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

2022-07-12 13:40:36 +08:00 · 2022-07-12 13:40:36 +08:00 · a059736755
parent 8684f75dcd 946f1101fd
commit a059736755
156 changed files with 7625 additions and 4604 deletions
--- a/docs/en/07-develop/02-model/index.mdx
+++ b/docs/en/07-develop/02-model/index.mdx
@ -9,15 +9,15 @@ The data model employed by TDengine is similar to that of a relational database.
 The [characteristics of time-series data](https://www.taosdata.com/blog/2019/07/09/86.html) from different data collection points may be different. Characteristics include collection frequency, retention policy and others which determine how you create and configure the database. For e.g. days to keep, number of replicas, data block size, whether data updates are allowed and other configurable parameters would be determined by the characteristics of your data and your business requirements. For TDengine to operate with the best performance, we strongly recommend that you create and configure different databases for data with different characteristics. This allows you, for example, to set up different storage and retention policies. When creating a database, there are a lot of parameters that can be configured such as, the days to keep data, the number of replicas, the number of memory blocks, time precision, the minimum and maximum number of rows in each data block, whether compression is enabled, the time range of the data in single data file and so on. Below is an example of the SQL statement to create a database.

 ```sql
-CREATE DATABASE power KEEP 365 DAYS 10 BLOCKS 6 UPDATE 1;
+CREATE DATABASE power KEEP 365 DURATION 10 BUFFER 16 VGROUPS 100 WAL 1;
 ```

 In the above SQL statement:
 - a database named "power" will be created
 - the data in it will be kept for 365 days, which means that data older than 365 days will be deleted automatically
 - a new data file will be created every 10 days
- the number of memory blocks is 6
- data is allowed to be updated
+- the size of memory cache for writing is 16 MB
+- data will be firstly written to WAL without FSYNC

 For more details please refer to [Database](/taos-sql/database).

@ -30,7 +30,6 @@ USE power;
 :::note

 - Any table or STable must belong to a database. To create a table or STable, the database it belongs to must be ready.
- JOIN operations can't be performed on tables from two different databases.
 - Timestamp needs to be specified when inserting rows or querying historical rows.

 :::
@ -52,7 +51,7 @@ Similar to creating a regular table, when creating a STable, the name and schema

 For each kind of data collection point, a corresponding STable must be created. There may be many STables in an application. For electrical power system, we need to create a STable respectively for meters, transformers, busbars, switches. There may be multiple kinds of data collection points on a single device, for example there may be one data collection point for electrical data like current and voltage and another data collection point for environmental data like temperature, humidity and wind direction. Multiple STables are required for these kinds of devices.

-At most 4096 (or 1024 prior to version 2.1.7.0) columns are allowed in a STable. If there are more than 4096 of metrics to be collected for a data collection point, multiple STables are required. There can be multiple databases in a system, while one or more STables can exist in a database.
+At most 4096 columns are allowed in a STable. If there are more than 4096 of metrics to be collected for a data collection point, multiple STables are required. There can be multiple databases in a system, while one or more STables can exist in a database.

 ## Create Table

@ -66,12 +65,11 @@ In the above SQL statement, "d1001" is the table name, "meters" is the STable na

 In the TDengine system, it's recommended to create a table for a data collection point via STable. A table created via STable is called subtable in some parts of the TDengine documentation. All SQL commands applied on regular tables can be applied on subtables.

-:::warning
-It's not recommended to create a table in a database while using a STable from another database as template.
-
 :::tip
 It's suggested to use the globally unique ID of a data collection point as the table name. For example the device serial number could be used as a unique ID. If a unique ID doesn't exist, multiple IDs that are not globally unique can be combined to form a globally unique ID. It's not recommended to use a globally unique ID as tag value.

+:::
+
 ## Create Table Automatically

 In some circumstances, it's unknown whether the table already exists when inserting rows. The table can be created automatically using the SQL statement below, and nothing will happen if the table already exists.
--- a/docs/en/12-taos-sql/02-database.md
+++ b/docs/en/12-taos-sql/02-database.md
@ -32,7 +32,6 @@ CREATE DATABASE [IF NOT EXISTS] db_name [KEEP keep] [DAYS days] [UPDATE 1];
   - cacheLast: [Description](/reference/config/#cachelast)
   - replica: [Description](/reference/config/#replica)
   - quorum: [Description](/reference/config/#quorum)
-   - maxVgroupsPerDb: [Description](/reference/config/#maxvgroupsperdb)
   - comp: [Description](/reference/config/#comp)
   - precision: [Description](/reference/config/#precision)
 6. Please note that all of the parameters mentioned in this section are configured in configuration file `taos.cfg` on the TDengine server. If not specified in the `create database` statement, the values from taos.cfg are used by default. To override default parameters, they must be specified in the `create database` statement.
--- a/docs/zh/07-develop/02-model/index.mdx
+++ b/docs/zh/07-develop/02-model/index.mdx
@ -8,13 +8,13 @@ TDengine 采用类关系型数据模型，需要建库、建表。因此对于

 ## 创建库

-不同类型的数据采集点往往具有不同的数据特征，包括数据采集频率的高低，数据保留时间的长短，副本的数目，数据块的大小，是否允许更新数据等等。为了在各种场景下 TDengine 都能最大效率的工作，TDengine 建议将不同数据特征的表创建在不同的库里，因为每个库可以配置不同的存储策略。创建一个库时，除 SQL 标准的选项外，还可以指定保留时长、副本数、内存块个数、时间精度、文件块里最大最小记录条数、是否压缩、一个数据文件覆盖的天数等多种参数。比如：
+不同类型的数据采集点往往具有不同的数据特征，包括数据采集频率的高低，数据保留时间的长短，副本的数目，数据块的大小，是否允许更新数据等等。为了在各种场景下 TDengine 都能最大效率的工作，TDengine 建议将不同数据特征的表创建在不同的库里，因为每个库可以配置不同的存储策略。创建一个库时，除 SQL 标准的选项外，还可以指定保留时长、副本数、缓存大小、时间精度、文件块里最大最小记录条数、是否压缩、一个数据文件覆盖的天数等多种参数。比如：

 ```sql
-CREATE DATABASE power KEEP 365 DAYS 10 BLOCKS 6 UPDATE 1;
+CREATE DATABASE power KEEP 365 DURATION 10 BUFFER 16 VGROUPS 100 WAL 1;
 ```

-上述语句将创建一个名为 power 的库，这个库的数据将保留 365 天（超过 365 天将被自动删除），每 10 天一个数据文件，内存块数为 6，允许更新数据。详细的语法及参数请见 [数据库管理](/taos-sql/database) 章节。
+上述语句将创建一个名为 power 的库，这个库的数据将保留 365 天（超过 365 天将被自动删除），每 10 天一个数据文件，每个 VNODE 的写入内存池的大小为 16 MB，数据库的 VGROUPS 数量，对该数据库入会写 WAL 但不执行 FSYNC。详细的语法及参数请见 [数据库管理](/taos-sql/database) 章节。

 创建库之后，需要使用 SQL 命令 `USE` 将当前库切换过来，例如：

@ -27,7 +27,6 @@ USE power;
 :::note

 - 任何一张表或超级表必须属于某个库，在创建表之前，必须先创建库。
- 处于两个不同库的表是不能进行 JOIN 操作的。
 - 创建并插入记录、查询历史记录的时候，均需要指定时间戳。

