SUBMIT) {
-      if (tqReadHandleSetMsg(pInfo->streamBlockReader, input, 0) < 0) {
+      if (tqReaderSetDataMsg(pInfo->tqReader, input, 0) < 0) {
         qError("submit msg messed up when initing stream block, %s" PRIx64, id);
         return TSDB_CODE_QRY_APP_ERROR;
       }
@@ -105,7 +105,7 @@ int32_t qSetMultiStreamInput(qTaskInfo_t tinfo, const void* pBlocks, size_t numO
   return code;
 }
 
-qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, void* streamReadHandle) {
+qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, SReadHandle* readers) {
   if (msg == NULL) {
     return NULL;
   }
@@ -120,7 +120,7 @@ qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, void* streamReadHandle) {
   }
 
   qTaskInfo_t pTaskInfo = NULL;
-  code = qCreateExecTask(streamReadHandle, 0, 0, plan, &pTaskInfo, NULL, NULL, OPTR_EXEC_MODEL_STREAM);
+  code = qCreateExecTask(readers, 0, 0, plan, &pTaskInfo, NULL, NULL, OPTR_EXEC_MODEL_STREAM);
   if (code != TSDB_CODE_SUCCESS) {
     // TODO: destroy SSubplan & pTaskInfo
     terrno = code;
@@ -130,7 +130,7 @@ qTaskInfo_t qCreateStreamExecTaskInfo(void* msg, void* streamReadHandle) {
   return pTaskInfo;
 }
 
-static SArray* filterQualifiedChildTables(const SStreamBlockScanInfo* pScanInfo, const SArray* tableIdList) {
+static SArray* filterQualifiedChildTables(const SStreamScanInfo* pScanInfo, const SArray* tableIdList) {
   SArray* qa = taosArrayInit(4, sizeof(tb_uid_t));
 
   // let's discard the tables those are not created according to the queried super table.
@@ -168,17 +168,17 @@ int32_t qUpdateQualifiedTableId(qTaskInfo_t tinfo, const SArray* tableIdList, bo
     pInfo = pInfo->pDownstream[0];
   }
 
-  int32_t               code = 0;
+  int32_t          code = 0;
-  SStreamBlockScanInfo* pScanInfo = pInfo->info;
+  SStreamScanInfo* pScanInfo = pInfo->info;
   if (isAdd) {  // add new table id
     SArray* qa = filterQualifiedChildTables(pScanInfo, tableIdList);
 
     qDebug(" %d qualified child tables added into stream scanner", (int32_t)taosArrayGetSize(qa));
-    code = tqReadHandleAddTbUidList(pScanInfo->streamBlockReader, qa);
+    code = tqReaderAddTbUidList(pScanInfo->tqReader, qa);
     taosArrayDestroy(qa);
   } else {  // remove the table id in current list
     qDebug(" %d remove child tables from the stream scanner", (int32_t)taosArrayGetSize(tableIdList));
-    code = tqReadHandleRemoveTbUidList(pScanInfo->streamBlockReader, tableIdList);
+    code = tqReaderRemoveTbUidList(pScanInfo->tqReader, tableIdList);
   }
 
   return code;

source/libs/executor/src/executorMain.c

@@ -52,7 +52,7 @@ int32_t qCreateExecTask(SReadHandle* readHandle, int32_t vgId, uint64_t taskId,
 
   if (handle) {
     void* pSinkParam = NULL;
-    code = createDataSinkParam(pSubplan->pDataSink, &pSinkParam, pTaskInfo);
+    code = createDataSinkParam(pSubplan->pDataSink, &pSinkParam, pTaskInfo, readHandle);
     if (code != TSDB_CODE_SUCCESS) {
       goto _error;
     }
@@ -236,6 +236,37 @@ int32_t qDeserializeTaskStatus(qTaskInfo_t tinfo, const char* pInput, int32_t le
   return decodeOperator(pTaskInfo->pRoot, pInput, len);
 }
 
+int32_t qExtractStreamScanner(qTaskInfo_t tinfo, void** scanner) {
+  SExecTaskInfo* pTaskInfo = (SExecTaskInfo*)tinfo;
+  SOperatorInfo* pOperator = pTaskInfo->pRoot;
+
+  while (1) {
+    uint8_t type = pOperator->operatorType;
+    if (type == QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN) {
+      *scanner = pOperator->info;
+      return 0;
+    } else {
+      ASSERT(pOperator->numOfDownstream == 1);
+      pOperator = pOperator->pDownstream[0];
+    }
+  }
+}
+
+void* qExtractReaderFromStreamScanner(void* scanner) {
+  SStreamScanInfo* pInfo = scanner;
+  return (void*)pInfo->tqReader;
+}
+
+const SSchemaWrapper* qExtractSchemaFromStreamScanner(void* scanner) {
+  SStreamScanInfo* pInfo = scanner;
+  return pInfo->tqReader->pSchemaWrapper;
+}
+
+const STqOffset* qExtractStatusFromStreamScanner(void* scanner) {
+  SStreamScanInfo* pInfo = scanner;
+  return &pInfo->offset;
+}
+
 int32_t qStreamPrepareScan(qTaskInfo_t tinfo, uint64_t uid, int64_t ts) {
   SExecTaskInfo* pTaskInfo = (SExecTaskInfo*)tinfo;
 

source/libs/executor/src/executorimpl.c

@@ -741,10 +741,10 @@ static int32_t doCreateConstantValColumnAggInfo(SInputColumnInfoData* pInput, SF
 
   if (type == TSDB_DATA_TYPE_BIGINT) {
     int64_t v = pFuncParam->param.i;
-    *da = (SColumnDataAgg){.numOfNull = 0, .min = v, .max = v, .maxIndex = 0, .minIndex = 0, .sum = v * numOfRows};
+    *da = (SColumnDataAgg){.numOfNull = 0, .min = v, .max = v, .sum = v * numOfRows};
   } else if (type == TSDB_DATA_TYPE_DOUBLE) {
     double v = pFuncParam->param.d;
-    *da = (SColumnDataAgg){.numOfNull = 0, .maxIndex = 0, .minIndex = 0};
+    *da = (SColumnDataAgg){.numOfNull = 0};
 
     *(double*)&da->min = v;
     *(double*)&da->max = v;
@@ -752,7 +752,7 @@ static int32_t doCreateConstantValColumnAggInfo(SInputColumnInfoData* pInput, SF
   } else if (type == TSDB_DATA_TYPE_BOOL) {  // todo validate this data type
     bool v = pFuncParam->param.i;
 
-    *da = (SColumnDataAgg){.numOfNull = 0, .maxIndex = 0, .minIndex = 0};
+    *da = (SColumnDataAgg){.numOfNull = 0};
     *(bool*)&da->min = 0;
     *(bool*)&da->max = v;
     *(bool*)&da->sum = v * numOfRows;
@@ -1130,7 +1130,7 @@ int32_t loadDataBlockOnDemand(SExecTaskInfo* pTaskInfo, STableScanInfo* pTableSc
   } else if ((*status) == BLK_DATA_SMA_LOAD) {
     // this function never returns error?
     pCost->loadBlockStatis += 1;
-//    tsdbRetrieveDataBlockStatisInfo(pTableScanInfo->pTsdbReadHandle, &pBlock->pBlockAgg);
+//    tsdbRetrieveDatablockSMA(pTableScanInfo->pTsdbReadHandle, &pBlock->pBlockAgg);
 
     if (pBlock->pBlockAgg == NULL) {  // data block statistics does not exist, load data block
 //      pBlock->pDataBlock = tsdbRetrieveDataBlock(pTableScanInfo->pTsdbReadHandle, NULL);
@@ -1141,7 +1141,7 @@ int32_t loadDataBlockOnDemand(SExecTaskInfo* pTaskInfo, STableScanInfo* pTableSc
 
     // load the data block statistics to perform further filter
     pCost->loadBlockStatis += 1;
-//    tsdbRetrieveDataBlockStatisInfo(pTableScanInfo->pTsdbReadHandle, &pBlock->pBlockAgg);
+//    tsdbRetrieveDatablockSMA(pTableScanInfo->pTsdbReadHandle, &pBlock->pBlockAgg);
 
     if (pQueryAttr->topBotQuery && pBlock->pBlockAgg != NULL) {
       { // set previous window
@@ -1994,7 +1994,7 @@ static void destroySendMsgInfo(SMsgSendInfo* pMsgBody) {
   taosMemoryFreeClear(pMsgBody);
 }
 
-void qProcessFetchRsp(void* parent, SRpcMsg* pMsg, SEpSet* pEpSet) {
+void qProcessRspMsg(void* parent, SRpcMsg* pMsg, SEpSet* pEpSet) {
   SMsgSendInfo* pSendInfo = (SMsgSendInfo*)pMsg->info.ahandle;
   assert(pMsg->info.ahandle != NULL);
 
@@ -2463,6 +2463,8 @@ static void destroySortedMergeOperatorInfo(void* param, int32_t numOfOutput) {
 
   blockDataDestroy(pInfo->binfo.pRes);
   cleanupAggSup(&pInfo->aggSup);
+  
+  taosMemoryFreeClear(param);
 }
 
 static bool needToMerge(SSDataBlock* pBlock, SArray* groupInfo, char** buf, int32_t rowIndex) {
@@ -2844,17 +2846,17 @@ int32_t getTableScanInfo(SOperatorInfo* pOperator, int32_t* order, int32_t* scan
 }
 
 int32_t doPrepareScan(SOperatorInfo* pOperator, uint64_t uid, int64_t ts) {
-  int32_t type = pOperator->operatorType;
+  uint8_t type = pOperator->operatorType;
 
   pOperator->status = OP_OPENED;
 
   if (type == QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN) {
-    SStreamBlockScanInfo* pScanInfo = pOperator->info;
+    SStreamScanInfo* pScanInfo = pOperator->info;
     pScanInfo->blockType = STREAM_INPUT__DATA_SCAN;
 
-    pScanInfo->pSnapshotReadOp->status = OP_OPENED;
+    pScanInfo->pTableScanOp->status = OP_OPENED;
 
-    STableScanInfo* pInfo = pScanInfo->pSnapshotReadOp->info;
+    STableScanInfo* pInfo = pScanInfo->pTableScanOp->info;
     ASSERT(pInfo->scanMode == TABLE_SCAN__TABLE_ORDER);
 
     if (uid == 0) {
@@ -2914,8 +2916,8 @@ int32_t doPrepareScan(SOperatorInfo* pOperator, uint64_t uid, int64_t ts) {
 int32_t doGetScanStatus(SOperatorInfo* pOperator, uint64_t* uid, int64_t* ts) {
   int32_t type = pOperator->operatorType;
   if (type == QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN) {
-    SStreamBlockScanInfo* pScanInfo = pOperator->info;
+    SStreamScanInfo* pScanInfo = pOperator->info;
-    STableScanInfo*       pSnapShotScanInfo = pScanInfo->pSnapshotReadOp->info;
+    STableScanInfo*  pSnapShotScanInfo = pScanInfo->pTableScanOp->info;
     *uid = pSnapShotScanInfo->lastStatus.uid;
     *ts = pSnapShotScanInfo->lastStatus.ts;
   } else {
@@ -3364,7 +3366,7 @@ static void doHandleRemainBlockFromNewGroup(SFillOperatorInfo* pInfo, SResultInf
   }
 }
 
-static SSDataBlock* doFill(SOperatorInfo* pOperator) {
+static SSDataBlock* doFillImpl(SOperatorInfo* pOperator) {
   SFillOperatorInfo* pInfo = pOperator->info;
   SExecTaskInfo*     pTaskInfo = pOperator->pTaskInfo;
 
@@ -3372,9 +3374,6 @@ static SSDataBlock* doFill(SOperatorInfo* pOperator) {
   SSDataBlock* pResBlock = pInfo->pRes;
 
   blockDataCleanup(pResBlock);
-  if (pOperator->status == OP_EXEC_DONE) {
-    return NULL;
-  }
 
   // todo handle different group data interpolation
   bool  n = false;
@@ -3440,6 +3439,39 @@ static SSDataBlock* doFill(SOperatorInfo* pOperator) {
   }
 }
 
+static SSDataBlock* doFill(SOperatorInfo* pOperator) {
+  SFillOperatorInfo* pInfo = pOperator->info;
+  SExecTaskInfo*     pTaskInfo = pOperator->pTaskInfo;
+
+  if (pOperator->status == OP_EXEC_DONE) {
+    return NULL;
+  }
+
+  SSDataBlock* fillResult = NULL;
+  while (true) {
+    fillResult = doFillImpl(pOperator);
+    if (fillResult != NULL) {
+      doFilter(pInfo->pCondition, fillResult);
+    }
+
+    if (fillResult == NULL) {
+      doSetOperatorCompleted(pOperator);
+      break;
+    }
+
+    if (fillResult->info.rows > 0) {
+      break;
+    }
+  }
+
+  if (fillResult != NULL) {
+    size_t rows = fillResult->info.rows;
+    pOperator->resultInfo.totalRows += rows;
+  }
+
+  return fillResult;
+}
+
 static void destroyExprInfo(SExprInfo* pExpr, int32_t numOfExprs) {
   for (int32_t i = 0; i < numOfExprs; ++i) {
     SExprInfo* pExprInfo = &pExpr[i];
@@ -3474,7 +3506,6 @@ static void destroyOperatorInfo(SOperatorInfo* pOperator) {
   }
 
   taosMemoryFreeClear(pOperator->exprSupp.pExprInfo);
-  taosMemoryFreeClear(pOperator->info);
   taosMemoryFreeClear(pOperator);
 }
 
@@ -3644,11 +3675,15 @@ void cleanupBasicInfo(SOptrBasicInfo* pInfo) {
 void destroyBasicOperatorInfo(void* param, int32_t numOfOutput) {
   SOptrBasicInfo* pInfo = (SOptrBasicInfo*)param;
   cleanupBasicInfo(pInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 void destroyAggOperatorInfo(void* param, int32_t numOfOutput) {
   SAggOperatorInfo* pInfo = (SAggOperatorInfo*)param;
-  cleanupBasicInfo(&pInfo->binfo);
+  cleanupBasicInfo(&pInfo->binfo);  
+  
+  taosMemoryFreeClear(param);
 }
 
 void destroySFillOperatorInfo(void* param, int32_t numOfOutput) {
@@ -3656,6 +3691,8 @@ void destroySFillOperatorInfo(void* param, int32_t numOfOutput) {
   pInfo->pFillInfo = taosDestroyFillInfo(pInfo->pFillInfo);
   pInfo->pRes = blockDataDestroy(pInfo->pRes);
   taosMemoryFreeClear(pInfo->p);
+  
+  taosMemoryFreeClear(param);
 }
 
 static void destroyProjectOperatorInfo(void* param, int32_t numOfOutput) {
@@ -3666,6 +3703,8 @@ static void destroyProjectOperatorInfo(void* param, int32_t numOfOutput) {
   cleanupBasicInfo(&pInfo->binfo);
   cleanupAggSup(&pInfo->aggSup);
   taosArrayDestroy(pInfo->pPseudoColInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 void cleanupExprSupp(SExprSupp* pSupp) {
@@ -3682,6 +3721,8 @@ static void destroyIndefinitOperatorInfo(void* param, int32_t numOfOutput) {
   taosArrayDestroy(pInfo->pPseudoColInfo);
   cleanupAggSup(&pInfo->aggSup);
   cleanupExprSupp(&pInfo->scalarSup);
+  
+  taosMemoryFreeClear(param);
 }
 
 void destroyExchangeOperatorInfo(void* param, int32_t numOfOutput) {
@@ -3699,6 +3740,8 @@ void doDestroyExchangeOperatorInfo(void* param) {
   }
 
   tsem_destroy(&pExInfo->ready);
+  
+  taosMemoryFreeClear(param);
 }
 
 static SArray* setRowTsColumnOutputInfo(SqlFunctionCtx* pCtx, int32_t numOfCols) {
@@ -3832,6 +3875,8 @@ static SSDataBlock* doApplyIndefinitFunction(SOperatorInfo* pOperator) {
     }
   }
 
+  doFilter(pIndefInfo->pCondition, pInfo->pRes);
+
   size_t rows = pInfo->pRes->info.rows;
   pOperator->resultInfo.totalRows += rows;
 
@@ -3885,6 +3930,7 @@ SOperatorInfo* createIndefinitOutputOperatorInfo(SOperatorInfo* downstream, SPhy
 
   pInfo->binfo.pRes = pResBlock;
   pInfo->pPseudoColInfo = setRowTsColumnOutputInfo(pSup->pCtx, numOfExpr);
+  pInfo->pCondition = pPhyNode->node.pConditions;
 
   pOperator->name = "IndefinitOperator";
   pOperator->operatorType = QUERY_NODE_PHYSICAL_PLAN_PROJECT;
@@ -3958,6 +4004,7 @@ SOperatorInfo* createFillOperatorInfo(SOperatorInfo* downstream, SFillPhysiNode*
 
   pInfo->pRes = pResBlock;
   pInfo->multigroupResult = multigroupResult;
+  pInfo->pCondition = pPhyFillNode->node.pConditions;
   pOperator->name = "FillOperator";
   pOperator->blocking = false;
   pOperator->status = OP_NOT_OPENED;
@@ -4312,11 +4359,11 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
     } else if (QUERY_NODE_PHYSICAL_PLAN_LAST_ROW_SCAN == type) {
       SLastRowScanPhysiNode* pScanNode = (SLastRowScanPhysiNode*)pPhyNode;
 
-//      int32_t code = createScanTableListInfo(pTableScanNode, pHandle, pTableListInfo, queryId, taskId);
+      //      int32_t code = createScanTableListInfo(pTableScanNode, pHandle, pTableListInfo, queryId, taskId);
-//      if (code) {
+      //      if (code) {
-//        pTaskInfo->code = code;
+      //        pTaskInfo->code = code;
-//        return NULL;
+      //        return NULL;
-//      }
+      //      }
 
       int32_t code = extractTableSchemaVersion(pHandle, pScanNode->uid, pTaskInfo);
       if (code != TSDB_CODE_SUCCESS) {
@@ -4373,8 +4420,8 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
       pOptr = createGroupOperatorInfo(ops[0], pExprInfo, num, pResBlock, pColList, pAggNode->node.pConditions,
                                       pScalarExprInfo, numOfScalarExpr, pTaskInfo);
     } else {
-      pOptr =
+      pOptr = createAggregateOperatorInfo(ops[0], pExprInfo, num, pResBlock, pAggNode->node.pConditions,
-          createAggregateOperatorInfo(ops[0], pExprInfo, num, pResBlock, pAggNode->node.pConditions, pScalarExprInfo, numOfScalarExpr, pTaskInfo);
+                                          pScalarExprInfo, numOfScalarExpr, pTaskInfo);
     }
   } else if (QUERY_NODE_PHYSICAL_PLAN_HASH_INTERVAL == type || QUERY_NODE_PHYSICAL_PLAN_STREAM_INTERVAL == type) {
     SIntervalPhysiNode* pIntervalPhyNode = (SIntervalPhysiNode*)pPhyNode;
@@ -4415,7 +4462,7 @@ SOperatorInfo* createOperatorTree(SPhysiNode* pPhyNode, SExecTaskInfo* pTaskInfo
                           .precision = ((SColumnNode*)pIntervalPhyNode->window.pTspk)->node.resType.precision};
 
     int32_t tsSlotId = ((SColumnNode*)pIntervalPhyNode->window.pTspk)->slotId;
-    pOptr = createMergeAlignedIntervalOperatorInfo(ops[0], pExprInfo, num, pResBlock, &interval, tsSlotId, pTaskInfo);
+    pOptr = createMergeAlignedIntervalOperatorInfo(ops[0], pExprInfo, num, pResBlock, &interval, tsSlotId, pPhyNode->pConditions, pTaskInfo);
   } else if (QUERY_NODE_PHYSICAL_PLAN_MERGE_INTERVAL == type) {
     SMergeIntervalPhysiNode* pIntervalPhyNode = (SMergeIntervalPhysiNode*)pPhyNode;
 
@@ -4541,7 +4588,8 @@ SArray* extractColumnInfo(SNodeList* pNodeList) {
   return pList;
 }
 
-STsdbReader* doCreateDataReader(STableScanPhysiNode* pTableScanNode, SReadHandle* pHandle, STableListInfo* pTableListInfo, const char* idstr) {
+STsdbReader* doCreateDataReader(STableScanPhysiNode* pTableScanNode, SReadHandle* pHandle,
+                                STableListInfo* pTableListInfo, const char* idstr) {
   int32_t code = getTableList(pHandle->meta, pHandle->vnode, &pTableScanNode->scan, pTableListInfo);
   if (code != TSDB_CODE_SUCCESS) {
     goto _error;
@@ -4587,9 +4635,9 @@ static int32_t extractTbscanInStreamOpTree(SOperatorInfo* pOperator, STableScanI
     }
     return extractTbscanInStreamOpTree(pOperator->pDownstream[0], ppInfo);
   } else {
-    SStreamBlockScanInfo* pInfo = pOperator->info;
+    SStreamScanInfo* pInfo = pOperator->info;
-    ASSERT(pInfo->pSnapshotReadOp->operatorType == QUERY_NODE_PHYSICAL_PLAN_TABLE_SCAN);
+    ASSERT(pInfo->pTableScanOp->operatorType == QUERY_NODE_PHYSICAL_PLAN_TABLE_SCAN);
-    *ppInfo = pInfo->pSnapshotReadOp->info;
+    *ppInfo = pInfo->pTableScanOp->info;
     return 0;
   }
 }
@@ -4737,10 +4785,20 @@ int32_t decodeOperator(SOperatorInfo* ops, const char* result, int32_t length) {
   return TDB_CODE_SUCCESS;
 }
 