 :::
@ -40,15 +39,11 @@ USE power;
 CREATE STABLE meters (ts timestamp, current float, voltage int, phase float) TAGS (location binary(64), groupId int);
 ```

-:::note
-这一指令中的 STABLE 关键字，在 2.0.15 之前的版本中需写作 TABLE 。
-:::
-
 与创建普通表一样，创建超级表时，需要提供表名（示例中为 meters），表结构 Schema，即数据列的定义。第一列必须为时间戳（示例中为 ts)，其他列为采集的物理量（示例中为 current, voltage, phase)，数据类型可以为整型、浮点型、字符串等。除此之外，还需要提供标签的 schema (示例中为 location, groupId)，标签的数据类型可以为整型、浮点型、字符串等。采集点的静态属性往往可以作为标签，比如采集点的地理位置、设备型号、设备组 ID、管理员 ID 等等。标签的 schema 可以事后增加、删除、修改。具体定义以及细节请见 [TAOS SQL 的超级表管理](/taos-sql/stable) 章节。

 每一种类型的数据采集点需要建立一个超级表，因此一个物联网系统，往往会有多个超级表。对于电网，我们就需要对智能电表、变压器、母线、开关等都建立一个超级表。在物联网中，一个设备就可能有多个数据采集点（比如一台风力发电的风机，有的采集点采集电流、电压等电参数，有的采集点采集温度、湿度、风向等环境参数），这个时候，对这一类型的设备，需要建立多张超级表。

-一张超级表最多容许 4096 列 （在 2.1.7.0 版本之前，列数限制为 1024 列），如果一个采集点采集的物理量个数超过 4096，需要建多张超级表来处理。一个系统可以有多个 DB，一个 DB 里可以有一到多个超级表。
+一张超级表最多容许 4096 列，如果一个采集点采集的物理量个数超过 4096，需要建多张超级表来处理。一个系统可以有多个 DB，一个 DB 里可以有一到多个超级表。

 ## 创建表

@ -60,11 +55,6 @@ CREATE TABLE d1001 USING meters TAGS ("California.SanFrancisco", 2);

 其中 d1001 是表名，meters 是超级表的表名，后面紧跟标签 Location 的具体标签值 "California.SanFrancisco"，标签 groupId 的具体标签值 2。虽然在创建表时，需要指定标签值，但可以事后修改。详细细则请见 [TAOS SQL 的表管理](/taos-sql/table) 章节。

-:::warning
-目前 TDengine 没有从技术层面限制使用一个 database (db1) 的超级表作为模板建立另一个 database (db2) 的子表，后续会禁止这种用法，不建议使用这种方法建表。
-
-:::
-
 TDengine 建议将数据采集点的全局唯一 ID 作为表名(比如设备序列号）。但对于有的场景，并没有唯一的 ID，可以将多个 ID 组合成一个唯一的 ID。不建议将具有唯一性的 ID 作为标签值。

 ### 自动建表
--- a/docs/zh/12-taos-sql/02-database.md
+++ b/docs/zh/12-taos-sql/02-database.md
@ -32,7 +32,6 @@ CREATE DATABASE [IF NOT EXISTS] db_name [KEEP keep] [DAYS days] [UPDATE 1];
   - cacheLast: [详细说明](/reference/config/#cachelast)
   - replica: [详细说明](/reference/config/#replica)
   - quorum: [详细说明](/reference/config/#quorum)
-   - maxVgroupsPerDb: [详细说明](/reference/config/#maxvgroupsperdb)
   - comp: [详细说明](/reference/config/#comp)
   - precision: [详细说明](/reference/config/#precision)
 6. 请注意上面列出的所有参数都可以配置在配置文件 `taosd.cfg` 中作为创建数据库时使用的默认配置， `create database` 的参数中明确指定的会覆盖配置文件中的设置。
--- a/include/common/tglobal.h
+++ b/include/common/tglobal.h
@ -67,7 +67,6 @@ extern int32_t tsNumOfVnodeQueryThreads;
 extern int32_t tsNumOfVnodeFetchThreads;
 extern int32_t tsNumOfVnodeWriteThreads;
 extern int32_t tsNumOfVnodeSyncThreads;
-extern int32_t tsNumOfVnodeMergeThreads;
 extern int32_t tsNumOfQnodeQueryThreads;
 extern int32_t tsNumOfQnodeFetchThreads;
 extern int32_t tsNumOfSnodeSharedThreads;
--- a/include/common/tmsg.h
+++ b/include/common/tmsg.h
@ -56,9 +56,9 @@ extern int32_t tMsgDict[];
 #define TMSG_SEG_CODE(TYPE) (((TYPE)&0xff00) >> 8)
 #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_STREAM_MAX_MSG || (TYPE) < TDMT_MON_MAX_MSG || (TYPE) < TDMT_SYNC_MAX_MSG))                         \
+  ((TYPE) >= 0 && ((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))                                                              \
      ? tMsgInfo[tMsgDict[TMSG_SEG_CODE(TYPE)] + TMSG_SEG_SEQ(TYPE)]                                         \
      : 0
 #define TMSG_INDEX(TYPE) (tMsgDict[TMSG_SEG_CODE(TYPE)] + TMSG_SEG_SEQ(TYPE))
@ -723,7 +723,7 @@ typedef struct {
  int32_t buffer;        // MB
  int32_t pageSize;
  int32_t pages;
-  int32_t lastRowMem;
+  int32_t cacheLastSize;
  int32_t daysPerFile;
  int32_t daysToKeep0;
  int32_t daysToKeep1;
@ -736,7 +736,7 @@ typedef struct {
  int8_t  compression;
  int8_t  replications;
  int8_t  strict;
-  int8_t  cacheLastRow;
+  int8_t  cacheLast;
  int8_t  schemaless;
  int8_t  ignoreExist;
  int32_t numOfRetensions;
@ -752,7 +752,7 @@ typedef struct {
  int32_t buffer;
  int32_t pageSize;
  int32_t pages;
-  int32_t lastRowMem;
+  int32_t cacheLastSize;
  int32_t daysPerFile;
  int32_t daysToKeep0;
  int32_t daysToKeep1;
@ -760,7 +760,7 @@ typedef struct {
  int32_t fsyncPeriod;
  int8_t  walLevel;
  int8_t  strict;
-  int8_t  cacheLastRow;
+  int8_t  cacheLast;
  int8_t  replications;
 } SAlterDbReq;

@ -815,6 +815,27 @@ typedef struct {
 int32_t tSerializeSDbCfgReq(void* buf, int32_t bufLen, SDbCfgReq* pReq);
 int32_t tDeserializeSDbCfgReq(void* buf, int32_t bufLen, SDbCfgReq* pReq);

+typedef struct {
+  char db[TSDB_DB_FNAME_LEN];
+} STrimDbReq;
+
+int32_t tSerializeSTrimDbReq(void* buf, int32_t bufLen, STrimDbReq* pReq);
+int32_t tDeserializeSTrimDbReq(void* buf, int32_t bufLen, STrimDbReq* pReq);
+
+typedef struct {
+  int32_t timestamp;
+} SVTrimDbReq;
+
+int32_t tSerializeSVTrimDbReq(void* buf, int32_t bufLen, SVTrimDbReq* pReq);
+int32_t tDeserializeSVTrimDbReq(void* buf, int32_t bufLen, SVTrimDbReq* pReq);
+
+typedef struct {
+  int32_t timestamp;
+} SVDropTtlTableReq;
+
+int32_t tSerializeSVDropTtlTableReq(void* buf, int32_t bufLen, SVDropTtlTableReq* pReq);
+int32_t tDeserializeSVDropTtlTableReq(void* buf, int32_t bufLen, SVDropTtlTableReq* pReq);
+
 typedef struct {
  int32_t numOfVgroups;
  int32_t numOfStables;
@ -833,7 +854,7 @@ typedef struct {
  int8_t  compression;
  int8_t  replications;
  int8_t  strict;
-  int8_t  cacheLastRow;
+  int8_t  cacheLast;
  int32_t numOfRetensions;
  SArray* pRetensions;
  int8_t  schemaless;
@ -1098,7 +1119,7 @@ typedef struct {
  int32_t  buffer;
  int32_t  pageSize;
  int32_t  pages;
-  int32_t  lastRowMem;
+  int32_t  cacheLastSize;
  int32_t  daysPerFile;
  int32_t  daysToKeep0;
  int32_t  daysToKeep1;
@ -1113,7 +1134,7 @@ typedef struct {
  int8_t   precision;
  int8_t   compression;
  int8_t   strict;
-  int8_t   cacheLastRow;
+  int8_t   cacheLast;
  int8_t   isTsma;
  int8_t   standby;
  int8_t   replica;
@ -1151,7 +1172,7 @@ typedef struct {
  int32_t  buffer;
  int32_t  pageSize;
  int32_t  pages;
-  int32_t  lastRowMem;
+  int32_t  cacheLastSize;
  int32_t  daysPerFile;
  int32_t  daysToKeep0;
  int32_t  daysToKeep1;
@ -1159,7 +1180,7 @@ typedef struct {
  int32_t  fsyncPeriod;
  int8_t   walLevel;
  int8_t   strict;
-  int8_t   cacheLastRow;
+  int8_t   cacheLast;
  int8_t   selfIndex;
  int8_t   replica;
  SReplica replicas[TSDB_MAX_REPLICA];
--- a/include/common/tmsgdef.h
+++ b/include/common/tmsgdef.h
@ -116,6 +116,7 @@ enum {
  TD_DEF_MSG_TYPE(TDMT_MND_ALTER_DB, "alter-db", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_MND_SYNC_DB, "sync-db", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_MND_COMPACT_DB, "compact-db", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_MND_TRIM_DB, "trim-db", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_MND_GET_DB_CFG, "get-db-cfg", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_MND_VGROUP_LIST, "vgroup-list", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_MND_CREATE_FUNC, "create-func", NULL, NULL)
@ -198,9 +199,10 @@ enum {
  TD_DEF_MSG_TYPE(TDMT_VND_ALTER_REPLICA, "alter-replica", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_VND_ALTER_CONFIRM, "alter-confirm", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_VND_ALTER_HASHRANGE, "alter-hashrange", NULL, NULL)
-  TD_DEF_MSG_TYPE(TDMT_VND_COMPACT, "compact", NULL, NULL)
-  TD_DEF_MSG_TYPE(TDMT_VND_DROP_TTL_TABLE, "drop-ttl-stb", NULL, NULL)
-  TD_DEF_MSG_TYPE(TDMT_VND_COMMIT, "commit vnode", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_VND_COMPACT, "vnode-compact", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_VND_DROP_TTL_TABLE, "vnode-drop-ttl-stb", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_VND_TRIM, "vnode-trim", NULL, NULL)
+  TD_DEF_MSG_TYPE(TDMT_VND_COMMIT, "vnode-commit", NULL, NULL)
  TD_DEF_MSG_TYPE(TDMT_VND_MAX_MSG, "vnd-max", NULL, NULL)

  TD_NEW_MSG_SEG(TDMT_SCH_MSG)
--- a/include/common/ttokendef.h
+++ b/include/common/ttokendef.h
@ -74,201 +74,202 @@
 #define TK_DATABASE       56
 #define TK_USE            57
 #define TK_FLUSH          58
-#define TK_IF             59
-#define TK_NOT            60
-#define TK_EXISTS         61
-#define TK_BUFFER         62
-#define TK_CACHELAST      63
-#define TK_CACHELASTSIZE  64
-#define TK_COMP           65
-#define TK_DURATION       66
-#define TK_NK_VARIABLE    67
-#define TK_FSYNC          68
-#define TK_MAXROWS        69
-#define TK_MINROWS        70
-#define TK_KEEP           71
-#define TK_PAGES          72
-#define TK_PAGESIZE       73
-#define TK_PRECISION      74
-#define TK_REPLICA        75
-#define TK_STRICT         76
-#define TK_WAL            77
-#define TK_VGROUPS        78
-#define TK_SINGLE_STABLE  79
-#define TK_RETENTIONS     80
-#define TK_SCHEMALESS     81
-#define TK_NK_COLON       82
-#define TK_TABLE          83
-#define TK_NK_LP          84
-#define TK_NK_RP          85
-#define TK_STABLE         86
-#define TK_ADD            87
-#define TK_COLUMN         88
-#define TK_MODIFY         89
-#define TK_RENAME         90
-#define TK_TAG            91
-#define TK_SET            92
-#define TK_NK_EQ          93
-#define TK_USING          94
-#define TK_TAGS           95
-#define TK_COMMENT        96
-#define TK_BOOL           97
-#define TK_TINYINT        98
-#define TK_SMALLINT       99
-#define TK_INT            100
-#define TK_INTEGER        101
-#define TK_BIGINT         102
-#define TK_FLOAT          103
-#define TK_DOUBLE         104
-#define TK_BINARY         105
-#define TK_TIMESTAMP      106
-#define TK_NCHAR          107
-#define TK_UNSIGNED       108
-#define TK_JSON           109
-#define TK_VARCHAR        110
-#define TK_MEDIUMBLOB     111
-#define TK_BLOB           112
-#define TK_VARBINARY      113
-#define TK_DECIMAL        114
-#define TK_MAX_DELAY      115
-#define TK_WATERMARK      116
-#define TK_ROLLUP         117
-#define TK_TTL            118
-#define TK_SMA            119
-#define TK_FIRST          120
-#define TK_LAST           121
-#define TK_SHOW           122
-#define TK_DATABASES      123
-#define TK_TABLES         124
-#define TK_STABLES        125
-#define TK_MNODES         126
-#define TK_MODULES        127
-#define TK_QNODES         128
-#define TK_FUNCTIONS      129
-#define TK_INDEXES        130
-#define TK_ACCOUNTS       131
-#define TK_APPS           132
-#define TK_CONNECTIONS    133
-#define TK_LICENCE        134
-#define TK_GRANTS         135
-#define TK_QUERIES        136
-#define TK_SCORES         137
-#define TK_TOPICS         138
-#define TK_VARIABLES      139
-#define TK_BNODES         140
-#define TK_SNODES         141
-#define TK_CLUSTER        142
-#define TK_TRANSACTIONS   143
-#define TK_DISTRIBUTED    144
-#define TK_CONSUMERS      145
-#define TK_SUBSCRIPTIONS  146
-#define TK_LIKE           147
-#define TK_INDEX          148
-#define TK_FUNCTION       149
-#define TK_INTERVAL       150
-#define TK_TOPIC          151
-#define TK_AS             152
-#define TK_WITH           153
-#define TK_META           154
-#define TK_CONSUMER       155
-#define TK_GROUP          156
-#define TK_DESC           157
-#define TK_DESCRIBE       158
-#define TK_RESET          159
-#define TK_QUERY          160
-#define TK_CACHE          161
-#define TK_EXPLAIN        162
-#define TK_ANALYZE        163
-#define TK_VERBOSE        164
-#define TK_NK_BOOL        165
-#define TK_RATIO          166
-#define TK_NK_FLOAT       167
-#define TK_COMPACT        168
-#define TK_VNODES         169
-#define TK_IN             170
-#define TK_OUTPUTTYPE     171
-#define TK_AGGREGATE      172
-#define TK_BUFSIZE        173
-#define TK_STREAM         174
-#define TK_INTO           175
-#define TK_TRIGGER        176
-#define TK_AT_ONCE        177
-#define TK_WINDOW_CLOSE   178
-#define TK_IGNORE         179
-#define TK_EXPIRED        180
-#define TK_KILL           181
-#define TK_CONNECTION     182
-#define TK_TRANSACTION    183
-#define TK_BALANCE        184
-#define TK_VGROUP         185
-#define TK_MERGE          186
-#define TK_REDISTRIBUTE   187
-#define TK_SPLIT          188
-#define TK_SYNCDB         189
-#define TK_DELETE         190
-#define TK_INSERT         191
-#define TK_NULL           192
-#define TK_NK_QUESTION    193
-#define TK_NK_ARROW       194
-#define TK_ROWTS          195
-#define TK_TBNAME         196
-#define TK_QSTARTTS       197
-#define TK_QENDTS         198
-#define TK_WSTARTTS       199
-#define TK_WENDTS         200
-#define TK_WDURATION      201
-#define TK_CAST           202
-#define TK_NOW            203
-#define TK_TODAY          204
-#define TK_TIMEZONE       205
-#define TK_CLIENT_VERSION 206
-#define TK_SERVER_VERSION 207
-#define TK_SERVER_STATUS  208
-#define TK_CURRENT_USER   209
-#define TK_COUNT          210
-#define TK_LAST_ROW       211
-#define TK_BETWEEN        212
-#define TK_IS             213
-#define TK_NK_LT          214
-#define TK_NK_GT          215
-#define TK_NK_LE          216
-#define TK_NK_GE          217
-#define TK_NK_NE          218
-#define TK_MATCH          219
-#define TK_NMATCH         220
-#define TK_CONTAINS       221
-#define TK_JOIN           222
-#define TK_INNER          223
-#define TK_SELECT         224
-#define TK_DISTINCT       225
-#define TK_WHERE          226
-#define TK_PARTITION      227
-#define TK_BY             228
-#define TK_SESSION        229
-#define TK_STATE_WINDOW   230
-#define TK_SLIDING        231
-#define TK_FILL           232
-#define TK_VALUE          233
-#define TK_NONE           234
-#define TK_PREV           235
-#define TK_LINEAR         236
-#define TK_NEXT           237
-#define TK_HAVING         238
-#define TK_RANGE          239
-#define TK_EVERY          240
-#define TK_ORDER          241
-#define TK_SLIMIT         242
-#define TK_SOFFSET        243
-#define TK_LIMIT          244
-#define TK_OFFSET         245
-#define TK_ASC            246
-#define TK_NULLS          247
-#define TK_ID             248
-#define TK_NK_BITNOT      249
-#define TK_VALUES         250
-#define TK_IMPORT         251
-#define TK_NK_SEMI        252
-#define TK_FILE           253
+#define TK_TRIM           59
+#define TK_IF             60
+#define TK_NOT            61
+#define TK_EXISTS         62
+#define TK_BUFFER         63
+#define TK_CACHELAST      64
+#define TK_CACHELASTSIZE  65
+#define TK_COMP           66
+#define TK_DURATION       67
+#define TK_NK_VARIABLE    68
+#define TK_FSYNC          69
+#define TK_MAXROWS        70
+#define TK_MINROWS        71
+#define TK_KEEP           72
+#define TK_PAGES          73
+#define TK_PAGESIZE       74
+#define TK_PRECISION      75
+#define TK_REPLICA        76
+#define TK_STRICT         77
+#define TK_WAL            78
+#define TK_VGROUPS        79
+#define TK_SINGLE_STABLE  80
+#define TK_RETENTIONS     81
+#define TK_SCHEMALESS     82
+#define TK_NK_COLON       83
+#define TK_TABLE          84
+#define TK_NK_LP          85
+#define TK_NK_RP          86
+#define TK_STABLE         87
+#define TK_ADD            88
+#define TK_COLUMN         89
+#define TK_MODIFY         90
+#define TK_RENAME         91
+#define TK_TAG            92
+#define TK_SET            93
+#define TK_NK_EQ          94
+#define TK_USING          95
+#define TK_TAGS           96
+#define TK_COMMENT        97
+#define TK_BOOL           98
+#define TK_TINYINT        99
+#define TK_SMALLINT       100
+#define TK_INT            101
+#define TK_INTEGER        102
+#define TK_BIGINT         103
+#define TK_FLOAT          104
+#define TK_DOUBLE         105
+#define TK_BINARY         106
+#define TK_TIMESTAMP      107
+#define TK_NCHAR          108
+#define TK_UNSIGNED       109
+#define TK_JSON           110
+#define TK_VARCHAR        111
+#define TK_MEDIUMBLOB     112
+#define TK_BLOB           113
+#define TK_VARBINARY      114
+#define TK_DECIMAL        115
+#define TK_MAX_DELAY      116
+#define TK_WATERMARK      117
+#define TK_ROLLUP         118
+#define TK_TTL            119
+#define TK_SMA            120
+#define TK_FIRST          121
+#define TK_LAST           122
+#define TK_SHOW           123
+#define TK_DATABASES      124
+#define TK_TABLES         125
+#define TK_STABLES        126