-int32_t createDataSinkParam(SDataSinkNode* pNode, void** pParam, qTaskInfo_t* pTaskInfo) {
+int32_t createDataSinkParam(SDataSinkNode* pNode, void** pParam, qTaskInfo_t* pTaskInfo, SReadHandle* readHandle) {
   SExecTaskInfo* pTask = *(SExecTaskInfo**)pTaskInfo;
 
   switch (pNode->type) {
+    case QUERY_NODE_PHYSICAL_PLAN_QUERY_INSERT: {
+      SInserterParam* pInserterParam = taosMemoryCalloc(1, sizeof(SInserterParam));
+      if (NULL == pInserterParam) {
+        return TSDB_CODE_OUT_OF_MEMORY;
+      }
+      pInserterParam->readHandle = readHandle;
+      
+      *pParam = pInserterParam;
+      break;
+    }
     case QUERY_NODE_PHYSICAL_PLAN_DELETE: {
       SDeleterParam* pDeleterParam = taosMemoryCalloc(1, sizeof(SDeleterParam));
       if (NULL == pDeleterParam) {
@@ -4785,7 +4843,6 @@ int32_t createExecTaskInfoImpl(SSubplan* pPlan, SExecTaskInfo** pTaskInfo, SRead
   (*pTaskInfo)->pRoot = createOperatorTree(pPlan->pNode, *pTaskInfo, pHandle, queryId, taskId,
                                            &(*pTaskInfo)->tableqinfoList, pPlan->user);
 
-
   if (NULL == (*pTaskInfo)->pRoot) {
     code = (*pTaskInfo)->code;
     goto _complete;

source/libs/executor/src/groupoperator.c

@@ -38,6 +38,8 @@ static void destroyGroupOperatorInfo(void* param, int32_t numOfOutput) {
   taosArrayDestroy(pInfo->pGroupCols);
   taosArrayDestroy(pInfo->pGroupColVals);
   cleanupExprSupp(&pInfo->scalarSup);
+  
+  taosMemoryFreeClear(param);
 }
 
 static int32_t initGroupOptrInfo(SArray** pGroupColVals, int32_t* keyLen, char** keyBuf, const SArray* pGroupColList) {
@@ -724,6 +726,8 @@ static void destroyPartitionOperatorInfo(void* param, int32_t numOfOutput) {
   taosMemoryFree(pInfo->columnOffset);
 
   cleanupExprSupp(&pInfo->scalarSup);
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createPartitionOperatorInfo(SOperatorInfo* downstream, SPartitionPhysiNode* pPartNode, SExecTaskInfo* pTaskInfo) {
@@ -806,4 +810,4 @@ int32_t setGroupResultOutputBuf(SOperatorInfo* pOperator, SOptrBasicInfo* binfo,
 
   setResultRowInitCtx(pResultRow, pCtx, numOfCols, pOperator->exprSupp.rowEntryInfoOffset);
   return TSDB_CODE_SUCCESS;
-}
+}

source/libs/executor/src/joinoperator.c

@@ -104,6 +104,8 @@ void setJoinColumnInfo(SColumnInfo* pColumn, const SColumnNode* pColumnNode) {
 void destroyMergeJoinOperator(void* param, int32_t numOfOutput) {
   SJoinOperatorInfo* pJoinOperator = (SJoinOperatorInfo*)param;
   nodesDestroyNode(pJoinOperator->pCondAfterMerge);
+  
+  taosMemoryFreeClear(param);
 }
 
 static void doMergeJoinImpl(struct SOperatorInfo* pOperator, SSDataBlock* pRes) {

source/libs/executor/src/scanoperator.c

@@ -210,7 +210,10 @@ static int32_t loadDataBlock(SOperatorInfo* pOperator, STableScanInfo* pTableSca
 
     bool             allColumnsHaveAgg = true;
     SColumnDataAgg** pColAgg = NULL;
-    tsdbRetrieveDataBlockStatisInfo(pTableScanInfo->dataReader, &pColAgg, &allColumnsHaveAgg);
+    int32_t code = tsdbRetrieveDatablockSMA(pTableScanInfo->dataReader, &pColAgg, &allColumnsHaveAgg);
+    if (code != TSDB_CODE_SUCCESS) {
+      longjmp(pTaskInfo->env, code);
+    }
 
     if (allColumnsHaveAgg == true) {
       int32_t numOfCols = taosArrayGetSize(pBlock->pDataBlock);
@@ -592,6 +595,8 @@ static void destroyTableScanOperatorInfo(void* param, int32_t numOfOutput) {
   if (pTableScanInfo->pColMatchInfo != NULL) {
     taosArrayDestroy(pTableScanInfo->pColMatchInfo);
   }
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createTableScanOperatorInfo(STableScanPhysiNode* pTableScanNode, SReadHandle* readHandle,
@@ -740,6 +745,8 @@ static SSDataBlock* doBlockInfoScan(SOperatorInfo* pOperator) {
 static void destroyBlockDistScanOperatorInfo(void* param, int32_t numOfOutput) {
   SBlockDistInfo* pDistInfo = (SBlockDistInfo*)param;
   blockDataDestroy(pDistInfo->pResBlock);
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createDataBlockInfoScanOperator(void* dataReader, SReadHandle* readHandle, uint64_t uid,
@@ -780,7 +787,7 @@ _error:
   return NULL;
 }
 
-static void doClearBufferedBlocks(SStreamBlockScanInfo* pInfo) {
+static void doClearBufferedBlocks(SStreamScanInfo* pInfo) {
   size_t total = taosArrayGetSize(pInfo->pBlockLists);
 
   pInfo->validBlockIndex = 0;
@@ -791,21 +798,20 @@ static void doClearBufferedBlocks(SStreamBlockScanInfo* pInfo) {
   taosArrayClear(pInfo->pBlockLists);
 }
 
-static bool isSessionWindow(SStreamBlockScanInfo* pInfo) {
+static bool isSessionWindow(SStreamScanInfo* pInfo) {
   return pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SESSION ||
-      pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SESSION;
+         pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SESSION;
 }
 
-static bool isStateWindow(SStreamBlockScanInfo* pInfo) {
+static bool isStateWindow(SStreamScanInfo* pInfo) {
   return pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_STATE;
 }
 
-static bool isIntervalWindow(SStreamBlockScanInfo* pInfo) {
+static bool isIntervalWindow(SStreamScanInfo* pInfo) {
   return pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_INTERVAL ||
-      pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SEMI_INTERVAL;
+         pInfo->sessionSup.parentType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SEMI_INTERVAL;
 }
 
-
 static uint64_t getGroupId(SOperatorInfo* pOperator, uint64_t uid) {
   uint64_t* groupId = taosHashGet(pOperator->pTaskInfo->tableqinfoList.map, &uid, sizeof(int64_t));
   if (groupId) {
@@ -827,19 +833,17 @@ static uint64_t getGroupId(SOperatorInfo* pOperator, uint64_t uid) {
   */
 }
 
-static void setGroupId(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, int32_t groupColIndex, int32_t rowIndex) {
+static void setGroupId(SStreamScanInfo* pInfo, SSDataBlock* pBlock, int32_t groupColIndex, int32_t rowIndex) {
   ASSERT(rowIndex < pBlock->info.rows);
-  switch (pBlock->info.type)
+  switch (pBlock->info.type) {
-  {
+    case STREAM_DELETE_DATA:
-  case STREAM_DELETE_DATA:
+    case STREAM_RETRIEVE: {
-  case STREAM_RETRIEVE: {
+      SColumnInfoData* pColInfo = taosArrayGet(pBlock->pDataBlock, groupColIndex);
-    SColumnInfoData* pColInfo = taosArrayGet(pBlock->pDataBlock, groupColIndex);
+      uint64_t*        groupCol = (uint64_t*)pColInfo->pData;
-    uint64_t* groupCol = (uint64_t*)pColInfo->pData;
+      pInfo->groupId = groupCol[rowIndex];
-    pInfo->groupId = groupCol[rowIndex];
+    } break;
-  }
+    default:
-    break;
+      break;
-  default:
-    break;
   }
 }
 
@@ -854,17 +858,17 @@ void resetTableScanInfo(STableScanInfo* pTableScanInfo, STimeWindow* pWin) {
   pTableScanInfo->currentGroupId = -1;
 }
 
-static bool prepareRangeScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, int32_t* pRowIndex) {
+static bool prepareRangeScan(SStreamScanInfo* pInfo, SSDataBlock* pBlock, int32_t* pRowIndex) {
   if ((*pRowIndex) == pBlock->info.rows) {
     return false;
   }
 
   ASSERT(taosArrayGetSize(pBlock->pDataBlock) >= 3);
   SColumnInfoData* pStartTsCol = taosArrayGet(pBlock->pDataBlock, START_TS_COLUMN_INDEX);
-  TSKEY* startData = (TSKEY*)pStartTsCol->pData;
+  TSKEY*           startData = (TSKEY*)pStartTsCol->pData;
   SColumnInfoData* pEndTsCol = taosArrayGet(pBlock->pDataBlock, END_TS_COLUMN_INDEX);
-  TSKEY* endData = (TSKEY*)pEndTsCol->pData;
+  TSKEY*           endData = (TSKEY*)pEndTsCol->pData;
-  STimeWindow win = {.skey = startData[*pRowIndex], .ekey = endData[*pRowIndex]};
+  STimeWindow      win = {.skey = startData[*pRowIndex], .ekey = endData[*pRowIndex]};
   setGroupId(pInfo, pBlock, GROUPID_COLUMN_INDEX, *pRowIndex);
   (*pRowIndex)++;
 
@@ -877,16 +881,16 @@ static bool prepareRangeScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, i
       win.skey = TMIN(win.skey, startData[*pRowIndex]);
       continue;
     }
-    ASSERT( (win.skey > startData[*pRowIndex] && win.ekey < endData[*pRowIndex]) ||
+    ASSERT((win.skey > startData[*pRowIndex] && win.ekey < endData[*pRowIndex]) ||
-            ( isInTimeWindow(&win, startData[*pRowIndex], 0) || isInTimeWindow(&win, endData[*pRowIndex], 0) ) );
+           (isInTimeWindow(&win, startData[*pRowIndex], 0) || isInTimeWindow(&win, endData[*pRowIndex], 0)));
     break;
   }
 
-  resetTableScanInfo(pInfo->pSnapshotReadOp->info, &win);
+  resetTableScanInfo(pInfo->pTableScanOp->info, &win);
   return true;
 }
 
-static bool prepareDataScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
+static bool prepareDataScan(SStreamScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
   STimeWindow win = {
       .skey = INT64_MIN,
       .ekey = INT64_MAX,
@@ -907,11 +911,10 @@ static bool prepareDataScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, int3
       setGroupId(pInfo, pSDB, GROUPID_COLUMN_INDEX, *pRowIndex);
       (*pRowIndex) += updateSessionWindowInfo(pCurWin, tsCols, NULL, pSDB->info.rows, *pRowIndex, gap, NULL);
     } else {
-      win =
+      win = getActiveTimeWindow(NULL, &dumyInfo, tsCols[*pRowIndex], &pInfo->interval, pInfo->interval.precision, NULL);
-          getActiveTimeWindow(NULL, &dumyInfo, tsCols[*pRowIndex], &pInfo->interval, pInfo->interval.precision, NULL);
       setGroupId(pInfo, pSDB, GROUPID_COLUMN_INDEX, *pRowIndex);
-      (*pRowIndex) += getNumOfRowsInTimeWindow(&pSDB->info, tsCols, *pRowIndex, win.ekey, binarySearchForKey, NULL,
+      (*pRowIndex) +=
-                                               TSDB_ORDER_ASC);
+          getNumOfRowsInTimeWindow(&pSDB->info, tsCols, *pRowIndex, win.ekey, binarySearchForKey, NULL, TSDB_ORDER_ASC);
     }
     needRead = true;
   } else if (isStateWindow(pInfo)) {
@@ -929,7 +932,7 @@ static bool prepareDataScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, int3
   if (!needRead) {
     return false;
   }
-  resetTableScanInfo(pInfo->pSnapshotReadOp->info, &win);
+  resetTableScanInfo(pInfo->pTableScanOp->info, &win);
   return true;
 }
 
@@ -946,13 +949,13 @@ static void copyOneRow(SSDataBlock* dest, SSDataBlock* source, int32_t sourceRow
   dest->info.rows++;
 }
 
-static SSDataBlock* doRangeScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
+static SSDataBlock* doRangeScan(SStreamScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
   while (1) {
     SSDataBlock* pResult = NULL;
-    pResult = doTableScan(pInfo->pSnapshotReadOp);
+    pResult = doTableScan(pInfo->pTableScanOp);
     if (!pResult && prepareRangeScan(pInfo, pSDB, pRowIndex)) {
       // scan next window data
-      pResult = doTableScan(pInfo->pSnapshotReadOp);
+      pResult = doTableScan(pInfo->pTableScanOp);
     }
     if (!pResult) {
       blockDataCleanup(pSDB);
@@ -966,14 +969,14 @@ static SSDataBlock* doRangeScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB,
   }
 }
 
-static SSDataBlock* doDataScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
+static SSDataBlock* doDataScan(SStreamScanInfo* pInfo, SSDataBlock* pSDB, int32_t tsColIndex, int32_t* pRowIndex) {
   while (1) {
     SSDataBlock* pResult = NULL;
-    pResult = doTableScan(pInfo->pSnapshotReadOp);
+    pResult = doTableScan(pInfo->pTableScanOp);
     if (pResult == NULL) {
       if (prepareDataScan(pInfo, pSDB, tsColIndex, pRowIndex)) {
         // scan next window data
-        pResult = doTableScan(pInfo->pSnapshotReadOp);
+        pResult = doTableScan(pInfo->pTableScanOp);
       }
     }
     if (!pResult) {
@@ -997,8 +1000,8 @@ static SSDataBlock* doDataScan(SStreamBlockScanInfo* pInfo, SSDataBlock* pSDB, i
     return pResult;
   */
 }
-
+static void generateIntervalTs(SStreamScanInfo* pInfo, SSDataBlock* pDelBlock, SOperatorInfo* pOperator,
-static void generateIntervalTs(SStreamBlockScanInfo* pInfo, SSDataBlock* pDelBlock, SOperatorInfo* pOperator, SSDataBlock* pUpdateRes) {
+                               SSDataBlock* pUpdateRes) {
   if (pDelBlock->info.rows == 0) {
     return;
   }
@@ -1006,18 +1009,20 @@ static void generateIntervalTs(SStreamBlockScanInfo* pInfo, SSDataBlock* pDelBlo
   blockDataEnsureCapacity(pUpdateRes, 64);
   ASSERT(taosArrayGetSize(pDelBlock->pDataBlock) >= 3);
   SColumnInfoData* pStartTsCol = taosArrayGet(pDelBlock->pDataBlock, START_TS_COLUMN_INDEX);
-  TSKEY* startData = (TSKEY*)pStartTsCol->pData;
+  TSKEY*           startData = (TSKEY*)pStartTsCol->pData;
   SColumnInfoData* pEndTsCol = taosArrayGet(pDelBlock->pDataBlock, END_TS_COLUMN_INDEX);
-  TSKEY* endData = (TSKEY*)pEndTsCol->pData;
+  TSKEY*           endData = (TSKEY*)pEndTsCol->pData;
   SColumnInfoData* pGpCol = taosArrayGet(pDelBlock->pDataBlock, UID_COLUMN_INDEX);
-  uint64_t* uidCol = (uint64_t*)pGpCol->pData;
+  uint64_t*        uidCol = (uint64_t*)pGpCol->pData;
 
   SColumnInfoData* pDestTsCol = taosArrayGet(pUpdateRes->pDataBlock, START_TS_COLUMN_INDEX);
   SColumnInfoData* pDestGpCol = taosArrayGet(pUpdateRes->pDataBlock, GROUPID_COLUMN_INDEX);
-  for (int32_t i = pInfo->deleteDataIndex ; i < pDelBlock->info.rows &&
+  for (int32_t i = pInfo->deleteDataIndex;
-      i < pDelBlock->info.capacity - (endData[i] - startData[i])/pInfo->interval.interval - 1; i++) {
+       i < pDelBlock->info.rows &&
+       i < pDelBlock->info.capacity - (endData[i] - startData[i]) / pInfo->interval.interval - 1;
+       i++) {
     uint64_t groupId = getGroupId(pOperator, uidCol[i]);
-    for (TSKEY startTs = startData[i]; startTs <= endData[i]; ) {
+    for (TSKEY startTs = startData[i]; startTs <= endData[i];) {
       colDataAppend(pDestTsCol, pUpdateRes->info.rows, (const char*)&startTs, false);
       colDataAppend(pDestGpCol, pUpdateRes->info.rows, (const char*)&groupId, false);
       pUpdateRes->info.rows++;
@@ -1032,33 +1037,36 @@ static void generateIntervalTs(SStreamBlockScanInfo* pInfo, SSDataBlock* pDelBlo
   }
 }
 
-static void generateScanRange(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, SOperatorInfo* pOperator, SSDataBlock* pUpdateRes) {
+static void generateScanRange(SStreamScanInfo* pInfo, SSDataBlock* pBlock, SOperatorInfo* pOperator,
-   if (pBlock->info.rows == 0) {
+                              SSDataBlock* pUpdateRes) {
+  if (pBlock->info.rows == 0) {
     return;
   }
   blockDataCleanup(pUpdateRes);
   blockDataEnsureCapacity(pUpdateRes, pBlock->info.rows);
   ASSERT(taosArrayGetSize(pBlock->pDataBlock) >= 3);
   SColumnInfoData* pStartTsCol = taosArrayGet(pBlock->pDataBlock, START_TS_COLUMN_INDEX);
-  TSKEY* startData = (TSKEY*)pStartTsCol->pData;
+  TSKEY*           startData = (TSKEY*)pStartTsCol->pData;
   SColumnInfoData* pEndTsCol = taosArrayGet(pBlock->pDataBlock, END_TS_COLUMN_INDEX);
-  TSKEY* endData = (TSKEY*)pEndTsCol->pData;
+  TSKEY*           endData = (TSKEY*)pEndTsCol->pData;
   SColumnInfoData* pGpCol = taosArrayGet(pBlock->pDataBlock, UID_COLUMN_INDEX);
-  uint64_t* uidCol = (uint64_t*)pGpCol->pData;
+  uint64_t*        uidCol = (uint64_t*)pGpCol->pData;
 
   SColumnInfoData* pDestStartCol = taosArrayGet(pUpdateRes->pDataBlock, START_TS_COLUMN_INDEX);
   SColumnInfoData* pDestEndCol = taosArrayGet(pUpdateRes->pDataBlock, END_TS_COLUMN_INDEX);
   SColumnInfoData* pDestGpCol = taosArrayGet(pUpdateRes->pDataBlock, GROUPID_COLUMN_INDEX);
-  int32_t dummy = 0;
+  int32_t          dummy = 0;
-  for (int32_t i = 0 ; i < pBlock->info.rows; i++) {
+  for (int32_t i = 0; i < pBlock->info.rows; i++) {
     uint64_t groupId = getGroupId(pOperator, uidCol[i]);
-    //gap must be 0.
+    // gap must be 0.
-    SResultWindowInfo* pStartWin = getCurSessionWindow(pInfo->sessionSup.pStreamAggSup, startData[i], endData[i], groupId, 0, &dummy);
+    SResultWindowInfo* pStartWin =
+        getCurSessionWindow(pInfo->sessionSup.pStreamAggSup, startData[i], endData[i], groupId, 0, &dummy);
     if (!pStartWin) {
       // window has been closed.
       continue;
     }
-    SResultWindowInfo* pEndWin = getCurSessionWindow(pInfo->sessionSup.pStreamAggSup, endData[i], endData[i], groupId, 0, &dummy);
+    SResultWindowInfo* pEndWin =
+        getCurSessionWindow(pInfo->sessionSup.pStreamAggSup, endData[i], endData[i], groupId, 0, &dummy);
     ASSERT(pEndWin);
     colDataAppend(pDestStartCol, i, (const char*)&pStartWin->win.skey, false);
     colDataAppend(pDestEndCol, i, (const char*)&pEndWin->win.ekey, false);
@@ -1066,7 +1074,7 @@ static void generateScanRange(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock,
     pUpdateRes->info.rows++;
   }
 }
-static void setUpdateData(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, SSDataBlock* pUpdateBlock) {
+static void setUpdateData(SStreamScanInfo* pInfo, SSDataBlock* pBlock, SSDataBlock* pUpdateBlock) {
   blockDataCleanup(pUpdateBlock);
   int32_t size = taosArrayGetSize(pInfo->tsArray);
   if (pInfo->tsArrayIndex < size) {
@@ -1075,11 +1083,11 @@ static void setUpdateData(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, SSDa
     blockDataEnsureCapacity(pUpdateBlock, size);
 
     int32_t rowId = *(int32_t*)taosArrayGet(pInfo->tsArray, pInfo->tsArrayIndex);
-    pInfo->groupId = getGroupId(pInfo->pSnapshotReadOp, pBlock->info.uid);
+    pInfo->groupId = getGroupId(pInfo->pTableScanOp, pBlock->info.uid);
     int32_t i = 0;
     for (; i < size; i++) {
       rowId = *(int32_t*)taosArrayGet(pInfo->tsArray, i + pInfo->tsArrayIndex);
-      uint64_t id = getGroupId(pInfo->pSnapshotReadOp, pBlock->info.uid);
+      uint64_t id = getGroupId(pInfo->pTableScanOp, pBlock->info.uid);
       if (pInfo->groupId != id) {
         break;
       }
@@ -1098,12 +1106,11 @@ static void setUpdateData(SStreamBlockScanInfo* pInfo, SSDataBlock* pBlock, SSDa
   }
 
   if (size == 0) {
-    generateIntervalTs(pInfo, pInfo->pDeleteDataRes, pInfo->pSnapshotReadOp, pUpdateBlock);
+    generateIntervalTs(pInfo, pInfo->pDeleteDataRes, pInfo->pTableScanOp, pUpdateBlock);
   }
 }
 
-static void checkUpdateData(SStreamBlockScanInfo* pInfo, bool invertible, SSDataBlock* pBlock,
+static void checkUpdateData(SStreamScanInfo* pInfo, bool invertible, SSDataBlock* pBlock, bool out) {
-    bool out) {
   SColumnInfoData* pColDataInfo = taosArrayGet(pBlock->pDataBlock, pInfo->primaryTsIndex);
   ASSERT(pColDataInfo->info.type == TSDB_DATA_TYPE_TIMESTAMP);
   TSKEY* ts = (TSKEY*)pColDataInfo->pData;
@@ -1119,15 +1126,15 @@ static void setBlockGroupId(SOperatorInfo* pOperator, SSDataBlock* pBlock, int32
   SColumnInfoData* pColDataInfo = taosArrayGet(pBlock->pDataBlock, uidColIndex);
   uint64_t*        uidCol = (uint64_t*)pColDataInfo->pData;
   ASSERT(pBlock->info.rows > 0);
-  for (int32_t i = 0 ; i < pBlock->info.rows; i++) {
+  for (int32_t i = 0; i < pBlock->info.rows; i++) {
     uidCol[i] = getGroupId(pOperator, uidCol[i]);
   }
 }
 
-static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
+static SSDataBlock* doStreamScan(SOperatorInfo* pOperator) {
   // NOTE: this operator does never check if current status is done or not
-  SExecTaskInfo*        pTaskInfo = pOperator->pTaskInfo;
+  SExecTaskInfo*   pTaskInfo = pOperator->pTaskInfo;
-  SStreamBlockScanInfo* pInfo = pOperator->info;
+  SStreamScanInfo* pInfo = pOperator->info;
 
   pTaskInfo->code = pOperator->fpSet._openFn(pOperator);
   if (pTaskInfo->code != TSDB_CODE_SUCCESS || pOperator->status == OP_EXEC_DONE) {
@@ -1145,36 +1152,35 @@ static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
 
     int32_t      current = pInfo->validBlockIndex++;
     SSDataBlock* pBlock = taosArrayGetP(pInfo->pBlockLists, current);
+    // TODO move into scan
     blockDataUpdateTsWindow(pBlock, 0);
     switch (pBlock->info.type) {
-    case STREAM_RETRIEVE:{
+      case STREAM_RETRIEVE: {
-      pInfo->blockType = STREAM_INPUT__DATA_SUBMIT;
+        pInfo->blockType = STREAM_INPUT__DATA_SUBMIT;
-      pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER_RETRIEVE;
+        pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER_RETRIEVE;
-      copyDataBlock(pInfo->pPullDataRes, pBlock);
+        copyDataBlock(pInfo->pPullDataRes, pBlock);
-      pInfo->pullDataResIndex = 0;
+        pInfo->pullDataResIndex = 0;
-      prepareDataScan(pInfo, pInfo->pPullDataRes, START_TS_COLUMN_INDEX, &pInfo->pullDataResIndex);
+        prepareDataScan(pInfo, pInfo->pPullDataRes, START_TS_COLUMN_INDEX, &pInfo->pullDataResIndex);
-      updateInfoAddCloseWindowSBF(pInfo->pUpdateInfo);
+        updateInfoAddCloseWindowSBF(pInfo->pUpdateInfo);
-    }
+      } break;
-      break;
+      case STREAM_DELETE_DATA: {
-    case STREAM_DELETE_DATA: {
+        pInfo->blockType = STREAM_INPUT__DATA_SUBMIT;
-      pInfo->blockType = STREAM_INPUT__DATA_SUBMIT;
+        pInfo->updateResIndex = 0;
-      pInfo->updateResIndex = 0;
+        if (isIntervalWindow(pInfo)) {
-      if (isIntervalWindow(pInfo)) {
+          copyDataBlock(pInfo->pDeleteDataRes, pBlock);
-        copyDataBlock(pInfo->pDeleteDataRes, pBlock);
+          generateIntervalTs(pInfo, pInfo->pDeleteDataRes, pInfo->pTableScanOp, pInfo->pUpdateRes);
-        generateIntervalTs(pInfo, pInfo->pDeleteDataRes, pInfo->pSnapshotReadOp, pInfo->pUpdateRes);
+          prepareDataScan(pInfo, pInfo->pUpdateRes, START_TS_COLUMN_INDEX, &pInfo->updateResIndex);
-        prepareDataScan(pInfo, pInfo->pUpdateRes, START_TS_COLUMN_INDEX, &pInfo->updateResIndex);
+          pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER;
-        pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER;
+        } else {
-      } else {
+          generateScanRange(pInfo, pBlock, pInfo->pTableScanOp, pInfo->pUpdateRes);
-        generateScanRange(pInfo, pBlock, pInfo->pSnapshotReadOp, pInfo->pUpdateRes);
+          prepareRangeScan(pInfo, pInfo->pUpdateRes, &pInfo->updateResIndex);
-        prepareRangeScan(pInfo, pInfo->pUpdateRes, &pInfo->updateResIndex);
+          pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER_RANGE;
-        pInfo->scanMode = STREAM_SCAN_FROM_DATAREADER_RANGE;
+        }
-      }
+        pInfo->pUpdateRes->info.type = STREAM_DELETE_DATA;
-      pInfo->pUpdateRes->info.type = STREAM_DELETE_DATA;
+        return pInfo->pUpdateRes;
-      return pInfo->pUpdateRes;
+      } break;
-    }
+      default:
-      break;
+        break;
-    default:
-      break;
     }
     return pBlock;
   } else if (pInfo->blockType == STREAM_INPUT__DATA_SUBMIT) {
@@ -1233,38 +1239,35 @@ static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
     SDataBlockInfo* pBlockInfo = &pInfo->pRes->info;
     blockDataCleanup(pInfo->pRes);
 
-    while (tqNextDataBlock(pInfo->streamBlockReader)) {
+    while (tqNextDataBlock(pInfo->tqReader)) {
       SSDataBlock block = {0};
 
       // todo refactor
-      int32_t code = tqRetrieveDataBlock(&block, pInfo->streamBlockReader);
+      int32_t code = tqRetrieveDataBlock(&block, pInfo->tqReader);
 
-      uint64_t groupId = block.info.groupId;
+      if (code != TSDB_CODE_SUCCESS || block.info.rows == 0) {
-      uint64_t uid = block.info.uid;
-      int32_t  numOfRows = block.info.rows;
-
-      if (code != TSDB_CODE_SUCCESS || numOfRows == 0) {
         pTaskInfo->code = code;
         return NULL;
       }
 
-      pInfo->pRes->info.groupId = groupId;
+      pInfo->pRes->info.rows = block.info.rows;
-      pInfo->pRes->info.rows = numOfRows;
+      pInfo->pRes->info.uid = block.info.uid;
-      pInfo->pRes->info.uid = uid;
       pInfo->pRes->info.type = STREAM_NORMAL;
-      pInfo->pRes->info.capacity = numOfRows;
+      pInfo->pRes->info.capacity = block.info.rows;
+
+
+
+      uint64_t* groupIdPre = taosHashGet(pOperator->pTaskInfo->tableqinfoList.map, &block.info.uid, sizeof(int64_t));
+      if (groupIdPre) {
+        pInfo->pRes->info.groupId = *groupIdPre;
+      } else {
+        pInfo->pRes->info.groupId = 0;
+      }
 
       // for generating rollup SMA result, each time is an independent time serie.
       // TODO temporarily used, when the statement of "partition by tbname" is ready, remove this
       if (pInfo->assignBlockUid) {
-        pInfo->pRes->info.groupId = uid;
+        pInfo->pRes->info.groupId = block.info.uid;
-      } else {
-        pInfo->pRes->info.groupId = groupId;
-      }
-
-      uint64_t* groupIdPre = taosHashGet(pOperator->pTaskInfo->tableqinfoList.map, &uid, sizeof(int64_t));
-      if (groupIdPre) {
-        pInfo->pRes->info.groupId = *groupIdPre;
       }
 
       // todo extract method
@@ -1333,11 +1336,13 @@ static SSDataBlock* doStreamBlockScan(SOperatorInfo* pOperator) {
         }
       }
     }
+
     return (pBlockInfo->rows == 0) ? NULL : pInfo->pRes;
+
   } else if (pInfo->blockType == STREAM_INPUT__DATA_SCAN) {
     // check reader last status
     // if not match, reset status
-    SSDataBlock* pResult = doTableScan(pInfo->pSnapshotReadOp);
+    SSDataBlock* pResult = doTableScan(pInfo->pTableScanOp);
     return pResult && pResult->info.rows > 0 ? pResult : NULL;
 
   } else {
@@ -1361,8 +1366,8 @@ static SArray* extractTableIdList(const STableListInfo* pTableGroupInfo) {
 SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhysiNode* pTableScanNode,
                                             SExecTaskInfo* pTaskInfo, STimeWindowAggSupp* pTwSup, uint64_t queryId,
                                             uint64_t taskId) {
-  SStreamBlockScanInfo* pInfo = taosMemoryCalloc(1, sizeof(SStreamBlockScanInfo));
+  SStreamScanInfo* pInfo = taosMemoryCalloc(1, sizeof(SStreamScanInfo));
-  SOperatorInfo*        pOperator = taosMemoryCalloc(1, sizeof(SOperatorInfo));
+  SOperatorInfo*   pOperator = taosMemoryCalloc(1, sizeof(SOperatorInfo));
 
   if (pInfo == NULL || pOperator == NULL) {
     terrno = TSDB_CODE_QRY_OUT_OF_MEMORY;
@@ -1400,13 +1405,25 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
   }
 
   if (pHandle) {
-    SOperatorInfo*  pTableScanDummy = createTableScanOperatorInfo(pTableScanNode, pHandle, pTaskInfo);
+    SOperatorInfo*  pTableScanOp = createTableScanOperatorInfo(pTableScanNode, pHandle, pTaskInfo);
-    STableScanInfo* pSTInfo = (STableScanInfo*)pTableScanDummy->info;
+    STableScanInfo* pSTInfo = (STableScanInfo*)pTableScanOp->info;
 
     SArray* tableList = taosArrayGetP(pTaskInfo->tableqinfoList.pGroupList, 0);
-    if (pHandle->tqReader) {
+    if (pHandle->initTableReader) {
       pSTInfo->scanMode = TABLE_SCAN__TABLE_ORDER;
-      tsdbReaderOpen(pHandle->vnode, &pSTInfo->cond, tableList, &pSTInfo->dataReader, 0);
+      pSTInfo->dataReader = NULL;
+      if (tsdbReaderOpen(pHandle->vnode, &pSTInfo->cond, tableList, &pSTInfo->dataReader, NULL) < 0) {
+        ASSERT(0);
+      }
+    }
+
+    if (pHandle->initTqReader) {
+      ASSERT(pHandle->tqReader == NULL);
+      pInfo->tqReader = tqOpenReader(pHandle->vnode);
+      ASSERT(pInfo->tqReader);
+    } else {
+      ASSERT(pHandle->tqReader);
+      pInfo->tqReader = pHandle->tqReader;
     }
 
     if (pSTInfo->interval.interval > 0) {
@@ -1414,18 +1431,17 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
     } else {
       pInfo->pUpdateInfo = NULL;
     }
-    pInfo->pSnapshotReadOp = pTableScanDummy;
+
+    pInfo->pTableScanOp = pTableScanOp;
     pInfo->interval = pSTInfo->interval;
 
     pInfo->readHandle = *pHandle;
-    ASSERT(pHandle->reader);
-    pInfo->streamBlockReader = pHandle->reader;
     pInfo->tableUid = pScanPhyNode->uid;
 
     // set the extract column id to streamHandle
-    tqReadHandleSetColIdList((SStreamReader*)pHandle->reader, pColIds);
+    tqReaderSetColIdList(pInfo->tqReader, pColIds);
     SArray* tableIdList = extractTableIdList(&pTaskInfo->tableqinfoList);
-    int32_t code = tqReadHandleSetTbUidList(pHandle->reader, tableIdList);
+    int32_t code = tqReaderSetTbUidList(pInfo->tqReader, tableIdList);
     if (code != 0) {
       taosArrayDestroy(tableIdList);
       goto _error;
@@ -1449,7 +1465,7 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
   pInfo->deleteDataIndex = 0;
   pInfo->pDeleteDataRes = createPullDataBlock();
 
-  pOperator->name = "StreamBlockScanOperator";
+  pOperator->name = "StreamScanOperator";
   pOperator->operatorType = QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN;
   pOperator->blocking = false;
   pOperator->status = OP_NOT_OPENED;
@@ -1458,7 +1474,7 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
   pOperator->pTaskInfo = pTaskInfo;
 
   pOperator->fpSet =
-      createOperatorFpSet(operatorDummyOpenFn, doStreamBlockScan, NULL, NULL, operatorDummyCloseFn, NULL, NULL, NULL);
+      createOperatorFpSet(operatorDummyOpenFn, doStreamScan, NULL, NULL, operatorDummyCloseFn, NULL, NULL, NULL);
 
   return pOperator;
 
@@ -1481,6 +1497,8 @@ static void destroySysScanOperator(void* param, int32_t numOfOutput) {
 
   taosArrayDestroy(pInfo->scanCols);
   taosMemoryFreeClear(pInfo->pUser);
+
+  taosMemoryFreeClear(param);
 }
 
 static int32_t getSysTableDbNameColId(const char* pTable) {
@@ -2159,6 +2177,8 @@ static SSDataBlock* doTagScan(SOperatorInfo* pOperator) {
 static void destroyTagScanOperatorInfo(void* param, int32_t numOfOutput) {
   STagScanInfo* pInfo = (STagScanInfo*)param;
   pInfo->pRes = blockDataDestroy(pInfo->pRes);
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createTagScanOperatorInfo(SReadHandle* pReadHandle, STagScanPhysiNode* pPhyNode,
@@ -2340,7 +2360,7 @@ static int32_t loadDataBlockFromOneTable(SOperatorInfo* pOperator, STableMergeSc
     bool             allColumnsHaveAgg = true;
     SColumnDataAgg** pColAgg = NULL;
     STsdbReader*     reader = taosArrayGetP(pTableScanInfo->dataReaders, readerIdx);
-    tsdbRetrieveDataBlockStatisInfo(reader, &pColAgg, &allColumnsHaveAgg);
+    tsdbRetrieveDatablockSMA(reader, &pColAgg, &allColumnsHaveAgg);
 
     if (allColumnsHaveAgg == true) {
       int32_t numOfCols = taosArrayGetSize(pBlock->pDataBlock);
@@ -2649,6 +2669,8 @@ void destroyTableMergeScanOperatorInfo(void* param, int32_t numOfOutput) {
   pTableScanInfo->pSortInputBlock = blockDataDestroy(pTableScanInfo->pSortInputBlock);
 
   taosArrayDestroy(pTableScanInfo->pSortInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 typedef struct STableMergeScanExecInfo {
@@ -2780,6 +2802,8 @@ static void destroyLastrowScanOperator(void* param, int32_t numOfOutput) {
   SLastrowScanInfo* pInfo = (SLastrowScanInfo*)param;
   blockDataDestroy(pInfo->pRes);
   tsdbLastrowReaderClose(pInfo->pLastrowReader);
+
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createLastrowScanOperator(SLastRowScanPhysiNode* pScanNode, SReadHandle* readHandle, SArray* pTableList,

source/libs/executor/src/sortoperator.c

@@ -235,6 +235,8 @@ void destroyOrderOperatorInfo(void* param, int32_t numOfOutput) {
 
   taosArrayDestroy(pInfo->pSortInfo);
   taosArrayDestroy(pInfo->pColMatchInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 int32_t getExplainExecInfo(SOperatorInfo* pOptr, void** pOptrExplain, uint32_t* len) {
@@ -451,6 +453,8 @@ void destroyGroupSortOperatorInfo(void* param, int32_t numOfOutput) {
 
   taosArrayDestroy(pInfo->pSortInfo);
   taosArrayDestroy(pInfo->pColMatchInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createGroupSortOperatorInfo(SOperatorInfo* downstream, SGroupSortPhysiNode* pSortPhyNode,
@@ -670,6 +674,8 @@ void destroyMultiwayMergeOperatorInfo(void* param, int32_t numOfOutput) {
 
   taosArrayDestroy(pInfo->pSortInfo);
   taosArrayDestroy(pInfo->pColMatchInfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 int32_t getMultiwayMergeExplainExecInfo(SOperatorInfo* pOptr, void** pOptrExplain, uint32_t* len) {

source/libs/executor/src/timewindowoperator.c

@@ -1316,7 +1316,7 @@ bool doDeleteIntervalWindow(SAggSupporter* pAggSup, TSKEY ts, uint64_t groupId)
     // window has been closed
     return false;
   }
-  SFilePage* bufPage = getBufPage(pAggSup->pResultBuf, p1->pageId);
+  // SFilePage* bufPage = getBufPage(pAggSup->pResultBuf, p1->pageId);
   // dBufSetBufPageRecycled(pAggSup->pResultBuf, bufPage);
   taosHashRemove(pAggSup->pResultRowHashTable, pAggSup->keyBuf, GET_RES_WINDOW_KEY_LEN(bytes));
   return true;
@@ -1419,7 +1419,7 @@ static int32_t closeIntervalWindow(SHashObj* pHashMap, STimeWindowAggSupp* pSup,
         ASSERT(pRecyPages != NULL);
         taosArrayPush(pRecyPages, &pPos->pageId);
       } else {
-        SFilePage* bufPage = getBufPage(pDiscBuf, pPos->pageId);
+        // SFilePage* bufPage = getBufPage(pDiscBuf, pPos->pageId);
         // dBufSetBufPageRecycled(pDiscBuf, bufPage);
       }
       char keyBuf[GET_RES_WINDOW_KEY_LEN(sizeof(TSKEY))];
@@ -1446,7 +1446,7 @@ static void freeAllPages(SArray* pageIds, SDiskbasedBuf* pDiskBuf) {
   int32_t size = taosArrayGetSize(pageIds);
   for (int32_t i = 0; i < size; i++) {
     int32_t pageId = *(int32_t*)taosArrayGet(pageIds, i);
-    SFilePage* bufPage = getBufPage(pDiskBuf, pageId);
+    // SFilePage* bufPage = getBufPage(pDiskBuf, pageId);
     // dBufSetBufPageRecycled(pDiskBuf, bufPage);
   }
   taosArrayClear(pageIds);
@@ -1557,6 +1557,8 @@ static void destroyStateWindowOperatorInfo(void* param, int32_t numOfOutput) {
   SStateWindowOperatorInfo* pInfo = (SStateWindowOperatorInfo*)param;
   cleanupBasicInfo(&pInfo->binfo);
   taosMemoryFreeClear(pInfo->stateKey.pData);
+  
+  taosMemoryFreeClear(param);
 }
 
 void destroyIntervalOperatorInfo(void* param, int32_t numOfOutput) {
@@ -1564,6 +1566,8 @@ void destroyIntervalOperatorInfo(void* param, int32_t numOfOutput) {
   cleanupBasicInfo(&pInfo->binfo);
   cleanupAggSup(&pInfo->aggSup);
   taosArrayDestroy(pInfo->pRecycledPages);
+  
+  taosMemoryFreeClear(param);
 }
 
 void destroyStreamFinalIntervalOperatorInfo(void* param, int32_t numOfOutput) {
@@ -1586,6 +1590,8 @@ void destroyStreamFinalIntervalOperatorInfo(void* param, int32_t numOfOutput) {
     }
   }
   nodesDestroyNode((SNode*)pInfo->pPhyNode);
+  
+  taosMemoryFreeClear(param);
 }
 
 static bool allInvertible(SqlFunctionCtx* pFCtx, int32_t numOfCols) {
@@ -2319,6 +2325,8 @@ _error:
 void destroySWindowOperatorInfo(void* param, int32_t numOfOutput) {
   SSessionAggOperatorInfo* pInfo = (SSessionAggOperatorInfo*)param;
   cleanupBasicInfo(&pInfo->binfo);
+  
+  taosMemoryFreeClear(param);
 }
 