+#define TK_MNODES         127
+#define TK_MODULES        128
+#define TK_QNODES         129
+#define TK_FUNCTIONS      130
+#define TK_INDEXES        131
+#define TK_ACCOUNTS       132
+#define TK_APPS           133
+#define TK_CONNECTIONS    134
+#define TK_LICENCE        135
+#define TK_GRANTS         136
+#define TK_QUERIES        137
+#define TK_SCORES         138
+#define TK_TOPICS         139
+#define TK_VARIABLES      140
+#define TK_BNODES         141
+#define TK_SNODES         142
+#define TK_CLUSTER        143
+#define TK_TRANSACTIONS   144
+#define TK_DISTRIBUTED    145
+#define TK_CONSUMERS      146
+#define TK_SUBSCRIPTIONS  147
+#define TK_LIKE           148
+#define TK_INDEX          149
+#define TK_FUNCTION       150
+#define TK_INTERVAL       151
+#define TK_TOPIC          152
+#define TK_AS             153
+#define TK_WITH           154
+#define TK_META           155
+#define TK_CONSUMER       156
+#define TK_GROUP          157
+#define TK_DESC           158
+#define TK_DESCRIBE       159
+#define TK_RESET          160
+#define TK_QUERY          161
+#define TK_CACHE          162
+#define TK_EXPLAIN        163
+#define TK_ANALYZE        164
+#define TK_VERBOSE        165
+#define TK_NK_BOOL        166
+#define TK_RATIO          167
+#define TK_NK_FLOAT       168
+#define TK_COMPACT        169
+#define TK_VNODES         170
+#define TK_IN             171
+#define TK_OUTPUTTYPE     172
+#define TK_AGGREGATE      173
+#define TK_BUFSIZE        174
+#define TK_STREAM         175
+#define TK_INTO           176
+#define TK_TRIGGER        177
+#define TK_AT_ONCE        178
+#define TK_WINDOW_CLOSE   179
+#define TK_IGNORE         180
+#define TK_EXPIRED        181
+#define TK_KILL           182
+#define TK_CONNECTION     183
+#define TK_TRANSACTION    184
+#define TK_BALANCE        185
+#define TK_VGROUP         186
+#define TK_MERGE          187
+#define TK_REDISTRIBUTE   188
+#define TK_SPLIT          189
+#define TK_SYNCDB         190
+#define TK_DELETE         191
+#define TK_INSERT         192
+#define TK_NULL           193
+#define TK_NK_QUESTION    194
+#define TK_NK_ARROW       195
+#define TK_ROWTS          196
+#define TK_TBNAME         197
+#define TK_QSTARTTS       198
+#define TK_QENDTS         199
+#define TK_WSTARTTS       200
+#define TK_WENDTS         201
+#define TK_WDURATION      202
+#define TK_CAST           203
+#define TK_NOW            204
+#define TK_TODAY          205
+#define TK_TIMEZONE       206
+#define TK_CLIENT_VERSION 207
+#define TK_SERVER_VERSION 208
+#define TK_SERVER_STATUS  209
+#define TK_CURRENT_USER   210
+#define TK_COUNT          211
+#define TK_LAST_ROW       212
+#define TK_BETWEEN        213
+#define TK_IS             214
+#define TK_NK_LT          215
+#define TK_NK_GT          216
+#define TK_NK_LE          217
+#define TK_NK_GE          218
+#define TK_NK_NE          219
+#define TK_MATCH          220
+#define TK_NMATCH         221
+#define TK_CONTAINS       222
+#define TK_JOIN           223
+#define TK_INNER          224
+#define TK_SELECT         225
+#define TK_DISTINCT       226
+#define TK_WHERE          227
+#define TK_PARTITION      228
+#define TK_BY             229
+#define TK_SESSION        230
+#define TK_STATE_WINDOW   231
+#define TK_SLIDING        232
+#define TK_FILL           233
+#define TK_VALUE          234
+#define TK_NONE           235
+#define TK_PREV           236
+#define TK_LINEAR         237
+#define TK_NEXT           238
+#define TK_HAVING         239
+#define TK_RANGE          240
+#define TK_EVERY          241
+#define TK_ORDER          242
+#define TK_SLIMIT         243
+#define TK_SOFFSET        244
+#define TK_LIMIT          245
+#define TK_OFFSET         246
+#define TK_ASC            247
+#define TK_NULLS          248
+#define TK_ID             249
+#define TK_NK_BITNOT      250
+#define TK_VALUES         251
+#define TK_IMPORT         252
+#define TK_NK_SEMI        253
+#define TK_FILE           254

 #define TK_NK_SPACE   300
 #define TK_NK_COMMENT 301
--- a/include/libs/nodes/cmdnodes.h
+++ b/include/libs/nodes/cmdnodes.h
@ -103,6 +103,11 @@ typedef struct SFlushDatabaseStmt {
  char      dbName[TSDB_DB_NAME_LEN];
 } SFlushDatabaseStmt;

+typedef struct STrimDatabaseStmt {
+  ENodeType type;
+  char      dbName[TSDB_DB_NAME_LEN];
+} STrimDatabaseStmt;
+
 typedef struct STableOptions {
  ENodeType  type;
  bool       commentNull;
--- a/include/libs/nodes/nodes.h
+++ b/include/libs/nodes/nodes.h
@ -112,6 +112,7 @@ typedef enum ENodeType {
  QUERY_NODE_DROP_DATABASE_STMT,
  QUERY_NODE_ALTER_DATABASE_STMT,
  QUERY_NODE_FLUSH_DATABASE_STMT,
+  QUERY_NODE_TRIM_DATABASE_STMT,
  QUERY_NODE_CREATE_TABLE_STMT,
  QUERY_NODE_CREATE_SUBTABLE_CLAUSE,
  QUERY_NODE_CREATE_MULTI_TABLE_STMT,
--- a/include/libs/wal/wal.h
+++ b/include/libs/wal/wal.h
@ -45,7 +45,6 @@ extern "C" {
 #define WAL_MAGIC        0xFAFBFCFDULL

 typedef enum {
-  TAOS_WAL_NOLOG = 0,
  TAOS_WAL_WRITE = 1,
  TAOS_WAL_FSYNC = 2,
 } EWalType;
@ -74,7 +73,7 @@ typedef struct {
  int8_t   isWeek;
  uint64_t seqNum;
  uint64_t term;
-} SSyncLogMeta;
+} SWalSyncInfo;

 typedef struct {
  int8_t  protoVer;
@ -84,7 +83,7 @@ typedef struct {
  int64_t ingestTs;  // not implemented

  // sync meta
-  SSyncLogMeta syncMeta;
+  SWalSyncInfo syncMeta;

  char body[];
 } SWalCont;
@ -149,10 +148,21 @@ SWal   *walOpen(const char *path, SWalCfg *pCfg);
 int32_t walAlter(SWal *, SWalCfg *pCfg);
 void    walClose(SWal *);

-// write
-int32_t walWriteWithSyncInfo(SWal *, int64_t index, tmsg_t msgType, SSyncLogMeta syncMeta, const void *body,
-                             int32_t bodyLen);
+// write interfaces
+
+// By assigning index by the caller, wal gurantees linearizability
 int32_t walWrite(SWal *, int64_t index, tmsg_t msgType, const void *body, int32_t bodyLen);
+int32_t walWriteWithSyncInfo(SWal *, int64_t index, tmsg_t msgType, SWalSyncInfo syncMeta, const void *body,
+                             int32_t bodyLen);
+
+// This interface assign version automatically and return to caller.
+// When using this interface with concurrent writes,
+// wal will write all logs atomically,
+// but not sure which one will be actually write first,
+// and then the unique index of successful writen is returned.
+// -1 will be returned for failed writes
+int64_t walAppendLog(SWal *, tmsg_t msgType, SWalSyncInfo syncMeta, const void *body, int32_t bodyLen);
+
 void walFsync(SWal *, bool force);

 // apis for lifecycle management
--- a/include/util/tRealloc.h
+++ b/include/util/tRealloc.h
@ -25,10 +25,11 @@ extern "C" {
 static FORCE_INLINE int32_t tRealloc(uint8_t **ppBuf, int64_t size) {
  int32_t  code = 0;
  int64_t  bsize = 0;
-  uint8_t *pBuf;
+  uint8_t *pBuf = NULL;

  if (*ppBuf) {
-    bsize = *(int64_t *)((*ppBuf) - sizeof(int64_t));
+    pBuf = (*ppBuf) - sizeof(int64_t);
+    bsize = *(int64_t *)pBuf;
  }

  if (bsize >= size) goto _exit;
@ -38,7 +39,7 @@ static FORCE_INLINE int32_t tRealloc(uint8_t **ppBuf, int64_t size) {
    bsize *= 2;
  }

-  pBuf = (uint8_t *)taosMemoryRealloc(*ppBuf ? (*ppBuf) - sizeof(int64_t) : *ppBuf, bsize + sizeof(int64_t));
+  pBuf = (uint8_t *)taosMemoryRealloc(pBuf, bsize + sizeof(int64_t));
  if (pBuf == NULL) {
    code = TSDB_CODE_OUT_OF_MEMORY;
    goto _exit;
--- a/include/util/tdef.h
+++ b/include/util/tdef.h
@ -331,12 +331,12 @@ typedef enum ELogicConditionType {
 #define TSDB_DB_STRICT_OFF              0
 #define TSDB_DB_STRICT_ON               1
 #define TSDB_DEFAULT_DB_STRICT          0
-#define TSDB_MIN_DB_CACHE_LAST_ROW      0
-#define TSDB_MAX_DB_CACHE_LAST_ROW      3
-#define TSDB_DEFAULT_CACHE_LAST_ROW     0
-#define TSDB_MIN_DB_LAST_ROW_MEM        1  // MB
-#define TSDB_MAX_DB_LAST_ROW_MEM        65536
-#define TSDB_DEFAULT_LAST_ROW_MEM       1
+#define TSDB_MIN_DB_CACHE_LAST          0
+#define TSDB_MAX_DB_CACHE_LAST          3