 SOperatorInfo* createSessionAggOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
@@ -2995,6 +3003,8 @@ void destroyStreamSessionAggOperatorInfo(void* param, int32_t numOfOutput) {
       taosMemoryFreeClear(pChInfo);
     }
   }
+  
+  taosMemoryFreeClear(param);
 }
 
 int32_t initBasicInfoEx(SOptrBasicInfo* pBasicInfo, SExprSupp* pSup, SExprInfo* pExprInfo, int32_t numOfCols,
@@ -3023,7 +3033,7 @@ void initDummyFunction(SqlFunctionCtx* pDummy, SqlFunctionCtx* pCtx, int32_t num
 void initDownStream(SOperatorInfo* downstream, SStreamAggSupporter* pAggSup, int64_t gap, int64_t waterMark,
                     uint8_t type) {
   ASSERT(downstream->operatorType == QUERY_NODE_PHYSICAL_PLAN_STREAM_SCAN);
-  SStreamBlockScanInfo* pScanInfo = downstream->info;
+  SStreamScanInfo* pScanInfo = downstream->info;
   pScanInfo->sessionSup = (SessionWindowSupporter){.pStreamAggSup = pAggSup, .gap = gap, .parentType = type};
   pScanInfo->pUpdateInfo = updateInfoInit(60000, TSDB_TIME_PRECISION_MILLI, waterMark);
 }
@@ -3189,7 +3199,7 @@ SResultWindowInfo* getCurSessionWindow(SStreamAggSupporter* pAggSup, TSKEY start
       *pIndex = index + 1;
       return pWin;
     } else if (endTs != INT64_MIN && isInWindow(pWin, endTs, gap)) {
-      *pIndex = index;
+      *pIndex = index + 1;
       return pWin;
     }
   }
@@ -3442,7 +3452,7 @@ void deleteWindow(SArray* pWinInfos, int32_t index) {
   taosArrayRemove(pWinInfos, index);
 }
 
-static void doDeleteSessionWindows(SStreamAggSupporter* pAggSup, SSDataBlock* pBlock, int64_t gap, SArray* result) {
+static void doDeleteTimeWindows(SStreamAggSupporter* pAggSup, SSDataBlock* pBlock, int64_t gap, SArray* result) {
   SColumnInfoData* pStartTsCol = taosArrayGet(pBlock->pDataBlock, START_TS_COLUMN_INDEX);
   TSKEY* startDatas = (TSKEY*)pStartTsCol->pData;
   SColumnInfoData* pEndTsCol = taosArrayGet(pBlock->pDataBlock, END_TS_COLUMN_INDEX);
@@ -3580,8 +3590,8 @@ typedef SResultWindowInfo* (*__get_win_info_)(void*);
 SResultWindowInfo* getResWinForSession(void* pData) { return (SResultWindowInfo*)pData; }
 SResultWindowInfo* getResWinForState(void* pData) { return &((SStateWindowInfo*)pData)->winInfo; }
 
-int32_t closeSessionWindow(SHashObj* pHashMap, STimeWindowAggSupp* pTwSup,
+int32_t closeSessionWindow(SHashObj* pHashMap, STimeWindowAggSupp* pTwSup, SArray* pClosed, __get_win_info_ fn,
-    SArray* pClosed, __get_win_info_ fn, bool delete) {
+                           bool delete) {
   // Todo(liuyao) save window to tdb
   void** pIte = NULL;
   size_t keyLen = 0;
@@ -3700,13 +3710,13 @@ static SSDataBlock* doStreamSessionAgg(SOperatorInfo* pOperator) {
     } else if (pBlock->info.type == STREAM_DELETE_DATA || pBlock->info.type == STREAM_DELETE_RESULT) {
       SArray* pWins = taosArrayInit(16, sizeof(SResultWindowInfo));
       // gap must be 0
-      doDeleteSessionWindows(&pInfo->streamAggSup, pBlock, 0, pWins);
+      doDeleteTimeWindows(&pInfo->streamAggSup, pBlock, 0, pWins);
       if (IS_FINAL_OP(pInfo)) {
         int32_t                        childIndex = getChildIndex(pBlock);
         SOperatorInfo*                 pChildOp = taosArrayGetP(pInfo->pChildren, childIndex);
         SStreamSessionAggOperatorInfo* pChildInfo = pChildOp->info;
         // gap must be 0
-        doDeleteSessionWindows(&pChildInfo->streamAggSup, pBlock, 0, NULL);
+        doDeleteTimeWindows(&pChildInfo->streamAggSup, pBlock, 0, NULL);
         rebuildTimeWindow(pInfo, pWins, pBlock->info.groupId, pOperator->exprSupp.numOfExprs, pOperator);
       }
       copyDeleteWindowInfo(pWins, pInfo->pStDeleted);
@@ -3743,8 +3753,8 @@ static SSDataBlock* doStreamSessionAgg(SOperatorInfo* pOperator) {
   // restore the value
   pOperator->status = OP_RES_TO_RETURN;
 
-  closeSessionWindow(pInfo->streamAggSup.pResultRows, &pInfo->twAggSup, pUpdated,
+  closeSessionWindow(pInfo->streamAggSup.pResultRows, &pInfo->twAggSup, pUpdated, getResWinForSession,
-      getResWinForSession, pInfo->ignoreExpiredData);
+                     pInfo->ignoreExpiredData);
   closeChildSessionWindow(pInfo->pChildren, pInfo->twAggSup.maxTs, pInfo->ignoreExpiredData);
   copyUpdateResult(pStUpdated, pUpdated);
   taosHashCleanup(pStUpdated);
@@ -3840,7 +3850,7 @@ static SSDataBlock* doStreamSessionSemiAgg(SOperatorInfo* pOperator) {
       break;
     } else if (pBlock->info.type == STREAM_DELETE_DATA || pBlock->info.type == STREAM_DELETE_RESULT) {
       // gap must be 0
-      doDeleteSessionWindows(&pInfo->streamAggSup, pBlock, 0, NULL); 
+      doDeleteTimeWindows(&pInfo->streamAggSup, pBlock, 0, NULL); 
       copyDataBlock(pInfo->pDelRes, pBlock);
       pInfo->pDelRes->info.type = STREAM_DELETE_RESULT;
       break;
@@ -3954,6 +3964,8 @@ void destroyStreamStateOperatorInfo(void* param, int32_t numOfOutput) {
       taosMemoryFreeClear(pChInfo);
     }
   }
+
+  taosMemoryFreeClear(param);
 }
 
 int64_t getStateWinTsKey(void* data, int32_t index) {
@@ -4232,6 +4244,12 @@ static SSDataBlock* doStreamStateAgg(SOperatorInfo* pOperator) {
       doClearStateWindows(&pInfo->streamAggSup, pBlock, pInfo->primaryTsIndex, &pInfo->stateCol, pInfo->stateCol.slotId,
                           pSeUpdated, pInfo->pSeDeleted);
       continue;
+    } else if (pBlock->info.type == STREAM_DELETE_DATA) {
+      SArray* pWins = taosArrayInit(16, sizeof(SResultWindowInfo));
+      doDeleteTimeWindows(&pInfo->streamAggSup, pBlock, 0, pWins);
+      copyDeleteWindowInfo(pWins, pInfo->pSeDeleted);
+      taosArrayDestroy(pWins);
+      continue;
     } else if (pBlock->info.type == STREAM_GET_ALL) {
       getAllSessionWindow(pInfo->streamAggSup.pResultRows, pUpdated, getResWinForState);
       continue;
@@ -4245,8 +4263,8 @@ static SSDataBlock* doStreamStateAgg(SOperatorInfo* pOperator) {
   // restore the value
   pOperator->status = OP_RES_TO_RETURN;
 
-  closeSessionWindow(pInfo->streamAggSup.pResultRows, &pInfo->twAggSup, pUpdated,
+  closeSessionWindow(pInfo->streamAggSup.pResultRows, &pInfo->twAggSup, pUpdated, getResWinForState,
-      getResWinForState, pInfo->ignoreExpiredData);
+                     pInfo->ignoreExpiredData);
   closeChildSessionWindow(pInfo->pChildren, pInfo->twAggSup.maxTs, pInfo->ignoreExpiredData);
   copyUpdateResult(pSeUpdated, pUpdated);
   taosHashCleanup(pSeUpdated);
@@ -4351,23 +4369,27 @@ _error:
 }
 
 typedef struct SMergeAlignedIntervalAggOperatorInfo {
-  SIntervalAggOperatorInfo intervalAggOperatorInfo;
+  SIntervalAggOperatorInfo *intervalAggOperatorInfo;
 
   bool         hasGroupId;
   uint64_t     groupId;
   SSDataBlock* prefetchedBlock;
   bool         inputBlocksFinished;
+
+  SNode*       pCondition;
 } SMergeAlignedIntervalAggOperatorInfo;
 
 void destroyMergeAlignedIntervalOperatorInfo(void* param, int32_t numOfOutput) {
   SMergeAlignedIntervalAggOperatorInfo* miaInfo = (SMergeAlignedIntervalAggOperatorInfo*)param;
-  destroyIntervalOperatorInfo(&miaInfo->intervalAggOperatorInfo, numOfOutput);
+  destroyIntervalOperatorInfo(miaInfo->intervalAggOperatorInfo, numOfOutput);
+
+  taosMemoryFreeClear(param);
 }
 
 static int32_t outputMergeAlignedIntervalResult(SOperatorInfo* pOperatorInfo, uint64_t tableGroupId,
                                                 SSDataBlock* pResultBlock, TSKEY wstartTs) {
   SMergeAlignedIntervalAggOperatorInfo* miaInfo = pOperatorInfo->info;
-  SIntervalAggOperatorInfo*             iaInfo = &miaInfo->intervalAggOperatorInfo;
+  SIntervalAggOperatorInfo*             iaInfo = miaInfo->intervalAggOperatorInfo;
   SExecTaskInfo*                        pTaskInfo = pOperatorInfo->pTaskInfo;
 
   SExprSupp* pSup = &pOperatorInfo->exprSupp;
@@ -4388,7 +4410,7 @@ static int32_t outputMergeAlignedIntervalResult(SOperatorInfo* pOperatorInfo, ui
 static void doMergeAlignedIntervalAggImpl(SOperatorInfo* pOperatorInfo, SResultRowInfo* pResultRowInfo,
                                           SSDataBlock* pBlock, int32_t scanFlag, SSDataBlock* pResultBlock) {
   SMergeAlignedIntervalAggOperatorInfo* miaInfo = pOperatorInfo->info;
-  SIntervalAggOperatorInfo*             iaInfo = &miaInfo->intervalAggOperatorInfo;
+  SIntervalAggOperatorInfo*             iaInfo = miaInfo->intervalAggOperatorInfo;
 
   SExecTaskInfo* pTaskInfo = pOperatorInfo->pTaskInfo;
   SExprSupp*     pSup = &pOperatorInfo->exprSupp;
@@ -4453,7 +4475,7 @@ static SSDataBlock* doMergeAlignedIntervalAgg(SOperatorInfo* pOperator) {
   SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
 
   SMergeAlignedIntervalAggOperatorInfo* miaInfo = pOperator->info;
-  SIntervalAggOperatorInfo*             iaInfo = &miaInfo->intervalAggOperatorInfo;
+  SIntervalAggOperatorInfo*             iaInfo = miaInfo->intervalAggOperatorInfo;
   if (pOperator->status == OP_EXEC_DONE) {
     return NULL;
   }
@@ -4492,8 +4514,8 @@ static SSDataBlock* doMergeAlignedIntervalAgg(SOperatorInfo* pOperator) {
       getTableScanInfo(pOperator, &iaInfo->order, &scanFlag);
       setInputDataBlock(pOperator, pSup->pCtx, pBlock, iaInfo->order, scanFlag, true);
       doMergeAlignedIntervalAggImpl(pOperator, &iaInfo->binfo.resultRowInfo, pBlock, scanFlag, pRes);
-
+      doFilter(miaInfo->pCondition, pRes);
-      if (pRes->info.rows >= pOperator->resultInfo.threshold) {
+      if (pRes->info.rows > 0) {
         break;
       }
     }
@@ -4501,7 +4523,7 @@ static SSDataBlock* doMergeAlignedIntervalAgg(SOperatorInfo* pOperator) {
     pRes->info.groupId = miaInfo->groupId;
   }
 
-  if (pRes->info.rows == 0) {
+  if (miaInfo->inputBlocksFinished) {
     doSetOperatorCompleted(pOperator);
   }
 
@@ -4512,16 +4534,22 @@ static SSDataBlock* doMergeAlignedIntervalAgg(SOperatorInfo* pOperator) {
 
 SOperatorInfo* createMergeAlignedIntervalOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo,
                                                       int32_t numOfCols, SSDataBlock* pResBlock, SInterval* pInterval,
-                                                      int32_t primaryTsSlotId, SExecTaskInfo* pTaskInfo) {
+                                                      int32_t primaryTsSlotId, SNode* pCondition, SExecTaskInfo* pTaskInfo) {
   SMergeAlignedIntervalAggOperatorInfo* miaInfo = taosMemoryCalloc(1, sizeof(SMergeAlignedIntervalAggOperatorInfo));
   SOperatorInfo*                        pOperator = taosMemoryCalloc(1, sizeof(SOperatorInfo));
   if (miaInfo == NULL || pOperator == NULL) {
     goto _error;
   }
 
-  SIntervalAggOperatorInfo* iaInfo = &miaInfo->intervalAggOperatorInfo;
+  miaInfo->intervalAggOperatorInfo = taosMemoryCalloc(1, sizeof(SIntervalAggOperatorInfo));
+  if (miaInfo->intervalAggOperatorInfo == NULL) {
+    goto _error;
+  }
+
+  SIntervalAggOperatorInfo* iaInfo = miaInfo->intervalAggOperatorInfo;
   SExprSupp*                pSup = &pOperator->exprSupp;
 
+  miaInfo->pCondition = pCondition;
   iaInfo->win = pTaskInfo->window;
   iaInfo->order = TSDB_ORDER_ASC;
   iaInfo->interval = *pInterval;
@@ -4596,6 +4624,8 @@ void destroyMergeIntervalOperatorInfo(void* param, int32_t numOfOutput) {
   SMergeIntervalAggOperatorInfo* miaInfo = (SMergeIntervalAggOperatorInfo*)param;
   tdListFree(miaInfo->groupIntervals);
   destroyIntervalOperatorInfo(&miaInfo->intervalAggOperatorInfo, numOfOutput);
+  
+  taosMemoryFreeClear(param);
 }
 
 static int32_t finalizeWindowResult(SOperatorInfo* pOperatorInfo, uint64_t tableGroupId, STimeWindow* win,

source/libs/function/inc/fnLog.h

@@ -10,12 +10,14 @@
 extern "C" {
 #endif
 
-#define fnFatal(...) { if (fnDebugFlag & DEBUG_FATAL) { taosPrintLog("FN  FATAL ", DEBUG_FATAL, 255, __VA_ARGS__); }}
+// clang-format off
-#define fnError(...) { if (fnDebugFlag & DEBUG_ERROR) { taosPrintLog("FN  ERROR ", DEBUG_ERROR, 255, __VA_ARGS__); }}
+#define fnFatal(...) { if (udfDebugFlag & DEBUG_FATAL) { taosPrintLog("UDF FATAL ", DEBUG_FATAL, 255, __VA_ARGS__); }}
-#define fnWarn(...)  { if (fnDebugFlag & DEBUG_WARN)  { taosPrintLog("FN  WARN ", DEBUG_WARN, 255, __VA_ARGS__); }}
+#define fnError(...) { if (udfDebugFlag & DEBUG_ERROR) { taosPrintLog("UDF ERROR ", DEBUG_ERROR, 255, __VA_ARGS__); }}
-#define fnInfo(...)  { if (fnDebugFlag & DEBUG_INFO)  { taosPrintLog("FN  ", DEBUG_INFO, 255, __VA_ARGS__); }}
+#define fnWarn(...)  { if (udfDebugFlag & DEBUG_WARN)  { taosPrintLog("UDF WARN ", DEBUG_WARN, 255, __VA_ARGS__); }}
-#define fnDebug(...) { if (fnDebugFlag & DEBUG_DEBUG) { taosPrintLog("FN  ", DEBUG_DEBUG, dDebugFlag, __VA_ARGS__); }}
+#define fnInfo(...)  { if (udfDebugFlag & DEBUG_INFO)  { taosPrintLog("UDF  ", DEBUG_INFO, 255, __VA_ARGS__); }}
-#define fnTrace(...) { if (fnDebugFlag & DEBUG_TRACE) { taosPrintLog("FN  ", DEBUG_TRACE, dDebugFlag, __VA_ARGS__); }}
+#define fnDebug(...) { if (udfDebugFlag & DEBUG_DEBUG) { taosPrintLog("UDF ", DEBUG_DEBUG, udfDebugFlag, __VA_ARGS__); }}
+#define fnTrace(...) { if (udfDebugFlag & DEBUG_TRACE) { taosPrintLog("UDF ", DEBUG_TRACE, udfDebugFlag, __VA_ARGS__); }}
+// clang-format on
 
 #ifdef __cplusplus
 }

source/libs/function/src/builtinsimpl.c

@@ -1080,6 +1080,19 @@ bool getMinmaxFuncEnv(SFunctionNode* UNUSED_PARAM(pFunc), SFuncExecEnv* pEnv) {
 static void saveTupleData(SqlFunctionCtx* pCtx, int32_t rowIndex, const SSDataBlock* pSrcBlock, STuplePos* pPos);
 static void copyTupleData(SqlFunctionCtx* pCtx, int32_t rowIndex, const SSDataBlock* pSrcBlock, STuplePos* pPos);
 
+static int32_t findRowIndex(int32_t start, int32_t num, SColumnInfoData* pCol, const char* tval) {
+  // the data is loaded, not only the block SMA value
+  for(int32_t i = start; i < num + start; ++i) {
+    char* p = colDataGetData(pCol, i);
+    if (memcpy((void*)tval, p, pCol->info.bytes) == 0)  {
+      return i;
+    }
+  }
+
+  ASSERT(0);
+}
+
+
 int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
   int32_t numOfElems = 0;
 
@@ -1111,15 +1124,14 @@ int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
 
     if (isMinFunc) {
       tval = &pInput->pColumnDataAgg[0]->min;
-      index = pInput->pColumnDataAgg[0]->minIndex;
     } else {
       tval = &pInput->pColumnDataAgg[0]->max;
-      index = pInput->pColumnDataAgg[0]->maxIndex;
     }
 
     if (!pBuf->assign) {
       pBuf->v = *(int64_t*)tval;
       if (pCtx->subsidiaries.num > 0) {
+        index = findRowIndex(pInput->startRowIndex, pInput->numOfRows, pCol, tval);
         saveTupleData(pCtx, index, pCtx->pSrcBlock, &pBuf->tuplePos);
       }
     } else {
@@ -1131,6 +1143,7 @@ int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
         if ((prev < val) ^ isMinFunc) {
           pBuf->v = val;
           if (pCtx->subsidiaries.num > 0) {
+            index = findRowIndex(pInput->startRowIndex, pInput->numOfRows, pCol, tval);
             saveTupleData(pCtx, index, pCtx->pSrcBlock, &pBuf->tuplePos);
           }
         }
@@ -1143,6 +1156,7 @@ int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
         if ((prev < val) ^ isMinFunc) {
           pBuf->v = val;
           if (pCtx->subsidiaries.num > 0) {
+            index = findRowIndex(pInput->startRowIndex, pInput->numOfRows, pCol, tval);
             saveTupleData(pCtx, index, pCtx->pSrcBlock, &pBuf->tuplePos);
           }
         }
@@ -1154,6 +1168,7 @@ int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
         if ((prev < val) ^ isMinFunc) {
           pBuf->v = val;
           if (pCtx->subsidiaries.num > 0) {
+            index = findRowIndex(pInput->startRowIndex, pInput->numOfRows, pCol, tval);
             saveTupleData(pCtx, index, pCtx->pSrcBlock, &pBuf->tuplePos);
           }
         }
@@ -1167,6 +1182,7 @@ int32_t doMinMaxHelper(SqlFunctionCtx* pCtx, int32_t isMinFunc) {
         }
 
         if (pCtx->subsidiaries.num > 0) {
+          index = findRowIndex(pInput->startRowIndex, pInput->numOfRows, pCol, tval);
           saveTupleData(pCtx, index, pCtx->pSrcBlock, &pBuf->tuplePos);
         }
       }
@@ -5547,30 +5563,18 @@ int32_t blockDistFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
     }
   }
 
-  int32_t delta = maxVal - minVal;
+  // maximum number of step is 80
-  int32_t step = delta / 50;
+  double factor = pData->numOfBlocks / 80.0;
-  if (step == 0) {
-    step = 1;
-  }
 
   int32_t numOfBuckets = sizeof(pData->blockRowsHisto) / sizeof(pData->blockRowsHisto[0]);
-  int32_t bucketRange = (pData->maxRows - pData->minRows) / numOfBuckets;
+  int32_t bucketRange = (pData->defMaxRows - pData->defMinRows) / numOfBuckets;
-
-  bool singleModel = false;
-  if (bucketRange == 0) {
-    singleModel = true;
-    step = 20;
-    bucketRange = (pData->defMaxRows - pData->defMinRows) / numOfBuckets;
-  }
 
   for (int32_t i = 0; i < tListLen(pData->blockRowsHisto); ++i) {
-    len = sprintf(st + VARSTR_HEADER_SIZE, "%04d |", pData->defMinRows + bucketRange * (i + 1));
+    len = sprintf(st + VARSTR_HEADER_SIZE, "%04d |", pData->defMinRows + bucketRange * i);
 
     int32_t num = 0;
-    if (singleModel && pData->blockRowsHisto[i] > 0) {
+    if (pData->blockRowsHisto[i] > 0) {
-      num = 20;
+      num = (pData->blockRowsHisto[i]) / factor;
-    } else {
-      num = (pData->blockRowsHisto[i] + step - 1) / step;
     }
 
     for (int32_t j = 0; j < num; ++j) {
@@ -5578,9 +5582,10 @@ int32_t blockDistFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
       len += x;
     }
 