+#define TSDB_DEFAULT_CACHE_LAST         0
+#define TSDB_MIN_DB_CACHE_LAST_SIZE     1  // MB
+#define TSDB_MAX_DB_CACHE_LAST_SIZE     65536
+#define TSDB_DEFAULT_CACHE_LAST_SIZE    1
 #define TSDB_DB_STREAM_MODE_OFF         0
 #define TSDB_DB_STREAM_MODE_ON          1
 #define TSDB_DEFAULT_DB_STREAM_MODE     0
--- a/include/util/thash.h
+++ b/include/util/thash.h
@ -188,7 +188,7 @@ void *taosHashGetKey(void *data, size_t* keyLen);
 void *taosHashAcquire(SHashObj *pHashObj, const void *key, size_t keyLen);

 /**
- * release the prevous acquired obj
+ * release the previous acquired obj
 *
 * @param pHashObj
 * @param data
--- a/include/util/tlockfree.h
+++ b/include/util/tlockfree.h
@ -69,9 +69,10 @@ typedef void (*_ref_fn_t)(const void *pObj);
 #define T_REF_VAL_GET(x) (x)->_ref.val

 // single writer multiple reader lock
-typedef volatile int32_t SRWLatch;
+typedef volatile int64_t SRWLatch;

 void    taosInitRWLatch(SRWLatch *pLatch);
+void    taosInitReentrantRWLatch(SRWLatch *pLatch);
 void    taosWLockLatch(SRWLatch *pLatch);
 void    taosWUnLockLatch(SRWLatch *pLatch);
 void    taosRLockLatch(SRWLatch *pLatch);
--- a/packaging/tools/install.sh
+++ b/packaging/tools/install.sh
@ -328,7 +328,7 @@ function install_header() {
  ${csudo}ln -s ${install_main_dir}/include/taoserror.h ${inc_link_dir}/taoserror.h
  ${csudo}ln -s ${install_main_dir}/include/taosudf.h ${inc_link_dir}/taosudf.h  

-  ${csudo}ln -s ${install_main_dir}/include/taosws.h ${inc_link_dir}/taosws.h || :
+  [ -f ${install_main_dir}/include/taosws.h ] && ${csudo}ln -s ${install_main_dir}/include/taosws.h ${inc_link_dir}/taosws.h || :
 }

 function add_newHostname_to_hosts() {
--- a/packaging/tools/makeclient.sh
+++ b/packaging/tools/makeclient.sh
@ -161,13 +161,11 @@ if [[ $productName == "TDengine" ]]; then
      mkdir -p ${install_dir}/connector
      if [[ "$pagMode" != "lite" ]] && [[ "$cpuType" != "aarch32" ]]; then
          if [ "$osType" != "Darwin" ]; then
-              cp ${build_dir}/lib/*.jar ${install_dir}/connector || :
-          fi
-          if find ${connector_dir}/go -mindepth 1 -maxdepth 1 | read; then
-              cp -r ${connector_dir}/go ${install_dir}/connector
-          else
-              echo "WARNING: go connector not found, please check if want to use it!"
+              [ -f ${build_dir}/lib/*.jar ] && cp ${build_dir}/lib/*.jar ${install_dir}/connector || :
          fi
+          git clone --depth 1 https://github.com/taosdata/driver-go ${install_dir}/connector/go
+          rm -rf ${install_dir}/connector/go/.git ||:
+
          git clone --depth 1 https://github.com/taosdata/taos-connector-python ${install_dir}/connector/python
          rm -rf ${install_dir}/connector/python/.git ||:
 #          cp -r ${connector_dir}/python ${install_dir}/connector
--- a/packaging/tools/makepkg.sh
+++ b/packaging/tools/makepkg.sh
@ -290,19 +290,17 @@ fi

 # Copy driver
 mkdir -p ${install_dir}/driver && cp ${lib_files} ${install_dir}/driver && echo "${versionComp}" >${install_dir}/driver/vercomp.txt
-cp ${wslib_files} ${install_dir}/driver || :
+[ -f ${wslib_files} ] && cp ${wslib_files} ${install_dir}/driver || :

 # Copy connector
 if [ "$verMode" == "cluster" ]; then
    connector_dir="${code_dir}/connector"
    mkdir -p ${install_dir}/connector
    if [[ "$pagMode" != "lite" ]] && [[ "$cpuType" != "aarch32" ]]; then
-        cp ${build_dir}/lib/*.jar ${install_dir}/connector || :
-        if find ${connector_dir}/go -mindepth 1 -maxdepth 1 | read; then
-            cp -r ${connector_dir}/go ${install_dir}/connector
-        else
-            echo "WARNING: go connector not found, please check if want to use it!"
-        fi
+        [ -f ${build_dir}/lib/*.jar ] && cp ${build_dir}/lib/*.jar ${install_dir}/connector || :
+        git clone --depth 1 https://github.com/taosdata/driver-go ${install_dir}/connector/go
+        rm -rf ${install_dir}/connector/go/.git ||:
+
        git clone --depth 1 https://github.com/taosdata/taos-connector-python ${install_dir}/connector/python
        rm -rf ${install_dir}/connector/python/.git ||:

@ -314,6 +312,7 @@ if [ "$verMode" == "cluster" ]; then

        git clone --depth 1 https://github.com/taosdata/libtaos-rs ${install_dir}/connector/rust
        rm -rf ${install_dir}/connector/rust/.git ||:
+
        # cp -r ${connector_dir}/python ${install_dir}/connector
        # cp -r ${connector_dir}/nodejs ${install_dir}/connector
    fi
--- a/packaging/tools/remove.sh
+++ b/packaging/tools/remove.sh
@ -114,6 +114,7 @@ function clean_header() {
  ${csudo}rm -f ${inc_link_dir}/taos.h || :
  ${csudo}rm -f ${inc_link_dir}/taosdef.h || :
  ${csudo}rm -f ${inc_link_dir}/taoserror.h || :
+  ${csudo}rm -f ${inc_link_dir}/taosudf.h || :

  ${csudo}rm -f ${inc_link_dir}/taosws.h || :
 }
--- a/source/client/src/clientImpl.c
+++ b/source/client/src/clientImpl.c
@ -148,7 +148,8 @@ STscObj* taos_connect_internal(const char* ip, const char* user, const char* pas
  return taosConnectImpl(user, &secretEncrypt[0], localDb, NULL, NULL, *pInst, connType);
 }

-int32_t buildRequest(uint64_t connId, const char* sql, int sqlLen, void* param, bool validateSql, SRequestObj** pRequest) {
+int32_t buildRequest(uint64_t connId, const char* sql, int sqlLen, void* param, bool validateSql,
+                     SRequestObj** pRequest) {
  *pRequest = createRequest(connId, TSDB_SQL_SELECT);
  if (*pRequest == NULL) {
    tscError("failed to malloc sqlObj, %s", sql);
@ -351,7 +352,8 @@ int32_t updateQnodeList(SAppInstInfo* pInfo, SArray* pNodeList) {
  if (pNodeList) {
    pInfo->pQnodeList = taosArrayDup(pNodeList);
    taosArraySort(pInfo->pQnodeList, compareQueryNodeLoad);
-    tscDebug("QnodeList updated in cluster 0x%" PRIx64 ", num:%d", pInfo->clusterId, taosArrayGetSize(pInfo->pQnodeList));
+    tscDebug("QnodeList updated in cluster 0x%" PRIx64 ", num:%d", pInfo->clusterId,
+             taosArrayGetSize(pInfo->pQnodeList));
  }
  taosThreadMutexUnlock(&pInfo->qnodeMutex);

@ -808,11 +810,16 @@ int32_t handleQueryExecRsp(SRequestObj* pRequest) {
 void schedulerExecCb(SExecResult* pResult, void* param, int32_t code) {
  SRequestObj* pRequest = (SRequestObj*)param;
  pRequest->code = code;
+
+  if (pResult) {
    memcpy(&pRequest->body.resInfo.execRes, pResult, sizeof(*pResult));
+  }

  if (TDMT_VND_SUBMIT == pRequest->type || TDMT_VND_DELETE == pRequest->type ||
      TDMT_VND_CREATE_TABLE == pRequest->type) {
+    if (pResult) {
      pRequest->body.resInfo.numOfRows = pResult->numOfRows;
+    }

    schedulerFreeJob(&pRequest->body.queryJob, 0);
  }
@ -993,6 +1000,7 @@ void launchAsyncQuery(SRequestObj* pRequest, SQuery* pQuery, SMetaData* pResultM
      pRequest->body.queryFp(pRequest->body.param, pRequest, 0);
      break;
    default:
+      pRequest->body.queryFp(pRequest->body.param, pRequest, -1);
      break;
  }

@ -1473,13 +1481,17 @@ void* doAsyncFetchRows(SRequestObj* pRequest, bool setupOneRowPtr, bool convertU
    tsem_wait(&pParam->sem);
  }

-  if (pRequest->code == TSDB_CODE_SUCCESS && pResultInfo->numOfRows > 0 && setupOneRowPtr) {
+  if (pResultInfo->numOfRows == 0  || pRequest->code != TSDB_CODE_SUCCESS) {
+    return NULL;
+  } else {
+    if (setupOneRowPtr) {
      doSetOneRowPtr(pResultInfo);
      pResultInfo->current += 1;
    }

    return pResultInfo->row;
  }
+}

 static int32_t doPrepareResPtr(SReqResultInfo* pResInfo) {
  if (pResInfo->row == NULL) {
--- a/source/client/src/clientStmt.c
+++ b/source/client/src/clientStmt.c
@ -357,6 +357,7 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
    pStmt->bInfo.inExecCache = true;

    if (pStmt->sql.autoCreateTbl) {
+      tscDebug("reuse stmt block for tb %s in execBlock", pStmt->bInfo.tbFName);
      return TSDB_CODE_SUCCESS;
    }
  }
@ -365,9 +366,11 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
    if (pStmt->bInfo.inExecCache) {
      ASSERT(taosHashGetSize(pStmt->exec.pBlockHash) == 1);
      pStmt->bInfo.needParse = false;
+      tscDebug("reuse stmt block for tb %s in execBlock", pStmt->bInfo.tbFName);
      return TSDB_CODE_SUCCESS;
    }

+    tscDebug("no stmt block cache for tb %s", pStmt->bInfo.tbFName);
    return TSDB_CODE_SUCCESS;
  }

@ -391,6 +394,8 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
        STMT_ERR_RET(TSDB_CODE_OUT_OF_MEMORY);
      }

+      tscDebug("reuse stmt block for tb %s in sqlBlock, suid:0x%" PRIx64 , pStmt->bInfo.tbFName, pStmt->bInfo.tbSuid);
+
      return TSDB_CODE_SUCCESS;
    }

@ -406,6 +411,8 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
  if (TSDB_CODE_PAR_TABLE_NOT_EXIST == code) {
    STMT_ERR_RET(stmtCleanBindInfo(pStmt));

+    tscDebug("tb %s not exist", pStmt->bInfo.tbFName);
+
    return TSDB_CODE_SUCCESS;
  }

@ -420,6 +427,8 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
  if (uid == pStmt->bInfo.tbUid) {
    pStmt->bInfo.needParse = false;

+    tscDebug("tb %s is current table", pStmt->bInfo.tbFName);
+
    return TSDB_CODE_SUCCESS;
  }

@ -440,6 +449,8 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
    pStmt->bInfo.boundTags = pCache->boundTags;
    pStmt->bInfo.tagsCached = true;

+    tscDebug("tb %s in execBlock list, set to current", pStmt->bInfo.tbFName);
+
    return TSDB_CODE_SUCCESS;
  }

@ -461,6 +472,8 @@ int32_t stmtGetFromCache(STscStmt* pStmt) {
      STMT_ERR_RET(TSDB_CODE_OUT_OF_MEMORY);
    }

+    tscDebug("tb %s in sqlBlock list, set to current", pStmt->bInfo.tbFName);
+
    return TSDB_CODE_SUCCESS;
  }

@ -510,6 +523,8 @@ TAOS_STMT* stmtInit(STscObj* taos) {
 int stmtPrepare(TAOS_STMT* stmt, const char* sql, unsigned long length) {
  STscStmt* pStmt = (STscStmt*)stmt;

+  tscDebug("stmt start to prepare");
+
  if (pStmt->sql.status >= STMT_PREPARE) {
    STMT_ERR_RET(stmtResetStmt(pStmt));
  }
@ -529,6 +544,8 @@ int stmtPrepare(TAOS_STMT* stmt, const char* sql, unsigned long length) {
 int stmtSetTbName(TAOS_STMT* stmt, const char* tbName) {
  STscStmt* pStmt = (STscStmt*)stmt;

+  tscDebug("stmt start to set tbName: %s", tbName);
+
  STMT_ERR_RET(stmtSwitchStatus(pStmt, STMT_SETTBNAME));

  int32_t insert = 0;
@ -559,6 +576,8 @@ int stmtSetTbName(TAOS_STMT* stmt, const char* tbName) {
 int stmtSetTbTags(TAOS_STMT* stmt, TAOS_MULTI_BIND* tags) {
  STscStmt* pStmt = (STscStmt*)stmt;

+  tscDebug("stmt start to set tbTags");
+
  STMT_ERR_RET(stmtSwitchStatus(pStmt, STMT_SETTAGS));

  if (pStmt->bInfo.inExecCache) {
@ -572,6 +591,7 @@ int stmtSetTbTags(TAOS_STMT* stmt, TAOS_MULTI_BIND* tags) {
    STMT_ERR_RET(TSDB_CODE_QRY_APP_ERROR);
  }

+  tscDebug("start to bind stmt tag values");
  STMT_ERR_RET(qBindStmtTagsValue(*pDataBlock, pStmt->bInfo.boundTags, pStmt->bInfo.tbSuid, pStmt->bInfo.sname.tname,
                                  tags, pStmt->exec.pRequest->msgBuf, pStmt->exec.pRequest->msgBufLen));

@ -617,6 +637,8 @@ int stmtFetchColFields(STscStmt* pStmt, int32_t* fieldNum, TAOS_FIELD_E** fields
 int stmtBindBatch(TAOS_STMT* stmt, TAOS_MULTI_BIND* bind, int32_t colIdx) {
  STscStmt* pStmt = (STscStmt*)stmt;

+  tscDebug("start to bind stmt data, colIdx: %d", colIdx);
+
  STMT_ERR_RET(stmtSwitchStatus(pStmt, STMT_BIND));

  if (pStmt->bInfo.needParse && pStmt->sql.runTimes && pStmt->sql.type > 0 &&
@ -707,6 +729,8 @@ int stmtBindBatch(TAOS_STMT* stmt, TAOS_MULTI_BIND* bind, int32_t colIdx) {
 int stmtAddBatch(TAOS_STMT* stmt) {
  STscStmt* pStmt = (STscStmt*)stmt;

+  tscDebug("stmt start to add batch");
+
  STMT_ERR_RET(stmtSwitchStatus(pStmt, STMT_ADD_BATCH));

  STMT_ERR_RET(stmtCacheBlock(pStmt));
@ -715,6 +739,8 @@ int stmtAddBatch(TAOS_STMT* stmt) {
 }

 int stmtUpdateTableUid(STscStmt* pStmt, SSubmitRsp* pRsp) {
+  tscDebug("stmt start to update tbUid, blockNum: %d", pRsp->nBlocks);
+
  if (pRsp->nBlocks <= 0) {
    tscError("invalid submit resp block number %d", pRsp->nBlocks);
    STMT_ERR_RET(TSDB_CODE_TSC_APP_ERROR);
@ -727,11 +753,6 @@ int stmtUpdateTableUid(STscStmt* pStmt, SSubmitRsp* pRsp) {
    char*             key = taosHashGetKey(pIter, &keyLen);

    STableMeta* pMeta = qGetTableMetaInDataBlock(pBlock);
-    if (pMeta->uid != pStmt->bInfo.tbUid) {
-      tscError("table uid %" PRIx64 " mis-match with current table uid %" PRIx64, pMeta->uid, pStmt->bInfo.tbUid);
-      STMT_ERR_RET(TSDB_CODE_TSC_APP_ERROR);
-    }
-
    if (pMeta->uid) {
      pIter = taosHashIterate(pStmt->exec.pBlockHash, pIter);
      continue;
@ -775,6 +796,8 @@ int stmtExec(TAOS_STMT* stmt) {
  SSubmitRsp* pRsp = NULL;
  bool        autoCreateTbl = pStmt->exec.autoCreateTbl;

+  tscDebug("stmt start to exec");
+
  STMT_ERR_RET(stmtSwitchStatus(pStmt, STMT_EXECUTE));

  if (STMT_TYPE_QUERY == pStmt->sql.type) {
--- a/source/common/src/tdatablock.c
+++ b/source/common/src/tdatablock.c
@ -463,6 +463,7 @@ SSDataBlock* blockDataExtractBlock(SSDataBlock* pBlock, int32_t startIndex, int3

  pDst->info = pBlock->info;
  pDst->info.rows = 0;
+  pDst->info.capacity = 0;
  size_t numOfCols = taosArrayGetSize(pBlock->pDataBlock);
  for (int32_t i = 0; i < numOfCols; ++i) {
    SColumnInfoData  colInfo = {0};
@ -1746,7 +1747,7 @@ char* dumpBlockData(SSDataBlock* pDataBlock, const char* flag, char** pDataBuf)
    for (int32_t k = 0; k < colNum; k++) {
      SColumnInfoData* pColInfoData = taosArrayGet(pDataBlock->pDataBlock, k);
      void*            var = POINTER_SHIFT(pColInfoData->pData, j * pColInfoData->info.bytes);
-      if (colDataIsNull(pColInfoData, rows, j, NULL) || !var) {
+      if (colDataIsNull(pColInfoData, rows, j, NULL) || !pColInfoData->pData) {
        len += snprintf(dumpBuf + len, size - len, " %15s |", "NULL");
        if (len >= size -1) return dumpBuf;
        continue;
--- a/source/common/src/tglobal.c
+++ b/source/common/src/tglobal.c
@ -58,9 +58,8 @@ int32_t tsNumOfVnodeQueryThreads = 2;
 int32_t tsNumOfVnodeFetchThreads = 4;
 int32_t tsNumOfVnodeWriteThreads = 2;
 int32_t tsNumOfVnodeSyncThreads = 2;
-int32_t tsNumOfVnodeMergeThreads = 2;
 int32_t tsNumOfQnodeQueryThreads = 2;
-int32_t tsNumOfQnodeFetchThreads = 1;
+int32_t tsNumOfQnodeFetchThreads = 4;
 int32_t tsNumOfSnodeSharedThreads = 2;
 int32_t tsNumOfSnodeUniqueThreads = 2;

@ -106,11 +105,6 @@ int32_t tsCompressMsgSize = -1;
 */
 int32_t tsCompressColData = -1;

-/*
- * denote if 3.0 query pattern compatible for 2.0
- */
-int32_t tsCompatibleModel = 1;
-
 // count/hyperloglog function always return values in case of all NULL data or Empty data set.
 int32_t tsCountAlwaysReturnValue = 1;

@ -414,7 +408,7 @@ static int32_t taosAddServerCfg(SConfig *pCfg) {
  tsNumOfMnodeReadThreads = TRANGE(tsNumOfMnodeReadThreads, 1, 4);
  if (cfgAddInt32(pCfg, "numOfMnodeReadThreads", tsNumOfMnodeReadThreads, 1, 1024, 0) != 0) return -1;

-  tsNumOfVnodeQueryThreads = tsNumOfCores / 2;
+  tsNumOfVnodeQueryThreads = tsNumOfCores / 4;
  tsNumOfVnodeQueryThreads = TMAX(tsNumOfVnodeQueryThreads, 2);
  if (cfgAddInt32(pCfg, "numOfVnodeQueryThreads", tsNumOfVnodeQueryThreads, 1, 1024, 0) != 0) return -1;

@ -425,19 +419,16 @@ static int32_t taosAddServerCfg(SConfig *pCfg) {
  tsNumOfVnodeWriteThreads = TMAX(tsNumOfVnodeWriteThreads, 1);
  if (cfgAddInt32(pCfg, "numOfVnodeWriteThreads", tsNumOfVnodeWriteThreads, 1, 1024, 0) != 0) return -1;

-  tsNumOfVnodeSyncThreads = tsNumOfCores / 2;
+  tsNumOfVnodeSyncThreads = tsNumOfCores;
  tsNumOfVnodeSyncThreads = TMAX(tsNumOfVnodeSyncThreads, 1);
  if (cfgAddInt32(pCfg, "numOfVnodeSyncThreads", tsNumOfVnodeSyncThreads, 1, 1024, 0) != 0) return -1;

-  tsNumOfVnodeMergeThreads = tsNumOfCores / 8;
-  tsNumOfVnodeMergeThreads = TRANGE(tsNumOfVnodeMergeThreads, 1, 1);
-  if (cfgAddInt32(pCfg, "numOfVnodeMergeThreads", tsNumOfVnodeMergeThreads, 1, 1024, 0) != 0) return -1;
-
  tsNumOfQnodeQueryThreads = tsNumOfCores / 2;