-    double v = pData->blockRowsHisto[i] * 100.0 / pData->numOfBlocks;
+    if (num > 0) {
-    len += sprintf(st + VARSTR_HEADER_SIZE + len, "  %d (%.2f%c)", pData->blockRowsHisto[i], v, '%');
+      double v = pData->blockRowsHisto[i] * 100.0 / pData->numOfBlocks;
-    printf("%s\n", st);
+      len += sprintf(st + VARSTR_HEADER_SIZE + len, "  %d (%.2f%c)", pData->blockRowsHisto[i], v, '%');
+    }
 
     varDataSetLen(st, len);
     colDataAppend(pColInfo, row++, st, false);

source/libs/nodes/src/nodesCodeFuncs.c

@@ -3605,7 +3605,7 @@ static int32_t databaseOptionsToJson(const void* pObj, SJson* pJson) {
 
   int32_t code = tjsonAddIntegerToObject(pJson, jkDatabaseOptionsBuffer, pNode->buffer);
   if (TSDB_CODE_SUCCESS == code) {
-    code = tjsonAddIntegerToObject(pJson, jkDatabaseOptionsCachelast, pNode->cachelast);
+    code = tjsonAddIntegerToObject(pJson, jkDatabaseOptionsCachelast, pNode->cacheLast);
   }
   if (TSDB_CODE_SUCCESS == code) {
     code = tjsonAddIntegerToObject(pJson, jkDatabaseOptionsCompressionLevel, pNode->compressionLevel);
@@ -3667,7 +3667,7 @@ static int32_t jsonToDatabaseOptions(const SJson* pJson, void* pObj) {
 
   int32_t code = tjsonGetIntValue(pJson, jkDatabaseOptionsBuffer, &pNode->buffer);
   if (TSDB_CODE_SUCCESS == code) {
-    code = tjsonGetTinyIntValue(pJson, jkDatabaseOptionsCachelast, &pNode->cachelast);
+    code = tjsonGetTinyIntValue(pJson, jkDatabaseOptionsCachelast, &pNode->cacheLast);
   }
   if (TSDB_CODE_SUCCESS == code) {
     code = tjsonGetTinyIntValue(pJson, jkDatabaseOptionsCompressionLevel, &pNode->compressionLevel);

source/libs/parser/inc/parAst.h

@@ -39,6 +39,7 @@ typedef struct SAstCreateContext {
 typedef enum EDatabaseOptionType {
   DB_OPTION_BUFFER = 1,
   DB_OPTION_CACHELAST,
+  DB_OPTION_CACHELASTSIZE,
   DB_OPTION_COMP,
   DB_OPTION_DAYS,
   DB_OPTION_FSYNC,

source/libs/parser/inc/sql.y

@@ -172,6 +172,7 @@ exists_opt(A) ::= .
 db_options(A) ::= .                                                               { A = createDefaultDatabaseOptions(pCxt); }
 db_options(A) ::= db_options(B) BUFFER NK_INTEGER(C).                             { A = setDatabaseOption(pCxt, B, DB_OPTION_BUFFER, &C); }
 db_options(A) ::= db_options(B) CACHELAST NK_INTEGER(C).                          { A = setDatabaseOption(pCxt, B, DB_OPTION_CACHELAST, &C); }
+db_options(A) ::= db_options(B) CACHELASTSIZE NK_INTEGER(C).                      { A = setDatabaseOption(pCxt, B, DB_OPTION_CACHELASTSIZE, &C); }
 db_options(A) ::= db_options(B) COMP NK_INTEGER(C).                               { A = setDatabaseOption(pCxt, B, DB_OPTION_COMP, &C); }
 db_options(A) ::= db_options(B) DURATION NK_INTEGER(C).                           { A = setDatabaseOption(pCxt, B, DB_OPTION_DAYS, &C); }
 db_options(A) ::= db_options(B) DURATION NK_VARIABLE(C).                          { A = setDatabaseOption(pCxt, B, DB_OPTION_DAYS, &C); }
@@ -198,6 +199,7 @@ alter_db_options(A) ::= alter_db_options(B) alter_db_option(C).
 %destructor alter_db_option                                                       { }
 alter_db_option(A) ::= BUFFER NK_INTEGER(B).                                      { A.type = DB_OPTION_BUFFER; A.val = B; }
 alter_db_option(A) ::= CACHELAST NK_INTEGER(B).                                   { A.type = DB_OPTION_CACHELAST; A.val = B; }
+alter_db_option(A) ::= CACHELASTSIZE NK_INTEGER(B).                               { A.type = DB_OPTION_CACHELASTSIZE; A.val = B; }
 alter_db_option(A) ::= FSYNC NK_INTEGER(B).                                       { A.type = DB_OPTION_FSYNC; A.val = B; }
 alter_db_option(A) ::= KEEP integer_list(B).                                      { A.type = DB_OPTION_KEEP; A.pList = B; }
 alter_db_option(A) ::= KEEP variable_list(B).                                     { A.type = DB_OPTION_KEEP; A.pList = B; }

source/libs/parser/src/parAstCreater.c

@@ -746,7 +746,8 @@ SNode* createDefaultDatabaseOptions(SAstCreateContext* pCxt) {
   SDatabaseOptions* pOptions = (SDatabaseOptions*)nodesMakeNode(QUERY_NODE_DATABASE_OPTIONS);
   CHECK_OUT_OF_MEM(pOptions);
   pOptions->buffer = TSDB_DEFAULT_BUFFER_PER_VNODE;
-  pOptions->cachelast = TSDB_DEFAULT_CACHE_LAST_ROW;
+  pOptions->cacheLast = TSDB_DEFAULT_CACHE_LAST_ROW;
+  pOptions->cacheLastSize = TSDB_DEFAULT_LAST_ROW_MEM;
   pOptions->compressionLevel = TSDB_DEFAULT_COMP_LEVEL;
   pOptions->daysPerFile = TSDB_DEFAULT_DAYS_PER_FILE;
   pOptions->fsyncPeriod = TSDB_DEFAULT_FSYNC_PERIOD;
@@ -772,7 +773,8 @@ SNode* createAlterDatabaseOptions(SAstCreateContext* pCxt) {
   SDatabaseOptions* pOptions = (SDatabaseOptions*)nodesMakeNode(QUERY_NODE_DATABASE_OPTIONS);
   CHECK_OUT_OF_MEM(pOptions);
   pOptions->buffer = -1;
-  pOptions->cachelast = -1;
+  pOptions->cacheLast = -1;
+  pOptions->cacheLastSize = -1;
   pOptions->compressionLevel = -1;
   pOptions->daysPerFile = -1;
   pOptions->fsyncPeriod = -1;
@@ -800,7 +802,10 @@ SNode* setDatabaseOption(SAstCreateContext* pCxt, SNode* pOptions, EDatabaseOpti
       ((SDatabaseOptions*)pOptions)->buffer = taosStr2Int32(((SToken*)pVal)->z, NULL, 10);
       break;
     case DB_OPTION_CACHELAST:
-      ((SDatabaseOptions*)pOptions)->cachelast = taosStr2Int8(((SToken*)pVal)->z, NULL, 10);
+      ((SDatabaseOptions*)pOptions)->cacheLast = taosStr2Int8(((SToken*)pVal)->z, NULL, 10);
+      break;
+    case DB_OPTION_CACHELASTSIZE:
+      ((SDatabaseOptions*)pOptions)->cacheLastSize = taosStr2Int32(((SToken*)pVal)->z, NULL, 10);
       break;
     case DB_OPTION_COMP:
       ((SDatabaseOptions*)pOptions)->compressionLevel = taosStr2Int8(((SToken*)pVal)->z, NULL, 10);

source/libs/parser/src/parTokenizer.c

@@ -53,6 +53,7 @@ static SKeyword keywordTable[] = {
     {"BY",             TK_BY},
     {"CACHE",          TK_CACHE},
     {"CACHELAST",      TK_CACHELAST},
+    {"CACHELASTSIZE",  TK_CACHELASTSIZE},
     {"CAST",           TK_CAST},
     {"CLIENT_VERSION", TK_CLIENT_VERSION},
     {"CLUSTER",        TK_CLUSTER},

source/libs/parser/src/parTranslater.c

@@ -2988,7 +2988,8 @@ static int32_t buildCreateDbReq(STranslateContext* pCxt, SCreateDatabaseStmt* pS
   pReq->compression = pStmt->pOptions->compressionLevel;
   pReq->replications = pStmt->pOptions->replica;
   pReq->strict = pStmt->pOptions->strict;
-  pReq->cacheLastRow = pStmt->pOptions->cachelast;
+  pReq->cacheLastRow = pStmt->pOptions->cacheLast;
+  pReq->lastRowMem = pStmt->pOptions->cacheLastSize;
   pReq->schemaless = pStmt->pOptions->schemaless;
   pReq->ignoreExist = pStmt->ignoreExists;
   return buildCreateDbRetentions(pStmt->pOptions->pRetentions, pReq);
@@ -3149,9 +3150,13 @@ static int32_t checkDatabaseOptions(STranslateContext* pCxt, const char* pDbName
   int32_t code =
       checkRangeOption(pCxt, "buffer", pOptions->buffer, TSDB_MIN_BUFFER_PER_VNODE, TSDB_MAX_BUFFER_PER_VNODE);
   if (TSDB_CODE_SUCCESS == code) {
-    code = checkRangeOption(pCxt, "cacheLast", pOptions->cachelast, TSDB_MIN_DB_CACHE_LAST_ROW,
+    code = checkRangeOption(pCxt, "cacheLast", pOptions->cacheLast, TSDB_MIN_DB_CACHE_LAST_ROW,
                             TSDB_MAX_DB_CACHE_LAST_ROW);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = checkRangeOption(pCxt, "cacheLastSize", pOptions->cacheLastSize, TSDB_MIN_DB_LAST_ROW_MEM,
+                            TSDB_MAX_DB_LAST_ROW_MEM);
+  }
   if (TSDB_CODE_SUCCESS == code) {
     code = checkRangeOption(pCxt, "compression", pOptions->compressionLevel, TSDB_MIN_COMP_LEVEL, TSDB_MAX_COMP_LEVEL);
   }
@@ -3271,7 +3276,8 @@ static void buildAlterDbReq(STranslateContext* pCxt, SAlterDatabaseStmt* pStmt,
   pReq->fsyncPeriod = pStmt->pOptions->fsyncPeriod;
   pReq->walLevel = pStmt->pOptions->walLevel;
   pReq->strict = pStmt->pOptions->strict;
-  pReq->cacheLastRow = pStmt->pOptions->cachelast;
+  pReq->cacheLastRow = pStmt->pOptions->cacheLast;
+  pReq->lastRowMem = pStmt->pOptions->cacheLastSize;
   pReq->replications = pStmt->pOptions->replica;
   return;
 }

source/libs/parser/src/parser.c

@@ -39,6 +39,9 @@ bool qIsInsertValuesSql(const char* pStr, size_t length) {
     if (TK_USING == t.type || TK_VALUES == t.type) {
       return true;
     }
+    if (0 == t.type) {
+      break;
+    }
   } while (pStr - pSql < length);
   return false;
 }

source/libs/parser/test/parInitialCTest.cpp

@@ -77,6 +77,7 @@ TEST_F(ParserInitialCTest, createDatabase) {
     expect.ignoreExist = igExists;
     expect.buffer = TSDB_DEFAULT_BUFFER_PER_VNODE;
     expect.cacheLastRow = TSDB_DEFAULT_CACHE_LAST_ROW;
+    expect.lastRowMem = TSDB_DEFAULT_LAST_ROW_MEM;
     expect.compression = TSDB_DEFAULT_COMP_LEVEL;
     expect.daysPerFile = TSDB_DEFAULT_DAYS_PER_FILE;
     expect.fsyncPeriod = TSDB_DEFAULT_FSYNC_PERIOD;
@@ -97,7 +98,8 @@ TEST_F(ParserInitialCTest, createDatabase) {
   };
 
   auto setDbBufferFunc = [&](int32_t buffer) { expect.buffer = buffer; };
-  auto setDbCachelastFunc = [&](int8_t CACHELAST) { expect.cacheLastRow = CACHELAST; };
+  auto setDbCachelastFunc = [&](int8_t cachelast) { expect.cacheLastRow = cachelast; };
+  auto setDbCachelastSize = [&](int8_t cachelastSize) { expect.lastRowMem = cachelastSize; };
   auto setDbCompressionFunc = [&](int8_t compressionLevel) { expect.compression = compressionLevel; };
   auto setDbDaysFunc = [&](int32_t daysPerFile) { expect.daysPerFile = daysPerFile; };
   auto setDbFsyncFunc = [&](int32_t fsyncPeriod) { expect.fsyncPeriod = fsyncPeriod; };
@@ -154,6 +156,7 @@ TEST_F(ParserInitialCTest, createDatabase) {
     ASSERT_EQ(req.replications, expect.replications);
     ASSERT_EQ(req.strict, expect.strict);
     ASSERT_EQ(req.cacheLastRow, expect.cacheLastRow);
+    ASSERT_EQ(req.lastRowMem, expect.lastRowMem);
     // ASSERT_EQ(req.schemaless, expect.schemaless);
     ASSERT_EQ(req.ignoreExist, expect.ignoreExist);
     ASSERT_EQ(req.numOfRetensions, expect.numOfRetensions);
@@ -179,6 +182,7 @@ TEST_F(ParserInitialCTest, createDatabase) {
   setCreateDbReqFunc("wxy_db", 1);
   setDbBufferFunc(64);
   setDbCachelastFunc(2);
+  setDbCachelastSize(20);
   setDbCompressionFunc(1);
   setDbDaysFunc(100 * 1440);
   setDbFsyncFunc(100);
@@ -200,6 +204,7 @@ TEST_F(ParserInitialCTest, createDatabase) {
   run("CREATE DATABASE IF NOT EXISTS wxy_db "
       "BUFFER 64 "
       "CACHELAST 2 "
+      "CACHELASTSIZE 20 "
       "COMP 1 "
       "DURATION 100 "
       "FSYNC 100 "

source/libs/planner/src/planLogicCreater.c

@@ -1340,6 +1340,17 @@ static void doSetLogicNodeParent(SLogicNode* pNode, SLogicNode* pParent) {
 
 static void setLogicNodeParent(SLogicNode* pNode) { doSetLogicNodeParent(pNode, NULL); }
 
+static void setLogicSubplanType(SLogicSubplan* pSubplan) {
+  if (QUERY_NODE_LOGIC_PLAN_VNODE_MODIFY != nodeType(pSubplan->pNode)) {
+    pSubplan->subplanType = SUBPLAN_TYPE_SCAN;
+  } else {
+    SVnodeModifyLogicNode* pModify = (SVnodeModifyLogicNode*)pSubplan->pNode;
+    pSubplan->subplanType = (MODIFY_TABLE_TYPE_INSERT == pModify->modifyType && NULL != pModify->node.pChildren)
+                                ? SUBPLAN_TYPE_SCAN
+                                : SUBPLAN_TYPE_MODIFY;
+  }
+}
+
 int32_t createLogicPlan(SPlanContext* pCxt, SLogicSubplan** pLogicSubplan) {
   SLogicPlanContext cxt = {.pPlanCxt = pCxt};
 
@@ -1354,11 +1365,7 @@ int32_t createLogicPlan(SPlanContext* pCxt, SLogicSubplan** pLogicSubplan) {
   int32_t code = createQueryLogicNode(&cxt, pCxt->pAstRoot, &pSubplan->pNode);
   if (TSDB_CODE_SUCCESS == code) {
     setLogicNodeParent(pSubplan->pNode);
-    if (QUERY_NODE_LOGIC_PLAN_VNODE_MODIFY == nodeType(pSubplan->pNode)) {
+    setLogicSubplanType(pSubplan);
-      pSubplan->subplanType = SUBPLAN_TYPE_MODIFY;
-    } else {
-      pSubplan->subplanType = SUBPLAN_TYPE_SCAN;
-    }
   }
 
   if (TSDB_CODE_SUCCESS == code) {

source/libs/planner/src/planPhysiCreater.c

@@ -1566,7 +1566,7 @@ static int32_t buildInsertSelectSubplan(SPhysiPlanContext* pCxt, SVnodeModifyLog
   if (TSDB_CODE_SUCCESS == code) {
     code = createQueryInserter(pCxt, pModify, pSubplan, &pSubplan->pDataSink);
   }
-  pSubplan->msgType = TDMT_VND_SUBMIT;
+  pSubplan->msgType = TDMT_SCH_MERGE_QUERY;
   return code;
 }
 

source/libs/planner/src/planSpliter.c

@@ -39,7 +39,6 @@ typedef struct SSplitRule {
   FSplit splitFunc;
 } SSplitRule;
 
-// typedef bool (*FSplFindSplitNode)(SSplitContext* pCxt, SLogicSubplan* pSubplan, void* pInfo);
 typedef bool (*FSplFindSplitNode)(SSplitContext* pCxt, SLogicSubplan* pSubplan, SLogicNode* pNode, void* pInfo);
 
 static void splSetSubplanVgroups(SLogicSubplan* pSubplan, SLogicNode* pNode) {
@@ -67,6 +66,19 @@ static SLogicSubplan* splCreateScanSubplan(SSplitContext* pCxt, SLogicNode* pNod
   return pSubplan;
 }
 
+static SLogicSubplan* splCreateSubplan(SSplitContext* pCxt, SLogicNode* pNode, ESubplanType subplanType) {
+  SLogicSubplan* pSubplan = (SLogicSubplan*)nodesMakeNode(QUERY_NODE_LOGIC_SUBPLAN);
+  if (NULL == pSubplan) {
+    return NULL;
+  }
+  pSubplan->id.queryId = pCxt->queryId;
+  pSubplan->id.groupId = pCxt->groupId;
+  pSubplan->subplanType = subplanType;
+  pSubplan->pNode = pNode;
+  pNode->pParent = NULL;
+  return pSubplan;
+}
+
 static int32_t splCreateExchangeNode(SSplitContext* pCxt, SLogicNode* pChild, SExchangeLogicNode** pOutput) {
   SExchangeLogicNode* pExchange = (SExchangeLogicNode*)nodesMakeNode(QUERY_NODE_LOGIC_PLAN_EXCHANGE);
   if (NULL == pExchange) {
@@ -98,6 +110,43 @@ static int32_t splCreateExchangeNodeForSubplan(SSplitContext* pCxt, SLogicSubpla
   return code;
 }
 
+static bool splIsChildSubplan(SLogicNode* pLogicNode, int32_t groupId) {
+  if (QUERY_NODE_LOGIC_PLAN_EXCHANGE == nodeType(pLogicNode)) {
+    return ((SExchangeLogicNode*)pLogicNode)->srcGroupId == groupId;
+  }
+
+  if (QUERY_NODE_LOGIC_PLAN_MERGE == nodeType(pLogicNode)) {
+    return ((SMergeLogicNode*)pLogicNode)->srcGroupId == groupId;
+  }
+
+  SNode* pChild;
+  FOREACH(pChild, pLogicNode->pChildren) {
+    bool isChild = splIsChildSubplan((SLogicNode*)pChild, groupId);
+    if (isChild) {
+      return isChild;
+    }
+  }
+  return false;
+}
+
+static int32_t splMountSubplan(SLogicSubplan* pParent, SNodeList* pChildren) {
+  SNode* pChild = NULL;
+  WHERE_EACH(pChild, pChildren) {
+    if (splIsChildSubplan(pParent->pNode, ((SLogicSubplan*)pChild)->id.groupId)) {
+      int32_t code = nodesListMakeAppend(&pParent->pChildren, pChild);
+      if (TSDB_CODE_SUCCESS == code) {
+        REPLACE_NODE(NULL);
+        ERASE_NODE(pChildren);
+        continue;
+      } else {
+        return code;
+      }
+    }
+    WHERE_NEXT;
+  }
+  return TSDB_CODE_SUCCESS;
+}
+
 static bool splMatchByNode(SSplitContext* pCxt, SLogicSubplan* pSubplan, SLogicNode* pNode, FSplFindSplitNode func,
                            void* pInfo) {
   if (func(pCxt, pSubplan, pNode, pInfo)) {
@@ -982,56 +1031,6 @@ static int32_t singleTableJoinSplit(SSplitContext* pCxt, SLogicSubplan* pSubplan
   return code;
 }
 
-static bool unionIsChildSubplan(SLogicNode* pLogicNode, int32_t groupId) {
-  if (QUERY_NODE_LOGIC_PLAN_EXCHANGE == nodeType(pLogicNode)) {
-    return ((SExchangeLogicNode*)pLogicNode)->srcGroupId == groupId;
-  }
-
-  if (QUERY_NODE_LOGIC_PLAN_MERGE == nodeType(pLogicNode)) {
-    return ((SMergeLogicNode*)pLogicNode)->srcGroupId == groupId;
-  }
-
-  SNode* pChild;
-  FOREACH(pChild, pLogicNode->pChildren) {
-    bool isChild = unionIsChildSubplan((SLogicNode*)pChild, groupId);
-    if (isChild) {
-      return isChild;
-    }
-  }
-  return false;
-}
-
-static int32_t unionMountSubplan(SLogicSubplan* pParent, SNodeList* pChildren) {
-  SNode* pChild = NULL;
-  WHERE_EACH(pChild, pChildren) {
-    if (unionIsChildSubplan(pParent->pNode, ((SLogicSubplan*)pChild)->id.groupId)) {
-      int32_t code = nodesListMakeAppend(&pParent->pChildren, pChild);
-      if (TSDB_CODE_SUCCESS == code) {
-        REPLACE_NODE(NULL);
-        ERASE_NODE(pChildren);
-        continue;
-      } else {
-        return code;
-      }
-    }
-    WHERE_NEXT;
-  }
-  return TSDB_CODE_SUCCESS;
-}
-
-static SLogicSubplan* unionCreateSubplan(SSplitContext* pCxt, SLogicNode* pNode, ESubplanType subplanType) {
-  SLogicSubplan* pSubplan = (SLogicSubplan*)nodesMakeNode(QUERY_NODE_LOGIC_SUBPLAN);
-  if (NULL == pSubplan) {
-    return NULL;
-  }
-  pSubplan->id.queryId = pCxt->queryId;
-  pSubplan->id.groupId = pCxt->groupId;
-  pSubplan->subplanType = subplanType;
-  pSubplan->pNode = pNode;
-  pNode->pParent = NULL;
-  return pSubplan;
-}
-
 static int32_t unionSplitSubplan(SSplitContext* pCxt, SLogicSubplan* pUnionSubplan, SLogicNode* pSplitNode) {
   SNodeList* pSubplanChildren = pUnionSubplan->pChildren;
   pUnionSubplan->pChildren = NULL;
@@ -1040,11 +1039,11 @@ static int32_t unionSplitSubplan(SSplitContext* pCxt, SLogicSubplan* pUnionSubpl
 
   SNode* pChild = NULL;
   FOREACH(pChild, pSplitNode->pChildren) {
-    SLogicSubplan* pNewSubplan = unionCreateSubplan(pCxt, (SLogicNode*)pChild, pUnionSubplan->subplanType);
+    SLogicSubplan* pNewSubplan = splCreateSubplan(pCxt, (SLogicNode*)pChild, pUnionSubplan->subplanType);
     code = nodesListMakeStrictAppend(&pUnionSubplan->pChildren, (SNode*)pNewSubplan);
     if (TSDB_CODE_SUCCESS == code) {
       REPLACE_NODE(NULL);
-      code = unionMountSubplan(pNewSubplan, pSubplanChildren);
+      code = splMountSubplan(pNewSubplan, pSubplanChildren);
     }
     if (TSDB_CODE_SUCCESS != code) {
       break;
@@ -1219,14 +1218,24 @@ static int32_t insertSelectSplit(SSplitContext* pCxt, SLogicSubplan* pSubplan) {
     return TSDB_CODE_SUCCESS;
   }
 
-  int32_t code = splCreateExchangeNodeForSubplan(pCxt, info.pSubplan, info.pQueryRoot, info.pSubplan->subplanType);
+  SLogicSubplan* pNewSubplan = NULL;
+  SNodeList*     pSubplanChildren = info.pSubplan->pChildren;
+  ESubplanType   subplanType = info.pSubplan->subplanType;
+  int32_t        code = splCreateExchangeNodeForSubplan(pCxt, info.pSubplan, info.pQueryRoot, SUBPLAN_TYPE_MODIFY);
   if (TSDB_CODE_SUCCESS == code) {
-    code = nodesListMakeStrictAppend(&info.pSubplan->pChildren, (SNode*)splCreateScanSubplan(pCxt, info.pQueryRoot, 0));
+    pNewSubplan = splCreateSubplan(pCxt, info.pQueryRoot, subplanType);
+    if (NULL == pNewSubplan) {
+      code = TSDB_CODE_OUT_OF_MEMORY;
+    }
   }
   if (TSDB_CODE_SUCCESS == code) {
-    info.pSubplan->subplanType = SUBPLAN_TYPE_MODIFY;
+    code = nodesListMakeStrictAppend(&info.pSubplan->pChildren, (SNode*)pNewSubplan);
-    SPLIT_FLAG_SET_MASK(info.pSubplan->splitFlag, SPLIT_FLAG_INSERT_SPLIT);
   }
+  if (TSDB_CODE_SUCCESS == code) {
+    code = splMountSubplan(pNewSubplan, pSubplanChildren);
+  }
+
+  SPLIT_FLAG_SET_MASK(info.pSubplan->splitFlag, SPLIT_FLAG_INSERT_SPLIT);
   ++(pCxt->groupId);
   pCxt->split = true;
   return code;

source/libs/qworker/inc/qwInt.h

@@ -80,12 +80,19 @@ typedef struct SQWDebug {
 
 extern SQWDebug gQWDebug;
 
+typedef struct SQWMsgInfo {
+  int8_t taskType;
+  int8_t explain;
+  int8_t needFetch;
+} SQWMsgInfo;
+
 typedef struct SQWMsg {
   void          *node;
   int32_t        code;
   int32_t        msgType;
   char          *msg;
   int32_t        msgLen;
+  SQWMsgInfo     msgInfo;
   SRpcHandleInfo connInfo;
 } SQWMsg;
 
@@ -122,15 +129,18 @@ typedef struct SQWTaskCtx {
   int8_t   phase;
   int8_t   taskType;
   int8_t   explain;
+  int8_t   needFetch;
   int32_t  queryType;
   int32_t  fetchType;
   int32_t  execId;
 
+  bool    queryRsped;
   bool    queryFetched;
   bool    queryEnd;
   bool    queryContinue;
   bool    queryInQueue;
   int32_t rspCode;
+  int64_t affectedRows; // for insert ...select stmt
 
   SRpcHandleInfo ctrlConnInfo;
   SRpcHandleInfo dataConnInfo;
@@ -162,7 +172,7 @@ typedef struct SQWMsgStat {
   uint64_t queryProcessed;
   uint64_t cqueryProcessed;
   uint64_t fetchProcessed;
-  uint64_t fetchRspProcessed;
+  uint64_t rspProcessed;
   uint64_t cancelProcessed;
   uint64_t dropProcessed;
   uint64_t hbProcessed;
@@ -212,8 +222,8 @@ typedef struct SQWorkerMgmt {
 #define QW_STAT_GET(_item) atomic_load_64(&(_item))
 
 #define QW_GET_EVENT(ctx, event) atomic_load_8(&(ctx)->events[event])
-#define QW_IS_EVENT_RECEIVED(ctx, event)   (QW_GET_EVENT(ctx, event) == QW_EVENT_RECEIVED)
+#define QW_EVENT_RECEIVED(ctx, event)   (QW_GET_EVENT(ctx, event) == QW_EVENT_RECEIVED)
-#define QW_IS_EVENT_PROCESSED(ctx, event)  (QW_GET_EVENT(ctx, event) == QW_EVENT_PROCESSED)
+#define QW_EVENT_PROCESSED(ctx, event)  (QW_GET_EVENT(ctx, event) == QW_EVENT_PROCESSED)
 #define QW_SET_EVENT_RECEIVED(ctx, event)  atomic_store_8(&(ctx)->events[event], QW_EVENT_RECEIVED)
 #define QW_SET_EVENT_PROCESSED(ctx, event) atomic_store_8(&(ctx)->events[event], QW_EVENT_PROCESSED)
 
@@ -222,13 +232,8 @@ typedef struct SQWorkerMgmt {
 #define QW_SET_RSP_CODE(ctx, code)    atomic_store_32(&(ctx)->rspCode, code)
 #define QW_UPDATE_RSP_CODE(ctx, code) atomic_val_compare_exchange_32(&(ctx)->rspCode, 0, code)
 
-#define QW_IS_QUERY_RUNNING(ctx) (QW_GET_PHASE(ctx) == QW_PHASE_PRE_QUERY || QW_GET_PHASE(ctx) == QW_PHASE_PRE_CQUERY)
+#define QW_QUERY_RUNNING(ctx) (QW_GET_PHASE(ctx) == QW_PHASE_PRE_QUERY || QW_GET_PHASE(ctx) == QW_PHASE_PRE_CQUERY)
 
-#define QW_TASK_NOT_EXIST(code)     (TSDB_CODE_QRY_SCH_NOT_EXIST == (code) || TSDB_CODE_QRY_TASK_NOT_EXIST == (code))
-#define QW_TASK_ALREADY_EXIST(code) (TSDB_CODE_QRY_TASK_ALREADY_EXIST == (code))
-#define QW_TASK_READY(status)                                                                                      \
-  (status == JOB_TASK_STATUS_SUCC || status == JOB_TASK_STATUS_FAIL || status == JOB_TASK_STATUS_CANCELLED || \
-   status == JOB_TASK_STATUS_PART_SUCC)
 #define QW_SET_QTID(id, qId, tId, eId)                              \
   do {                                                              \
     *(uint64_t *)(id) = (qId);                                      \

source/libs/qworker/inc/qwMsg.h

@@ -25,7 +25,7 @@ extern "C" {
 
 int32_t qwAbortPrerocessQuery(QW_FPARAMS_DEF);
 int32_t qwPrerocessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg);
-int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, int8_t taskType, int8_t explain, const char* sql);
+int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, const char* sql);
 int32_t qwProcessCQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg);
 int32_t qwProcessReady(QW_FPARAMS_DEF, SQWMsg *qwMsg);
 int32_t qwProcessFetch(QW_FPARAMS_DEF, SQWMsg *qwMsg);
@@ -38,7 +38,7 @@ int32_t qwBuildAndSendCancelRsp(SRpcHandleInfo *pConn, int32_t code);
 int32_t qwBuildAndSendFetchRsp(int32_t rspType, SRpcHandleInfo *pConn, SRetrieveTableRsp *pRsp, int32_t dataLength, int32_t code);
 void    qwBuildFetchRsp(void *msg, SOutputData *input, int32_t len, bool qComplete);
 int32_t qwBuildAndSendCQueryMsg(QW_FPARAMS_DEF, SRpcHandleInfo *pConn);
-int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, STbVerInfo* tbInfo);
+int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, SQWTaskCtx *ctx);
 int32_t qwBuildAndSendExplainRsp(SRpcHandleInfo *pConn, SExplainExecInfo *execInfo, int32_t num);
 void    qwFreeFetchRsp(void *msg);
 int32_t qwMallocFetchRsp(int32_t length, SRetrieveTableRsp **rsp);

source/libs/qworker/src/qwMsg.c

@@ -43,13 +43,16 @@ void qwFreeFetchRsp(void *msg) {
   }
 }
 
-int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, STbVerInfo* tbInfo) {
+int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, SQWTaskCtx *ctx) {
+  STbVerInfo* tbInfo = ctx ? &ctx->tbInfo : NULL;
+  int64_t affectedRows = ctx ? ctx->affectedRows : 0;
   SQueryTableRsp *pRsp = (SQueryTableRsp *)rpcMallocCont(sizeof(SQueryTableRsp));
-  pRsp->code = code;
+  pRsp->code = htonl(code);
+  pRsp->affectedRows = htobe64(affectedRows);
   if (tbInfo) {
     strcpy(pRsp->tbFName, tbInfo->tbFName);
-    pRsp->sversion = tbInfo->sversion;
+    pRsp->sversion = htonl(tbInfo->sversion);
-    pRsp->tversion = tbInfo->tversion;
+    pRsp->tversion = htonl(tbInfo->tversion);
   }
 
   SRpcMsg rpcRsp = {
@@ -366,10 +369,14 @@ int32_t qWorkerProcessQueryMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int
   int32_t  eId = msg->execId;
 
   SQWMsg qwMsg = {.node = node, .msg = msg->msg + msg->sqlLen, .msgLen = msg->phyLen, .connInfo = pMsg->info, .msgType = pMsg->msgType};
+  qwMsg.msgInfo.explain = msg->explain;
+  qwMsg.msgInfo.taskType = msg->taskType;
+  qwMsg.msgInfo.needFetch = msg->needFetch;
+  
   char * sql = strndup(msg->msg, msg->sqlLen);
   QW_SCH_TASK_DLOG("processQuery start, node:%p, type:%s, handle:%p, sql:%s", node, TMSG_INFO(pMsg->msgType), pMsg->info.handle, sql);
 
-  QW_ERR_RET(qwProcessQuery(QW_FPARAMS(), &qwMsg, msg->taskType, msg->explain, sql));
+  QW_ERR_RET(qwProcessQuery(QW_FPARAMS(), &qwMsg, sql));
   QW_SCH_TASK_DLOG("processQuery end, node:%p", node);
 
   return TSDB_CODE_SUCCESS;
@@ -447,14 +454,14 @@ int32_t qWorkerProcessFetchMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int
   return TSDB_CODE_SUCCESS;
 }
 
-int32_t qWorkerProcessFetchRsp(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts) {
+int32_t qWorkerProcessRspMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int64_t ts) {
   SQWorker *      mgmt = (SQWorker *)qWorkerMgmt;
   if (mgmt) {
     qwUpdateTimeInQueue(mgmt, ts, FETCH_QUEUE);
-    QW_STAT_INC(mgmt->stat.msgStat.fetchRspProcessed, 1);
+    QW_STAT_INC(mgmt->stat.msgStat.rspProcessed, 1);
   }
 
-  qProcessFetchRsp(NULL, pMsg, NULL);
+  qProcessRspMsg(NULL, pMsg, NULL);
   pMsg->pCont = NULL;
   return TSDB_CODE_SUCCESS;
 }

source/libs/qworker/src/qworker.c

@@ -57,6 +57,10 @@ int32_t qwHandleTaskComplete(QW_FPARAMS_DEF, SQWTaskCtx *ctx) {
       connInfo.ahandle = NULL;
       QW_ERR_RET(qwBuildAndSendExplainRsp(&connInfo, execInfo, resNum));
     }
+
+    if (!ctx->needFetch) {
+      dsGetDataLength(ctx->sinkHandle, &ctx->affectedRows, NULL);
+    }
   }
 
   return TSDB_CODE_SUCCESS;
@@ -123,11 +127,11 @@ int32_t qwExecTask(QW_FPARAMS_DEF, SQWTaskCtx *ctx, bool *queryEnd) {
       break;
     }
 
-    if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_READY) && execNum >= QW_DEFAULT_SHORT_RUN_TIMES) {
+    if (ctx->needFetch && (!ctx->queryRsped) && execNum >= QW_DEFAULT_SHORT_RUN_TIMES) {
       break;
     }
 
-    if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
+    if (QW_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
       break;
     }
 
@@ -184,7 +188,7 @@ int32_t qwGenerateSchHbRsp(SQWorker *mgmt, SQWSchStatus *sch, SQWHbInfo *hbInfo)
 }
 
 int32_t qwGetQueryResFromSink(QW_FPARAMS_DEF, SQWTaskCtx *ctx, int32_t *dataLen, void **rspMsg, SOutputData *pOutput) {
-  int32_t            len = 0;
+  int64_t            len = 0;
   SRetrieveTableRsp *rsp = NULL;
   bool               queryEnd = false;
   int32_t            code = 0;
@@ -243,7 +247,7 @@ int32_t qwGetQueryResFromSink(QW_FPARAMS_DEF, SQWTaskCtx *ctx, int32_t *dataLen,
 }
 
 int32_t qwGetDeleteResFromSink(QW_FPARAMS_DEF, SQWTaskCtx *ctx, SDeleteRes *pRes) {
-  int32_t            len = 0;
+  int64_t            len = 0;
   bool               queryEnd = false;
   int32_t            code = 0;
   SOutputData        output = {0};
@@ -251,7 +255,7 @@ int32_t qwGetDeleteResFromSink(QW_FPARAMS_DEF, SQWTaskCtx *ctx, SDeleteRes *pRes
   dsGetDataLength(ctx->sinkHandle, &len, &queryEnd);
 
   if (len <= 0 || len != sizeof(SDeleterRes)) {
-    QW_TASK_ELOG("invalid length from dsGetDataLength, length:%d", len);
+    QW_TASK_ELOG("invalid length from dsGetDataLength, length:%" PRId64, len);
     QW_ERR_RET(TSDB_CODE_QRY_INVALID_INPUT);
   }
 
@@ -282,7 +286,6 @@ int32_t qwGetDeleteResFromSink(QW_FPARAMS_DEF, SQWTaskCtx *ctx, SDeleteRes *pRes
 int32_t qwHandlePrePhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *input, SQWPhaseOutput *output) {
   int32_t         code = 0;
   SQWTaskCtx     *ctx = NULL;
-  SRpcHandleInfo *cancelConnection = NULL;
 
   QW_TASK_DLOG("start to handle event at phase %s", qwPhaseStr(phase));
 
@@ -303,13 +306,13 @@ int32_t qwHandlePrePhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inpu
 
   switch (phase) {
     case QW_PHASE_PRE_QUERY: {
-      if (QW_IS_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
+      if (QW_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
         QW_TASK_ELOG("task already dropped at wrong phase %s", qwPhaseStr(phase));
         QW_ERR_JRET(TSDB_CODE_QRY_TASK_STATUS_ERROR);
         break;
       }
 
-      if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
+      if (QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
         QW_ERR_JRET(qwDropTask(QW_FPARAMS()));
 
         //qwBuildAndSendDropRsp(&ctx->ctrlConnInfo, code);
@@ -323,29 +326,29 @@ int32_t qwHandlePrePhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inpu
       break;
     }
     case QW_PHASE_PRE_FETCH: {
-      if (QW_IS_EVENT_PROCESSED(ctx, QW_EVENT_DROP) || QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
+      if (QW_EVENT_PROCESSED(ctx, QW_EVENT_DROP) || QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
         QW_TASK_WLOG("task dropping or already dropped, phase:%s", qwPhaseStr(phase));
         QW_ERR_JRET(TSDB_CODE_QRY_TASK_DROPPED);
       }
 
-      if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
+      if (QW_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
         QW_TASK_WLOG("last fetch still not processed, phase:%s", qwPhaseStr(phase));
         QW_ERR_JRET(TSDB_CODE_QRY_DUPLICATTED_OPERATION);
       }
 
-      if (!QW_IS_EVENT_PROCESSED(ctx, QW_EVENT_READY)) {
+      if (!ctx->queryRsped) {
         QW_TASK_ELOG("ready msg has not been processed, phase:%s", qwPhaseStr(phase));
         QW_ERR_JRET(TSDB_CODE_QRY_TASK_MSG_ERROR);
       }
       break;
     }
     case QW_PHASE_PRE_CQUERY: {
-      if (QW_IS_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
+      if (QW_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
         QW_TASK_WLOG("task already dropped, phase:%s", qwPhaseStr(phase));
         QW_ERR_JRET(TSDB_CODE_QRY_TASK_DROPPED);
       }
 
-      if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
+      if (QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
         QW_ERR_JRET(qwDropTask(QW_FPARAMS()));
 
         //qwBuildAndSendDropRsp(&ctx->ctrlConnInfo, code);
@@ -374,11 +377,6 @@ _return:
     qwReleaseTaskCtx(mgmt, ctx);
   }
 
-  if (cancelConnection) {
-    qwBuildAndSendCancelRsp(cancelConnection, code);
-    QW_TASK_DLOG("cancel rsp send, handle:%p, code:%x - %s", cancelConnection->handle, code, tstrerror(code));
-  }
-
   if (code != TSDB_CODE_SUCCESS) {
     QW_TASK_ELOG("end to handle event at phase %s, code:%s", qwPhaseStr(phase), tstrerror(code));
   } else {
@@ -400,7 +398,7 @@ int32_t qwHandlePostPhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inp
 
   QW_LOCK(QW_WRITE, &ctx->lock);
 
-  if (QW_IS_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
+  if (QW_EVENT_PROCESSED(ctx, QW_EVENT_DROP)) {
     QW_TASK_WLOG("task already dropped, phase:%s", qwPhaseStr(phase));
     QW_ERR_JRET(TSDB_CODE_QRY_TASK_DROPPED);
   }
@@ -409,10 +407,10 @@ int32_t qwHandlePostPhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inp
     connInfo = ctx->ctrlConnInfo;
     rspConnection = &connInfo;
 
-    QW_SET_EVENT_PROCESSED(ctx, QW_EVENT_READY);
+    ctx->queryRsped = true;
   }
 
-  if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
+  if (QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
     if (QW_PHASE_POST_FETCH == phase) {
       QW_TASK_WLOG("drop received at wrong phase %s", qwPhaseStr(phase));
       QW_ERR_JRET(TSDB_CODE_QRY_APP_ERROR);
@@ -440,7 +438,7 @@ _return:
   }
 
   if (rspConnection) {
-    qwBuildAndSendQueryRsp(input->msgType + 1, rspConnection, code, ctx ? &ctx->tbInfo : NULL);
+    qwBuildAndSendQueryRsp(input->msgType + 1, rspConnection, code, ctx);
     QW_TASK_DLOG("query msg rsped, handle:%p, code:%x - %s", rspConnection->handle, code, tstrerror(code));
   }
 
@@ -501,7 +499,7 @@ _return:
 }
 
 
-int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, int8_t taskType, int8_t explain, const char* sql) {
+int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, const char* sql) {
   int32_t        code = 0;
   bool           queryRsped = false;
   SSubplan      *plan = NULL;
@@ -514,8 +512,9 @@ int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, int8_t taskType, int8_t ex
 
   QW_ERR_JRET(qwGetTaskCtx(QW_FPARAMS(), &ctx));
 
-  ctx->taskType = taskType;
+  ctx->taskType = qwMsg->msgInfo.taskType;
-  ctx->explain = explain;
+  ctx->explain = qwMsg->msgInfo.explain;
+  ctx->needFetch = qwMsg->msgInfo.needFetch;
   ctx->queryType = qwMsg->msgType;
 