  tsNumOfQnodeQueryThreads = TMAX(tsNumOfQnodeQueryThreads, 1);
  if (cfgAddInt32(pCfg, "numOfQnodeQueryThreads", tsNumOfQnodeQueryThreads, 1, 1024, 0) != 0) return -1;

-  tsNumOfQnodeFetchThreads = TRANGE(tsNumOfQnodeFetchThreads, 1, 1);
+  tsNumOfQnodeFetchThreads = tsNumOfCores / 2;
+  tsNumOfQnodeFetchThreads = TMAX(tsNumOfQnodeFetchThreads, 4);
  if (cfgAddInt32(pCfg, "numOfQnodeFetchThreads", tsNumOfQnodeFetchThreads, 1, 1024, 0) != 0) return -1;

  tsNumOfSnodeSharedThreads = tsNumOfCores / 4;
@ -598,7 +589,6 @@ static int32_t taosSetServerCfg(SConfig *pCfg) {
  tsNumOfVnodeFetchThreads = cfgGetItem(pCfg, "numOfVnodeFetchThreads")->i32;
  tsNumOfVnodeWriteThreads = cfgGetItem(pCfg, "numOfVnodeWriteThreads")->i32;
  tsNumOfVnodeSyncThreads = cfgGetItem(pCfg, "numOfVnodeSyncThreads")->i32;
-  tsNumOfVnodeMergeThreads = cfgGetItem(pCfg, "numOfVnodeMergeThreads")->i32;
  tsNumOfQnodeQueryThreads = cfgGetItem(pCfg, "numOfQnodeQueryThreads")->i32;
  tsNumOfQnodeFetchThreads = cfgGetItem(pCfg, "numOfQnodeFetchThreads")->i32;
  tsNumOfSnodeSharedThreads = cfgGetItem(pCfg, "numOfSnodeSharedThreads")->i32;
@ -840,8 +830,6 @@ int32_t taosSetCfg(SConfig *pCfg, char *name) {
        tsNumOfVnodeWriteThreads = cfgGetItem(pCfg, "numOfVnodeWriteThreads")->i32;
      } else if (strcasecmp("numOfVnodeSyncThreads", name) == 0) {
        tsNumOfVnodeSyncThreads = cfgGetItem(pCfg, "numOfVnodeSyncThreads")->i32;
-      } else if (strcasecmp("numOfVnodeMergeThreads", name) == 0) {
-        tsNumOfVnodeMergeThreads = cfgGetItem(pCfg, "numOfVnodeMergeThreads")->i32;
      } else if (strcasecmp("numOfQnodeQueryThreads", name) == 0) {
        tsNumOfQnodeQueryThreads = cfgGetItem(pCfg, "numOfQnodeQueryThreads")->i32;
      } else if (strcasecmp("numOfQnodeFetchThreads", name) == 0) {
--- a/source/common/src/tmsg.c
+++ b/source/common/src/tmsg.c
@ -2001,7 +2001,7 @@ int32_t tSerializeSCreateDbReq(void *buf, int32_t bufLen, SCreateDbReq *pReq) {
  if (tEncodeI32(&encoder, pReq->buffer) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pageSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pages) < 0) return -1;
-  if (tEncodeI32(&encoder, pReq->lastRowMem) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->cacheLastSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysPerFile) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep0) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep1) < 0) return -1;
@ -2014,7 +2014,7 @@ int32_t tSerializeSCreateDbReq(void *buf, int32_t bufLen, SCreateDbReq *pReq) {
  if (tEncodeI8(&encoder, pReq->compression) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->replications) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->strict) < 0) return -1;
-  if (tEncodeI8(&encoder, pReq->cacheLastRow) < 0) return -1;
+  if (tEncodeI8(&encoder, pReq->cacheLast) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->schemaless) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->ignoreExist) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->numOfRetensions) < 0) return -1;
@ -2043,7 +2043,7 @@ int32_t tDeserializeSCreateDbReq(void *buf, int32_t bufLen, SCreateDbReq *pReq)
  if (tDecodeI32(&decoder, &pReq->buffer) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pageSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pages) < 0) return -1;
-  if (tDecodeI32(&decoder, &pReq->lastRowMem) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->cacheLastSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysPerFile) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep0) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep1) < 0) return -1;
@ -2056,7 +2056,7 @@ int32_t tDeserializeSCreateDbReq(void *buf, int32_t bufLen, SCreateDbReq *pReq)
  if (tDecodeI8(&decoder, &pReq->compression) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->replications) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->strict) < 0) return -1;
-  if (tDecodeI8(&decoder, &pReq->cacheLastRow) < 0) return -1;
+  if (tDecodeI8(&decoder, &pReq->cacheLast) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->schemaless) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->ignoreExist) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->numOfRetensions) < 0) return -1;
@ -2098,7 +2098,7 @@ int32_t tSerializeSAlterDbReq(void *buf, int32_t bufLen, SAlterDbReq *pReq) {
  if (tEncodeI32(&encoder, pReq->buffer) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pageSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pages) < 0) return -1;
-  if (tEncodeI32(&encoder, pReq->lastRowMem) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->cacheLastSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysPerFile) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep0) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep1) < 0) return -1;
@ -2106,7 +2106,7 @@ int32_t tSerializeSAlterDbReq(void *buf, int32_t bufLen, SAlterDbReq *pReq) {
  if (tEncodeI32(&encoder, pReq->fsyncPeriod) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->walLevel) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->strict) < 0) return -1;
-  if (tEncodeI8(&encoder, pReq->cacheLastRow) < 0) return -1;
+  if (tEncodeI8(&encoder, pReq->cacheLast) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->replications) < 0) return -1;
  tEndEncode(&encoder);

@ -2124,7 +2124,7 @@ int32_t tDeserializeSAlterDbReq(void *buf, int32_t bufLen, SAlterDbReq *pReq) {
  if (tDecodeI32(&decoder, &pReq->buffer) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pageSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pages) < 0) return -1;
-  if (tDecodeI32(&decoder, &pReq->lastRowMem) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->cacheLastSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysPerFile) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep0) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep1) < 0) return -1;
@ -2132,7 +2132,7 @@ int32_t tDeserializeSAlterDbReq(void *buf, int32_t bufLen, SAlterDbReq *pReq) {
  if (tDecodeI32(&decoder, &pReq->fsyncPeriod) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->walLevel) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->strict) < 0) return -1;
-  if (tDecodeI8(&decoder, &pReq->cacheLastRow) < 0) return -1;
+  if (tDecodeI8(&decoder, &pReq->cacheLast) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->replications) < 0) return -1;
  tEndDecode(&decoder);

@ -2647,6 +2647,81 @@ int32_t tDeserializeSDbCfgReq(void *buf, int32_t bufLen, SDbCfgReq *pReq) {
  return 0;
 }

+int32_t tSerializeSTrimDbReq(void *buf, int32_t bufLen, STrimDbReq *pReq) {
+  SEncoder encoder = {0};
+  tEncoderInit(&encoder, buf, bufLen);
+
+  if (tStartEncode(&encoder) < 0) return -1;
+  if (tEncodeCStr(&encoder, pReq->db) < 0) return -1;
+  tEndEncode(&encoder);
+
+  int32_t tlen = encoder.pos;
+  tEncoderClear(&encoder);
+  return tlen;
+}
+
+int32_t tDeserializeSTrimDbReq(void *buf, int32_t bufLen, STrimDbReq *pReq) {
+  SDecoder decoder = {0};
+  tDecoderInit(&decoder, buf, bufLen);
+
+  if (tStartDecode(&decoder) < 0) return -1;
+  if (tDecodeCStrTo(&decoder, pReq->db) < 0) return -1;
+  tEndDecode(&decoder);
+
+  tDecoderClear(&decoder);
+  return 0;
+}
+
+int32_t tSerializeSVTrimDbReq(void *buf, int32_t bufLen, SVTrimDbReq *pReq) {
+  SEncoder encoder = {0};
+  tEncoderInit(&encoder, buf, bufLen);
+
+  if (tStartEncode(&encoder) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->timestamp) < 0) return -1;
+  tEndEncode(&encoder);
+
+  int32_t tlen = encoder.pos;
+  tEncoderClear(&encoder);
+  return tlen;
+}
+
+int32_t tDeserializeSVTrimDbReq(void *buf, int32_t bufLen, SVTrimDbReq *pReq) {
+  SDecoder decoder = {0};
+  tDecoderInit(&decoder, buf, bufLen);
+
+  if (tStartDecode(&decoder) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->timestamp) < 0) return -1;