   QW_TASK_DLOGL("subplan json string, len:%d, %s", qwMsg->msgLen, qwMsg->msg);
@@ -585,7 +584,7 @@ int32_t qwProcessCQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
 
     QW_ERR_JRET(qwExecTask(QW_FPARAMS(), ctx, &queryEnd));
 
-    if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
+    if (QW_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
       SOutputData sOutput = {0};
       QW_ERR_JRET(qwGetQueryResFromSink(QW_FPARAMS(), ctx, &dataLen, &rsp, &sOutput));
 
@@ -622,7 +621,7 @@ int32_t qwProcessCQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
       break;
     }
 
-    if (code && QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
+    if (code && QW_EVENT_RECEIVED(ctx, QW_EVENT_FETCH)) {
       QW_SET_EVENT_PROCESSED(ctx, QW_EVENT_FETCH);
       qwFreeFetchRsp(rsp);
       rsp = NULL;
@@ -686,7 +685,7 @@ int32_t qwProcessFetch(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
     locked = true;
 
     // RC WARNING
-    if (QW_IS_QUERY_RUNNING(ctx)) {
+    if (QW_QUERY_RUNNING(ctx)) {
       atomic_store_8((int8_t *)&ctx->queryContinue, 1);
     } else if (0 == atomic_load_8((int8_t *)&ctx->queryInQueue)) {
       qwUpdateTaskStatus(QW_FPARAMS(), JOB_TASK_STATUS_EXEC);
@@ -714,7 +713,7 @@ _return:
 
   if (code || rsp) {
     qwBuildAndSendFetchRsp(qwMsg->msgType + 1, &qwMsg->connInfo, rsp, dataLen, code);
-    QW_TASK_DLOG("fetch rsp send, handle:%p, code:%x - %s, dataLen:%d", qwMsg->connInfo.handle, code, tstrerror(code),
+    QW_TASK_DLOG("%s send, handle:%p, code:%x - %s, dataLen:%d", TMSG_INFO(qwMsg->msgType + 1), qwMsg->connInfo.handle, code, tstrerror(code),
                  dataLen);
   }
 
@@ -733,12 +732,12 @@ int32_t qwProcessDrop(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
 
   locked = true;
 
-  if (QW_IS_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
+  if (QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
     QW_TASK_WLOG_E("task already dropping");
     QW_ERR_JRET(TSDB_CODE_QRY_DUPLICATTED_OPERATION);
   }
 
-  if (QW_IS_QUERY_RUNNING(ctx)) {
+  if (QW_QUERY_RUNNING(ctx)) {
     QW_ERR_JRET(qwKillTaskHandle(QW_FPARAMS(), ctx));
     qwUpdateTaskStatus(QW_FPARAMS(), JOB_TASK_STATUS_DROP);
   } else if (ctx->phase > 0) {

source/libs/qworker/test/qworkerTests.cpp

@@ -332,7 +332,7 @@ void qwtEndPut(DataSinkHandle handle, uint64_t useconds) {
   qwtTestSinkQueryEnd = true;
 }
 
-void qwtGetDataLength(DataSinkHandle handle, int32_t* pLen, bool* pQueryEnd) {
+void qwtGetDataLength(DataSinkHandle handle, int64_t* pLen, bool* pQueryEnd) {
   static int32_t in = 0;
 
   if (in > 0) {

source/libs/scheduler/inc/schInt.h

@@ -296,8 +296,8 @@ extern SSchedulerMgmt schMgmt;
 #define SCH_TASK_ID(_task) ((_task) ? (_task)->taskId : -1)
 #define SCH_TASK_EID(_task) ((_task) ? (_task)->execId : -1)
 
-#define SCH_IS_DATA_SRC_QRY_TASK(task) ((task)->plan->subplanType == SUBPLAN_TYPE_SCAN)
+#define SCH_IS_DATA_BIND_QRY_TASK(task) ((task)->plan->subplanType == SUBPLAN_TYPE_SCAN)
-#define SCH_IS_DATA_SRC_TASK(task) (((task)->plan->subplanType == SUBPLAN_TYPE_SCAN) || ((task)->plan->subplanType == SUBPLAN_TYPE_MODIFY))
+#define SCH_IS_DATA_BIND_TASK(task) (((task)->plan->subplanType == SUBPLAN_TYPE_SCAN) || ((task)->plan->subplanType == SUBPLAN_TYPE_MODIFY))
 #define SCH_IS_LEAF_TASK(_job, _task) (((_task)->level->level + 1) == (_job)->levelNum)
 
 #define SCH_SET_TASK_STATUS(task, st) atomic_store_8(&(task)->status, st)
@@ -317,8 +317,9 @@ extern SSchedulerMgmt schMgmt;
 
 #define SCH_SET_JOB_NEED_FLOW_CTRL(_job) (_job)->attr.needFlowCtrl = true
 #define SCH_JOB_NEED_FLOW_CTRL(_job) ((_job)->attr.needFlowCtrl)
-#define SCH_TASK_NEED_FLOW_CTRL(_job, _task) (SCH_IS_DATA_SRC_QRY_TASK(_task) && SCH_JOB_NEED_FLOW_CTRL(_job) && SCH_IS_LEVEL_UNFINISHED((_task)->level))
+#define SCH_TASK_NEED_FLOW_CTRL(_job, _task) (SCH_IS_DATA_BIND_QRY_TASK(_task) && SCH_JOB_NEED_FLOW_CTRL(_job) && SCH_IS_LEVEL_UNFINISHED((_task)->level))
-#define SCH_FETCH_TYPE(_pSrcTask) (SCH_IS_DATA_SRC_QRY_TASK(_pSrcTask) ? TDMT_SCH_FETCH : TDMT_SCH_MERGE_FETCH)
+#define SCH_FETCH_TYPE(_pSrcTask) (SCH_IS_DATA_BIND_QRY_TASK(_pSrcTask) ? TDMT_SCH_FETCH : TDMT_SCH_MERGE_FETCH)
+#define SCH_TASK_NEED_FETCH(_task) ((_task)->plan->subplanType != SUBPLAN_TYPE_MODIFY)
 
 #define SCH_SET_JOB_TYPE(_job, type) do { if ((type) != SUBPLAN_TYPE_MODIFY) { (_job)->attr.queryJob = true; } } while (0)
 #define SCH_IS_QUERY_JOB(_job) ((_job)->attr.queryJob) 

source/libs/scheduler/src/schJob.c

@@ -247,7 +247,7 @@ int32_t schBuildTaskRalation(SSchJob *pJob, SHashObj *planToTask) {
 
 
 int32_t schAppendJobDataSrc(SSchJob *pJob, SSchTask *pTask) {
-  if (!SCH_IS_DATA_SRC_QRY_TASK(pTask)) {
+  if (!SCH_IS_DATA_BIND_QRY_TASK(pTask)) {
     return TSDB_CODE_SUCCESS;
   }
 
@@ -879,7 +879,7 @@ int32_t schProcessOnCbBegin(SSchJob** job, SSchTask** task, uint64_t qId, int64_
   }
   
   if (schJobNeedToStop(pJob, &status)) {
-    SCH_TASK_ELOG("will not do further processing cause of job status %s", jobTaskStatusStr(status));
+    SCH_TASK_DLOG("will not do further processing cause of job status %s", jobTaskStatusStr(status));
     SCH_ERR_JRET(TSDB_CODE_SCH_IGNORE_ERROR);
   }
 

source/libs/scheduler/src/schRemote.c

@@ -21,44 +21,30 @@
 #include "tref.h"
 #include "trpc.h"
 
-int32_t schValidateReceivedMsgType(SSchJob *pJob, SSchTask *pTask, int32_t msgType) {
+int32_t schValidateRspMsgType(SSchJob *pJob, SSchTask *pTask, int32_t msgType) {
   int32_t lastMsgType = pTask->lastMsgType;
   int32_t taskStatus = SCH_GET_TASK_STATUS(pTask);
-  int32_t reqMsgType = msgType - 1;
+  int32_t reqMsgType = (msgType & 1U) ? msgType : (msgType - 1);
   switch (msgType) {
     case TDMT_SCH_LINK_BROKEN:
     case TDMT_SCH_EXPLAIN_RSP:
       return TSDB_CODE_SUCCESS;
-    case TDMT_SCH_MERGE_QUERY_RSP:
-    case TDMT_SCH_QUERY_RSP:  // query_rsp may be processed later than ready_rsp
-      if (lastMsgType != reqMsgType && -1 != lastMsgType) {
-        SCH_TASK_DLOG("rsp msg type mis-match, last sent msgType:%s, rspType:%s", TMSG_INFO(lastMsgType),
-                      TMSG_INFO(msgType));
-      }
-
-      if (taskStatus != JOB_TASK_STATUS_EXEC && taskStatus != JOB_TASK_STATUS_PART_SUCC) {
-        SCH_TASK_DLOG("rsp msg conflicted with task status, status:%s, rspType:%s", jobTaskStatusStr(taskStatus),
-                      TMSG_INFO(msgType));
-      }
-
-      // SCH_SET_TASK_LASTMSG_TYPE(pTask, -1);
-      return TSDB_CODE_SUCCESS;
     case TDMT_SCH_FETCH_RSP:
     case TDMT_SCH_MERGE_FETCH_RSP:
-      if (lastMsgType != reqMsgType && -1 != lastMsgType) {
+      if (lastMsgType != reqMsgType) {
         SCH_TASK_ELOG("rsp msg type mis-match, last sent msgType:%s, rspType:%s", TMSG_INFO(lastMsgType),
                       TMSG_INFO(msgType));
         SCH_ERR_RET(TSDB_CODE_SCH_STATUS_ERROR);
-      }
+      }    
-
+      if (taskStatus != JOB_TASK_STATUS_PART_SUCC) {
-      if (taskStatus != JOB_TASK_STATUS_EXEC && taskStatus != JOB_TASK_STATUS_PART_SUCC) {
         SCH_TASK_ELOG("rsp msg conflicted with task status, status:%s, rspType:%s", jobTaskStatusStr(taskStatus),
                       TMSG_INFO(msgType));
         SCH_ERR_RET(TSDB_CODE_SCH_STATUS_ERROR);
       }
 
-      // SCH_SET_TASK_LASTMSG_TYPE(pTask, -1);
       return TSDB_CODE_SUCCESS;
+    case TDMT_SCH_MERGE_QUERY_RSP:
+    case TDMT_SCH_QUERY_RSP:
     case TDMT_VND_CREATE_TABLE_RSP:
     case TDMT_VND_DROP_TABLE_RSP:
     case TDMT_VND_ALTER_TABLE_RSP:
@@ -77,14 +63,12 @@ int32_t schValidateReceivedMsgType(SSchJob *pJob, SSchTask *pTask, int32_t msgTy
     SCH_ERR_RET(TSDB_CODE_SCH_STATUS_ERROR);
   }
 
-  if (taskStatus != JOB_TASK_STATUS_EXEC && taskStatus != JOB_TASK_STATUS_PART_SUCC) {
+  if (taskStatus != JOB_TASK_STATUS_EXEC) {
     SCH_TASK_ELOG("rsp msg conflicted with task status, status:%s, rspType:%s", jobTaskStatusStr(taskStatus),
                   TMSG_INFO(msgType));
     SCH_ERR_RET(TSDB_CODE_SCH_STATUS_ERROR);
   }
 
-  // SCH_SET_TASK_LASTMSG_TYPE(pTask, -1);
-
   return TSDB_CODE_SUCCESS;
 }
 
@@ -98,7 +82,7 @@ int32_t schHandleResponseMsg(SSchJob *pJob, SSchTask *pTask, int32_t execId, SDa
   bool dropExecNode = (msgType == TDMT_SCH_LINK_BROKEN || SCH_NETWORK_ERR(rspCode));
   SCH_ERR_JRET(schUpdateTaskHandle(pJob, pTask, dropExecNode, pMsg->handle, execId));
 
-  SCH_ERR_JRET(schValidateReceivedMsgType(pJob, pTask, msgType));
+  SCH_ERR_JRET(schValidateRspMsgType(pJob, pTask, msgType));
 
   int32_t reqType = IsReq(pMsg) ? pMsg->msgType : (pMsg->msgType - 1);
   if (SCH_NEED_REDIRECT(reqType, rspCode, pMsg->len)) {
@@ -259,18 +243,25 @@ int32_t schHandleResponseMsg(SSchJob *pJob, SSchTask *pTask, int32_t execId, SDa
     }
     case TDMT_SCH_QUERY_RSP:
     case TDMT_SCH_MERGE_QUERY_RSP: {
-      SQueryTableRsp *rsp = (SQueryTableRsp *)msg;
-
       SCH_ERR_JRET(rspCode);
       if (NULL == msg) {
         SCH_ERR_JRET(TSDB_CODE_QRY_INVALID_INPUT);
       }
+
+      SQueryTableRsp *rsp = (SQueryTableRsp *)msg;
+      rsp->code = ntohl(rsp->code);
+      rsp->sversion = ntohl(rsp->sversion);
+      rsp->tversion = ntohl(rsp->tversion);
+      rsp->affectedRows = be64toh(rsp->affectedRows);
+      
       SCH_ERR_JRET(rsp->code);
 
       SCH_ERR_JRET(schSaveJobQueryRes(pJob, rsp));
 
-      taosMemoryFreeClear(msg);
+      atomic_add_fetch_32(&pJob->resNumOfRows, rsp->affectedRows);
 
+      taosMemoryFreeClear(msg);              
+      
       SCH_ERR_RET(schProcessOnTaskSuccess(pJob, pTask));
 
       break;
@@ -1010,6 +1001,7 @@ int32_t schBuildAndSendMsg(SSchJob *pJob, SSchTask *pTask, SQueryNodeAddr *addr,
       pMsg->execId = htonl(pTask->execId);
       pMsg->taskType = TASK_TYPE_TEMP;
       pMsg->explain = SCH_IS_EXPLAIN_JOB(pJob);
+      pMsg->needFetch = SCH_TASK_NEED_FETCH(pTask);
       pMsg->phyLen = htonl(pTask->msgLen);
       pMsg->sqlLen = htonl(len);
 

source/libs/scheduler/src/schTask.c

@@ -276,7 +276,7 @@ int32_t schProcessOnTaskSuccess(SSchJob *pJob, SSchTask *pTask) {
 }
 
 int32_t schRescheduleTask(SSchJob *pJob, SSchTask *pTask) {
-  if (SCH_IS_DATA_SRC_QRY_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     return TSDB_CODE_SUCCESS;
   }
 
@@ -313,7 +313,7 @@ int32_t schDoTaskRedirect(SSchJob *pJob, SSchTask *pTask, SDataBuf* pData, int32
   pTask->lastMsgType = 0;
   memset(&pTask->succeedAddr, 0, sizeof(pTask->succeedAddr));
 
-  if (SCH_IS_DATA_SRC_QRY_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     if (pData) {
       SCH_ERR_JRET(schUpdateTaskCandidateAddr(pJob, pTask, pData->pEpSet));
     }
@@ -358,7 +358,7 @@ _return:
 int32_t schHandleRedirect(SSchJob *pJob, SSchTask *pTask, SDataBuf* pData, int32_t rspCode) {
   int32_t code = 0;
 
-  if (SCH_IS_DATA_SRC_QRY_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     if (NULL == pData->pEpSet) {
       SCH_TASK_ELOG("no epset updated while got error %s", tstrerror(rspCode));
       SCH_ERR_JRET(rspCode);
@@ -492,7 +492,7 @@ int32_t schTaskCheckSetRetry(SSchJob *pJob, SSchTask *pTask, int32_t errCode, bo
     return TSDB_CODE_SUCCESS;
   }
 
-  if (SCH_IS_DATA_SRC_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     if ((pTask->execId + 1) >= SCH_TASK_NUM_OF_EPS(&pTask->plan->execNode)) {
       *needRetry = false;
       SCH_TASK_DLOG("task no more retry since all ep tried, execId:%d, epNum:%d", pTask->execId,
@@ -528,7 +528,7 @@ int32_t schHandleTaskRetry(SSchJob *pJob, SSchTask *pTask) {
 
   schDeregisterTaskHb(pJob, pTask);
 
-  if (SCH_IS_DATA_SRC_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     SCH_SWITCH_EPSET(&pTask->plan->execNode);
   } else {
     int32_t candidateNum = taosArrayGetSize(pTask->candidateAddrs);  
@@ -596,7 +596,7 @@ int32_t schSetTaskCandidateAddrs(SSchJob *pJob, SSchTask *pTask) {
     return TSDB_CODE_SUCCESS;
   }
 
-  if (SCH_IS_DATA_SRC_QRY_TASK(pTask)) {
+  if (SCH_IS_DATA_BIND_TASK(pTask)) {
     SCH_TASK_ELOG("no execNode specifed for data src task, numOfEps:%d", pTask->plan->execNode.epSet.numOfEps);
     SCH_ERR_RET(TSDB_CODE_QRY_APP_ERROR);
   }

source/libs/stream/inc/streamInc.h

@@ -17,6 +17,7 @@
 #define _STREAM_INC_H_
 
 #include "executor.h"
+#include "tref.h"
 #include "tstream.h"
 
 #ifdef __cplusplus
@@ -24,8 +25,9 @@ extern "C" {
 #endif
 
 typedef struct {
-  int8_t inited;
+  int8_t  inited;
-  void*  timer;
+  int32_t refPool;
+  void*   timer;
 } SStreamGlobalEnv;
 
 static SStreamGlobalEnv streamEnv;

source/libs/stream/src/stream.c

@@ -76,9 +76,6 @@ void streamTriggerByTimer(void* param, void* tmrId) {
 
 int32_t streamSetupTrigger(SStreamTask* pTask) {
   if (pTask->triggerParam != 0) {
-    if (streamInit() < 0) {
-      return -1;
-    }
     pTask->timer = taosTmrStart(streamTriggerByTimer, (int32_t)pTask->triggerParam, pTask, streamEnv.timer);
     pTask->triggerStatus = TASK_TRIGGER_STATUS__IN_ACTIVE;
   }

source/libs/sync/inc/syncInt.h

@@ -67,7 +67,6 @@ typedef struct SSyncNode {
   char        path[TSDB_FILENAME_LEN];
   char        raftStorePath[TSDB_FILENAME_LEN * 2];
   char        configPath[TSDB_FILENAME_LEN * 2];
-  int32_t     batchSize;
 
   // sync io
   SWal*         pWal;

source/libs/sync/inc/syncOnMessage.h

@@ -1,72 +0,0 @@
-/*
- * Copyright (c) 2019 TAOS Data, Inc. <jhtao@taosdata.com>
- *
- * This program is free software: you can use, redistribute, and/or modify
- * it under the terms of the GNU Affero General Public License, version 3
- * or later ("AGPL"), as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _TD_LIBS_SYNC_ON_MESSAGE_H
-#define _TD_LIBS_SYNC_ON_MESSAGE_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include "taosdef.h"
-
-// TLA+ Spec
-// Receive(m) ==
-//     LET i == m.mdest
-//         j == m.msource
-//     IN \* Any RPC with a newer term causes the recipient to advance
-//        \* its term first. Responses with stale terms are ignored.
-//        \/ UpdateTerm(i, j, m)
-//        \/ /\ m.mtype = RequestVoteRequest
-//           /\ HandleRequestVoteRequest(i, j, m)
-//        \/ /\ m.mtype = RequestVoteResponse
-//           /\ \/ DropStaleResponse(i, j, m)
-//              \/ HandleRequestVoteResponse(i, j, m)
-//        \/ /\ m.mtype = AppendEntriesRequest
-//           /\ HandleAppendEntriesRequest(i, j, m)
-//        \/ /\ m.mtype = AppendEntriesResponse
-//           /\ \/ DropStaleResponse(i, j, m)
-//              \/ HandleAppendEntriesResponse(i, j, m)
-
-// DuplicateMessage(m) ==
-//     /\ Send(m)
-//     /\ UNCHANGED <<serverVars, candidateVars, leaderVars, logVars>>
-
-// DropMessage(m) ==
-//     /\ Discard(m)
-//     /\ UNCHANGED <<serverVars, candidateVars, leaderVars, logVars>>
-
-// Next == /\ \/ \E i \in Server : Restart(i)
-//            \/ \E i \in Server : Timeout(i)
-//            \/ \E i,j \in Server : RequestVote(i, j)
-//            \/ \E i \in Server : BecomeLeader(i)
-//            \/ \E i \in Server, v \in Value : ClientRequest(i, v)
-//            \/ \E i \in Server : AdvanceCommitIndex(i)
-//            \/ \E i,j \in Server : AppendEntries(i, j)
-//            \/ \E m \in DOMAIN messages : Receive(m)
-//            \/ \E m \in DOMAIN messages : DuplicateMessage(m)
-//            \/ \E m \in DOMAIN messages : DropMessage(m)
-//            \* History variable that tracks every log ever:
-//         /\ allLogs' = allLogs \cup {log[i] : i \in Server}
-//
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif /*_TD_LIBS_SYNC_ON_MESSAGE_H*/

source/libs/sync/inc/syncRaftLog.h

@@ -32,8 +32,8 @@ typedef struct SSyncLogStoreData {
   SSyncNode* pSyncNode;
   SWal*      pWal;
 
-  TdThreadMutex   mutex;
+  TdThreadMutex mutex;
-  SWalReadHandle* pWalHandle;
+  SWalReader*   pWalHandle;
 
   // SyncIndex       beginIndex;  // valid begin index, default 0, may be set beginIndex > 0
 } SSyncLogStoreData;

source/libs/sync/src/syncAppendEntries.c

@@ -162,6 +162,17 @@ int32_t syncNodeOnAppendEntriesCb(SSyncNode* ths, SyncAppendEntries* pMsg) {
     pReply->success = false;
     pReply->matchIndex = SYNC_INDEX_INVALID;
 
+    // msg event log
+    do {
+      char     host[128];
+      uint16_t port;
+      syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+      sDebug(
+          "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+          "match-index:%ld}",
+          ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+    } while (0);
+
     SRpcMsg rpcMsg;
     syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
     syncNodeSendMsgById(&pReply->destId, ths, &rpcMsg);
@@ -334,270 +345,16 @@ int32_t syncNodeOnAppendEntriesCb(SSyncNode* ths, SyncAppendEntries* pMsg) {
       pReply->matchIndex = pMsg->prevLogIndex;
     }
 
-    SRpcMsg rpcMsg;
+    // msg event log
-    syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
+    do {
-    syncNodeSendMsgById(&pReply->destId, ths, &rpcMsg);
+      char     host[128];
-    syncAppendEntriesReplyDestroy(pReply);
+      uint16_t port;
-
+      syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
-    // maybe update commit index from leader
+      sDebug(
-    if (pMsg->commitIndex > ths->commitIndex) {
+          "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
-      // has commit entry in local
+          "match-index:%ld}",
-      if (pMsg->commitIndex <= ths->pLogStore->getLastIndex(ths->pLogStore)) {
+          ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
-        SyncIndex beginIndex = ths->commitIndex + 1;
+    } while (0);
-        SyncIndex endIndex = pMsg->commitIndex;
-
-        // update commit index
-        ths->commitIndex = pMsg->commitIndex;
-
-        // call back Wal
-        ths->pLogStore->updateCommitIndex(ths->pLogStore, ths->commitIndex);
-
-        int32_t code = syncNodeCommit(ths, beginIndex, endIndex, ths->state);
-        ASSERT(code == 0);
-      }
-    }
-  }
-
-  return ret;
-}
-
-#if 0
-
-int32_t syncNodeOnAppendEntriesCb(SSyncNode* ths, SyncAppendEntries* pMsg) {
-  int32_t ret = 0;
-
-  char logBuf[128] = {0};
-  snprintf(logBuf, sizeof(logBuf), "==syncNodeOnAppendEntriesCb== term:%lu", ths->pRaftStore->currentTerm);
-  syncAppendEntriesLog2(logBuf, pMsg);
-
-  if (pMsg->term > ths->pRaftStore->currentTerm) {
-    syncNodeUpdateTerm(ths, pMsg->term);
-  }
-  ASSERT(pMsg->term <= ths->pRaftStore->currentTerm);
-
-  // reset elect timer
-  if (pMsg->term == ths->pRaftStore->currentTerm) {
-    ths->leaderCache = pMsg->srcId;
-    syncNodeResetElectTimer(ths);
-  }
-  ASSERT(pMsg->dataLen >= 0);
-
-  SyncTerm localPreLogTerm = 0;
-  if (pMsg->prevLogIndex >= SYNC_INDEX_BEGIN && pMsg->prevLogIndex <= ths->pLogStore->getLastIndex(ths->pLogStore)) {
-    SSyncRaftEntry* pEntry = ths->pLogStore->getEntry(ths->pLogStore, pMsg->prevLogIndex);
-    if (pEntry == NULL) {
-      char logBuf[128];
-      snprintf(logBuf, sizeof(logBuf), "getEntry error, index:%ld, since %s", pMsg->prevLogIndex, terrstr());
-      syncNodeErrorLog(ths, logBuf);
-      return -1;
-    }
-
-    localPreLogTerm = pEntry->term;
-    syncEntryDestory(pEntry);
-  }
-
-  bool logOK =
-      (pMsg->prevLogIndex == SYNC_INDEX_INVALID) ||
-      ((pMsg->prevLogIndex >= SYNC_INDEX_BEGIN) &&
-       (pMsg->prevLogIndex <= ths->pLogStore->getLastIndex(ths->pLogStore)) && (pMsg->prevLogTerm == localPreLogTerm));
-
-  // reject request
-  if ((pMsg->term < ths->pRaftStore->currentTerm) ||
-      ((pMsg->term == ths->pRaftStore->currentTerm) && (ths->state == TAOS_SYNC_STATE_FOLLOWER) && !logOK)) {
-    sTrace(
-        "syncNodeOnAppendEntriesCb --> reject, pMsg->term:%lu, ths->pRaftStore->currentTerm:%lu, ths->state:%d, "
-        "logOK:%d",
-        pMsg->term, ths->pRaftStore->currentTerm, ths->state, logOK);
-
-    SyncAppendEntriesReply* pReply = syncAppendEntriesReplyBuild(ths->vgId);
-    pReply->srcId = ths->myRaftId;
-    pReply->destId = pMsg->srcId;
-    pReply->term = ths->pRaftStore->currentTerm;
-    pReply->success = false;
-    pReply->matchIndex = SYNC_INDEX_INVALID;
-
-    SRpcMsg rpcMsg;
-    syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
-    syncNodeSendMsgById(&pReply->destId, ths, &rpcMsg);
-    syncAppendEntriesReplyDestroy(pReply);
-
-    return ret;
-  }
-
-  // return to follower state
-  if (pMsg->term == ths->pRaftStore->currentTerm && ths->state == TAOS_SYNC_STATE_CANDIDATE) {
-    sTrace(
-        "syncNodeOnAppendEntriesCb --> return to follower, pMsg->term:%lu, ths->pRaftStore->currentTerm:%lu, "
-        "ths->state:%d, logOK:%d",
-        pMsg->term, ths->pRaftStore->currentTerm, ths->state, logOK);
-
-    syncNodeBecomeFollower(ths, "from candidate by append entries");
-
-    // ret or reply?
-    return ret;
-  }
-
-  // accept request
-  if (pMsg->term == ths->pRaftStore->currentTerm && ths->state == TAOS_SYNC_STATE_FOLLOWER && logOK) {
-    // preIndex = -1, or has preIndex entry in local log
-    ASSERT(pMsg->prevLogIndex <= ths->pLogStore->getLastIndex(ths->pLogStore));
-
-    // has extra entries (> preIndex) in local log
-    bool hasExtraEntries = pMsg->prevLogIndex < ths->pLogStore->getLastIndex(ths->pLogStore);
-
-    // has entries in SyncAppendEntries msg
-    bool hasAppendEntries = pMsg->dataLen > 0;
-
-    sTrace(
-        "syncNodeOnAppendEntriesCb --> accept, pMsg->term:%lu, ths->pRaftStore->currentTerm:%lu, ths->state:%d, "
-        "logOK:%d, hasExtraEntries:%d, hasAppendEntries:%d",
-        pMsg->term, ths->pRaftStore->currentTerm, ths->state, logOK, hasExtraEntries, hasAppendEntries);
-
-    if (hasExtraEntries && hasAppendEntries) {
-      // not conflict by default
-      bool conflict = false;
-
-      SyncIndex       extraIndex = pMsg->prevLogIndex + 1;
-      SSyncRaftEntry* pExtraEntry = ths->pLogStore->getEntry(ths->pLogStore, extraIndex);
-      if (pExtraEntry == NULL) {
-        char logBuf[128];
-        snprintf(logBuf, sizeof(logBuf), "getEntry error2, index:%ld, since %s", extraIndex, terrstr());
-        syncNodeErrorLog(ths, logBuf);
-        return -1;
-      }
-
-      SSyncRaftEntry* pAppendEntry = syncEntryDeserialize(pMsg->data, pMsg->dataLen);
-      if (pAppendEntry == NULL) {
-        syncNodeErrorLog(ths, "syncEntryDeserialize pAppendEntry error");
-        return -1;
-      }
-
-      // log not match, conflict
-      ASSERT(extraIndex == pAppendEntry->index);
-      if (pExtraEntry->term != pAppendEntry->term) {
-        conflict = true;
-      }
-
-      if (conflict) {
-        // roll back
-        SyncIndex delBegin = ths->pLogStore->getLastIndex(ths->pLogStore);
-        SyncIndex delEnd = extraIndex;
-
-        sTrace("syncNodeOnAppendEntriesCb --> conflict:%d, delBegin:%ld, delEnd:%ld", conflict, delBegin, delEnd);
-
-        // notice! reverse roll back!
-        for (SyncIndex index = delEnd; index >= delBegin; --index) {
-          if (ths->pFsm->FpRollBackCb != NULL) {
-            SSyncRaftEntry* pRollBackEntry = ths->pLogStore->getEntry(ths->pLogStore, index);
-            if (pRollBackEntry == NULL) {
-              char logBuf[128];
-              snprintf(logBuf, sizeof(logBuf), "getEntry error3, index:%ld, since %s", index, terrstr());
-              syncNodeErrorLog(ths, logBuf);
-              return -1;
-            }
-
-            // if (pRollBackEntry->msgType != TDMT_SYNC_NOOP) {
-            if (syncUtilUserRollback(pRollBackEntry->msgType)) {
-              SRpcMsg rpcMsg;
-              syncEntry2OriginalRpc(pRollBackEntry, &rpcMsg);
-
-              SFsmCbMeta cbMeta = {0};
-              cbMeta.index = pRollBackEntry->index;
-              cbMeta.lastConfigIndex = syncNodeGetSnapshotConfigIndex(ths, cbMeta.index);
-              cbMeta.isWeak = pRollBackEntry->isWeak;
-              cbMeta.code = 0;
-              cbMeta.state = ths->state;
-              cbMeta.seqNum = pRollBackEntry->seqNum;
-              ths->pFsm->FpRollBackCb(ths->pFsm, &rpcMsg, cbMeta);
-              rpcFreeCont(rpcMsg.pCont);
-            }
-
-            syncEntryDestory(pRollBackEntry);
-          }
-        }
-
-        // delete confict entries
-        ths->pLogStore->truncate(ths->pLogStore, extraIndex);
-
-        // append new entries
-        ths->pLogStore->appendEntry(ths->pLogStore, pAppendEntry);
-
-        // pre commit
-        SRpcMsg rpcMsg;
-        syncEntry2OriginalRpc(pAppendEntry, &rpcMsg);
-        if (ths->pFsm != NULL) {
-          // if (ths->pFsm->FpPreCommitCb != NULL && pAppendEntry->originalRpcType != TDMT_SYNC_NOOP) {
-          if (ths->pFsm->FpPreCommitCb != NULL && syncUtilUserPreCommit(pAppendEntry->originalRpcType)) {
-            SFsmCbMeta cbMeta = {0};
-            cbMeta.index = pAppendEntry->index;
-            cbMeta.lastConfigIndex = syncNodeGetSnapshotConfigIndex(ths, cbMeta.index);
-            cbMeta.isWeak = pAppendEntry->isWeak;
-            cbMeta.code = 2;
-            cbMeta.state = ths->state;
-            cbMeta.seqNum = pAppendEntry->seqNum;
-            ths->pFsm->FpPreCommitCb(ths->pFsm, &rpcMsg, cbMeta);
-          }
-        }
-        rpcFreeCont(rpcMsg.pCont);
-      }
-
-      // free memory
-      syncEntryDestory(pExtraEntry);
-      syncEntryDestory(pAppendEntry);
-
-    } else if (hasExtraEntries && !hasAppendEntries) {
-      // do nothing
-
-    } else if (!hasExtraEntries && hasAppendEntries) {
-      SSyncRaftEntry* pAppendEntry = syncEntryDeserialize(pMsg->data, pMsg->dataLen);
-      if (pAppendEntry == NULL) {
-        syncNodeErrorLog(ths, "syncEntryDeserialize pAppendEntry2 error");
-        return -1;
-      }
-
-      // append new entries
-      ths->pLogStore->appendEntry(ths->pLogStore, pAppendEntry);
-
-      // pre commit
-      SRpcMsg rpcMsg;
-      syncEntry2OriginalRpc(pAppendEntry, &rpcMsg);
-      if (ths->pFsm != NULL) {
-        // if (ths->pFsm->FpPreCommitCb != NULL && pAppendEntry->originalRpcType != TDMT_SYNC_NOOP) {
-        if (ths->pFsm->FpPreCommitCb != NULL && syncUtilUserPreCommit(pAppendEntry->originalRpcType)) {
-          SFsmCbMeta cbMeta = {0};
-          cbMeta.index = pAppendEntry->index;
-          cbMeta.lastConfigIndex = syncNodeGetSnapshotConfigIndex(ths, cbMeta.index);
-          cbMeta.isWeak = pAppendEntry->isWeak;
-          cbMeta.code = 3;
-          cbMeta.state = ths->state;
-          cbMeta.seqNum = pAppendEntry->seqNum;
-          ths->pFsm->FpPreCommitCb(ths->pFsm, &rpcMsg, cbMeta);
-        }
-      }
-      rpcFreeCont(rpcMsg.pCont);
-
-      // free memory
-      syncEntryDestory(pAppendEntry);
-
-    } else if (!hasExtraEntries && !hasAppendEntries) {
-      // do nothing
-
-    } else {
-      syncNodeLog3("", ths);
-      ASSERT(0);
-    }
-
-    SyncAppendEntriesReply* pReply = syncAppendEntriesReplyBuild(ths->vgId);
-    pReply->srcId = ths->myRaftId;
-    pReply->destId = pMsg->srcId;
-    pReply->term = ths->pRaftStore->currentTerm;
-    pReply->success = true;
-
-    if (hasAppendEntries) {
-      pReply->matchIndex = pMsg->prevLogIndex + 1;
-    } else {
-      pReply->matchIndex = pMsg->prevLogIndex;
-    }
 
     SRpcMsg rpcMsg;
     syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -626,8 +383,6 @@ int32_t syncNodeOnAppendEntriesCb(SSyncNode* ths, SyncAppendEntries* pMsg) {
   return ret;
 }
 
-#endif
-
 static int32_t syncNodeMakeLogSame(SSyncNode* ths, SyncAppendEntries* pMsg) {
   int32_t code;
 
@@ -842,8 +597,8 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
       do {
         char logBuf[128];
         snprintf(logBuf, sizeof(logBuf),
-                 "recv sync-append-entries-batch, fake match2, pre-index:%ld, pre-term:%lu, datalen:%d",
+                 "recv sync-append-entries-batch, fake match2, {pre-index:%ld, pre-term:%lu, datalen:%d, datacount:%d}",
-                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen);
+                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen, pMsg->dataCount);
         syncNodeEventLog(ths, logBuf);
       } while (0);
 
@@ -876,7 +631,7 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
           code = syncNodePreCommit(ths, pAppendEntry);
           ASSERT(code == 0);
 
-          syncEntryDestory(pAppendEntry);
+          // syncEntryDestory(pAppendEntry);
         }
 
         // fsync once
@@ -897,6 +652,17 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
       pReply->success = true;
       pReply->matchIndex = matchIndex;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -931,8 +697,8 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
       do {
         char logBuf[128];
         snprintf(logBuf, sizeof(logBuf),
-                 "recv sync-append-entries-batch, not match, pre-index:%ld, pre-term:%lu, datalen:%d",
+                 "recv sync-append-entries-batch, not match, {pre-index:%ld, pre-term:%lu, datalen:%d, datacount:%d}",
-                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen);
+                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen, pMsg->dataCount);
         syncNodeEventLog(ths, logBuf);
       } while (0);
 
@@ -945,6 +711,17 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
       pReply->success = false;
       pReply->matchIndex = SYNC_INDEX_INVALID;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -976,8 +753,9 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
 
       do {
         char logBuf[128];
-        snprintf(logBuf, sizeof(logBuf), "recv sync-append-entries, match, pre-index:%ld, pre-term:%lu, datalen:%d",
+        snprintf(logBuf, sizeof(logBuf),
-                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen);
+                 "recv sync-append-entries-batch, match, {pre-index:%ld, pre-term:%lu, datalen:%d, datacount:%d}",
+                 pMsg->prevLogIndex, pMsg->prevLogTerm, pMsg->dataLen, pMsg->dataCount);
         syncNodeEventLog(ths, logBuf);
       } while (0);
 
@@ -999,7 +777,7 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
           code = syncNodePreCommit(ths, pAppendEntry);
           ASSERT(code == 0);
 
-          syncEntryDestory(pAppendEntry);
+          // syncEntryDestory(pAppendEntry);
         }
 
         // fsync once
@@ -1017,6 +795,17 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
       pReply->success = true;
       pReply->matchIndex = hasAppendEntries ? pMsg->prevLogIndex + pMsg->dataCount : pMsg->prevLogIndex;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -1226,6 +1015,17 @@ int32_t syncNodeOnAppendEntriesSnapshotCb(SSyncNode* ths, SyncAppendEntries* pMs
       pReply->success = true;
       pReply->matchIndex = matchIndex;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -1271,6 +1071,17 @@ int32_t syncNodeOnAppendEntriesSnapshotCb(SSyncNode* ths, SyncAppendEntries* pMs
       pReply->success = false;
       pReply->matchIndex = SYNC_INDEX_INVALID;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);
@@ -1336,6 +1147,17 @@ int32_t syncNodeOnAppendEntriesSnapshotCb(SSyncNode* ths, SyncAppendEntries* pMs
       pReply->success = true;
       pReply->matchIndex = hasAppendEntries ? pMsg->prevLogIndex + 1 : pMsg->prevLogIndex;
 
+      // msg event log
+      do {
+        char     host[128];
+        uint16_t port;
+        syncUtilU642Addr(pReply->destId.addr, host, sizeof(host), &port);
+        sDebug(
+            "vgId:%d, send sync-append-entries-reply to %s:%d, {term:%lu, pterm:%lu, success:%d, "
+            "match-index:%ld}",
+            ths->vgId, host, port, pReply->term, pReply->privateTerm, pReply->success, pReply->matchIndex);
+      } while (0);
+
       // send response
       SRpcMsg rpcMsg;
       syncAppendEntriesReply2RpcMsg(pReply, &rpcMsg);

source/libs/sync/src/syncAppendEntriesReply.c

@@ -174,8 +174,12 @@ int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntrie
     SyncIndex newNextIndex = pMsg->matchIndex + 1;
     SyncIndex newMatchIndex = pMsg->matchIndex;
 
-    if (ths->pLogStore->syncLogExist(ths->pLogStore, newNextIndex) &&
+    bool needStartSnapshot = false;
-        ths->pLogStore->syncLogExist(ths->pLogStore, newNextIndex - 1)) {
+    if (newMatchIndex >= SYNC_INDEX_BEGIN && !ths->pLogStore->syncLogExist(ths->pLogStore, newMatchIndex)) {
+      needStartSnapshot = true;
+    }
+
+    if (!needStartSnapshot) {
       // update next-index, match-index
       syncIndexMgrSetIndex(ths->pNextIndex, &(pMsg->srcId), newNextIndex);
       syncIndexMgrSetIndex(ths->pMatchIndex, &(pMsg->srcId), newMatchIndex);
@@ -197,15 +201,36 @@ int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntrie
       syncIndexMgrSetIndex(ths->pMatchIndex, &(pMsg->srcId), newMatchIndex);
     }
 
+    // event log, update next-index
+    do {
+      char    host[64];
+      int16_t port;
+      syncUtilU642Addr(pMsg->srcId.addr, host, sizeof(host), &port);
+
+      char logBuf[256];
+      snprintf(logBuf, sizeof(logBuf), "reset next-index:%ld, match-index:%ld for %s:%d", newNextIndex, newMatchIndex,
+               host, port);
+      syncNodeEventLog(ths, logBuf);
+
+    } while (0);
+
   } else {
     SyncIndex nextIndex = syncIndexMgrGetIndex(ths->pNextIndex, &(pMsg->srcId));
 
     if (nextIndex > SYNC_INDEX_BEGIN) {
       --nextIndex;
 
-      if (ths->pLogStore->syncLogExist(ths->pLogStore, nextIndex) &&
+      bool needStartSnapshot = false;
-          ths->pLogStore->syncLogExist(ths->pLogStore, nextIndex - 1)) {
+      if (nextIndex >= SYNC_INDEX_BEGIN && !ths->pLogStore->syncLogExist(ths->pLogStore, nextIndex)) {
+        needStartSnapshot = true;
+      }
+      if (nextIndex - 1 >= SYNC_INDEX_BEGIN && !ths->pLogStore->syncLogExist(ths->pLogStore, nextIndex - 1)) {
+        needStartSnapshot = true;
+      }
+
+      if (!needStartSnapshot) {
         // do nothing
+
       } else {
         SSyncRaftEntry* pEntry;
         int32_t         code = ths->pLogStore->syncLogGetEntry(ths->pLogStore, nextIndex, &pEntry);
@@ -227,6 +252,21 @@ int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntrie
       nextIndex = SYNC_INDEX_BEGIN;
     }
     syncIndexMgrSetIndex(ths->pNextIndex, &(pMsg->srcId), nextIndex);
+
+    // event log, update next-index
+    do {
+      char    host[64];
+      int16_t port;
+      syncUtilU642Addr(pMsg->srcId.addr, host, sizeof(host), &port);
+
+      SyncIndex newNextIndex = nextIndex;
+      SyncIndex newMatchIndex = syncIndexMgrGetIndex(ths->pMatchIndex, &(pMsg->srcId));
+      char      logBuf[256];
+      snprintf(logBuf, sizeof(logBuf), "reset2 next-index:%ld, match-index:%ld for %s:%d", newNextIndex, newMatchIndex,
+               host, port);
+      syncNodeEventLog(ths, logBuf);
+
+    } while (0);
   }
 
   return 0;