+  tEndDecode(&decoder);
+
+  tDecoderClear(&decoder);
+  return 0;
+}
+
+int32_t tSerializeSVDropTtlTableReq(void *buf, int32_t bufLen, SVDropTtlTableReq *pReq) {
+  SEncoder encoder = {0};
+  tEncoderInit(&encoder, buf, bufLen);
+
+  if (tStartEncode(&encoder) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->timestamp) < 0) return -1;
+  tEndEncode(&encoder);
+
+  int32_t tlen = encoder.pos;
+  tEncoderClear(&encoder);
+  return tlen;
+}
+
+int32_t tDeserializeSVDropTtlTableReq(void *buf, int32_t bufLen, SVDropTtlTableReq *pReq) {
+  SDecoder decoder = {0};
+  tDecoderInit(&decoder, buf, bufLen);
+
+  if (tStartDecode(&decoder) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->timestamp) < 0) return -1;
+  tEndDecode(&decoder);
+
+  tDecoderClear(&decoder);
+  return 0;
+}
+
 int32_t tSerializeSDbCfgRsp(void *buf, int32_t bufLen, const SDbCfgRsp *pRsp) {
  SEncoder encoder = {0};
  tEncoderInit(&encoder, buf, bufLen);
@ -2669,7 +2744,7 @@ int32_t tSerializeSDbCfgRsp(void *buf, int32_t bufLen, const SDbCfgRsp *pRsp) {
  if (tEncodeI8(&encoder, pRsp->compression) < 0) return -1;
  if (tEncodeI8(&encoder, pRsp->replications) < 0) return -1;
  if (tEncodeI8(&encoder, pRsp->strict) < 0) return -1;
-  if (tEncodeI8(&encoder, pRsp->cacheLastRow) < 0) return -1;
+  if (tEncodeI8(&encoder, pRsp->cacheLast) < 0) return -1;
  if (tEncodeI32(&encoder, pRsp->numOfRetensions) < 0) return -1;
  for (int32_t i = 0; i < pRsp->numOfRetensions; ++i) {
    SRetention *pRetension = taosArrayGet(pRsp->pRetensions, i);
@ -2708,7 +2783,7 @@ int32_t tDeserializeSDbCfgRsp(void *buf, int32_t bufLen, SDbCfgRsp *pRsp) {
  if (tDecodeI8(&decoder, &pRsp->compression) < 0) return -1;
  if (tDecodeI8(&decoder, &pRsp->replications) < 0) return -1;
  if (tDecodeI8(&decoder, &pRsp->strict) < 0) return -1;
-  if (tDecodeI8(&decoder, &pRsp->cacheLastRow) < 0) return -1;
+  if (tDecodeI8(&decoder, &pRsp->cacheLast) < 0) return -1;
  if (tDecodeI32(&decoder, &pRsp->numOfRetensions) < 0) return -1;
  if (pRsp->numOfRetensions > 0) {
    pRsp->pRetensions = taosArrayInit(pRsp->numOfRetensions, sizeof(SRetention));
@ -3619,7 +3694,7 @@ int32_t tSerializeSCreateVnodeReq(void *buf, int32_t bufLen, SCreateVnodeReq *pR
  if (tEncodeI32(&encoder, pReq->buffer) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pageSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pages) < 0) return -1;
-  if (tEncodeI32(&encoder, pReq->lastRowMem) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->cacheLastSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysPerFile) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep0) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep1) < 0) return -1;
@ -3634,7 +3709,7 @@ int32_t tSerializeSCreateVnodeReq(void *buf, int32_t bufLen, SCreateVnodeReq *pR
  if (tEncodeI8(&encoder, pReq->precision) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->compression) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->strict) < 0) return -1;
-  if (tEncodeI8(&encoder, pReq->cacheLastRow) < 0) return -1;
+  if (tEncodeI8(&encoder, pReq->cacheLast) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->standby) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->replica) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->selfIndex) < 0) return -1;
@ -3677,7 +3752,7 @@ int32_t tDeserializeSCreateVnodeReq(void *buf, int32_t bufLen, SCreateVnodeReq *
  if (tDecodeI32(&decoder, &pReq->buffer) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pageSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pages) < 0) return -1;
-  if (tDecodeI32(&decoder, &pReq->lastRowMem) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->cacheLastSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysPerFile) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep0) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep1) < 0) return -1;
@ -3692,7 +3767,7 @@ int32_t tDeserializeSCreateVnodeReq(void *buf, int32_t bufLen, SCreateVnodeReq *
  if (tDecodeI8(&decoder, &pReq->precision) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->compression) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->strict) < 0) return -1;
-  if (tDecodeI8(&decoder, &pReq->cacheLastRow) < 0) return -1;
+  if (tDecodeI8(&decoder, &pReq->cacheLast) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->standby) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->replica) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->selfIndex) < 0) return -1;
@ -3802,7 +3877,7 @@ int32_t tSerializeSAlterVnodeReq(void *buf, int32_t bufLen, SAlterVnodeReq *pReq
  if (tEncodeI32(&encoder, pReq->buffer) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pageSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->pages) < 0) return -1;
-  if (tEncodeI32(&encoder, pReq->lastRowMem) < 0) return -1;
+  if (tEncodeI32(&encoder, pReq->cacheLastSize) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysPerFile) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep0) < 0) return -1;
  if (tEncodeI32(&encoder, pReq->daysToKeep1) < 0) return -1;
@ -3810,7 +3885,7 @@ int32_t tSerializeSAlterVnodeReq(void *buf, int32_t bufLen, SAlterVnodeReq *pReq
  if (tEncodeI32(&encoder, pReq->fsyncPeriod) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->walLevel) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->strict) < 0) return -1;
-  if (tEncodeI8(&encoder, pReq->cacheLastRow) < 0) return -1;
+  if (tEncodeI8(&encoder, pReq->cacheLast) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->selfIndex) < 0) return -1;
  if (tEncodeI8(&encoder, pReq->replica) < 0) return -1;
  for (int32_t i = 0; i < TSDB_MAX_REPLICA; ++i) {
@ -3833,7 +3908,7 @@ int32_t tDeserializeSAlterVnodeReq(void *buf, int32_t bufLen, SAlterVnodeReq *pR
  if (tDecodeI32(&decoder, &pReq->buffer) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pageSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->pages) < 0) return -1;
-  if (tDecodeI32(&decoder, &pReq->lastRowMem) < 0) return -1;
+  if (tDecodeI32(&decoder, &pReq->cacheLastSize) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysPerFile) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep0) < 0) return -1;
  if (tDecodeI32(&decoder, &pReq->daysToKeep1) < 0) return -1;
@ -3841,7 +3916,7 @@ int32_t tDeserializeSAlterVnodeReq(void *buf, int32_t bufLen, SAlterVnodeReq *pR
  if (tDecodeI32(&decoder, &pReq->fsyncPeriod) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->walLevel) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->strict) < 0) return -1;
-  if (tDecodeI8(&decoder, &pReq->cacheLastRow) < 0) return -1;
+  if (tDecodeI8(&decoder, &pReq->cacheLast) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->selfIndex) < 0) return -1;
  if (tDecodeI8(&decoder, &pReq->replica) < 0) return -1;
  for (int32_t i = 0; i < TSDB_MAX_REPLICA; ++i) {
--- a/source/dnode/mgmt/mgmt_mnode/src/mmHandle.c
+++ b/source/dnode/mgmt/mgmt_mnode/src/mmHandle.c
@ -171,6 +171,7 @@ SArray *mmGetMsgHandles() {
  if (dmSetMgmtHandle(pArray, TDMT_MND_USE_DB, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_MND_ALTER_DB, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_MND_COMPACT_DB, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_MND_TRIM_DB, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_MND_GET_DB_CFG, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_MND_VGROUP_LIST, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_MND_REDISTRIBUTE_VGROUP, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
--- a/source/dnode/mgmt/mgmt_vnode/src/vmHandle.c
+++ b/source/dnode/mgmt/mgmt_vnode/src/vmHandle.c
@ -138,6 +138,8 @@ static void vmGenerateVnodeCfg(SCreateVnodeReq *pCreate, SVnodeCfg *pCfg) {
  pCfg->dbId = pCreate->dbUid;
  pCfg->szPage = pCreate->pageSize * 1024;
  pCfg->szCache = pCreate->pages;
+  pCfg->cacheLast = pCreate->cacheLast;
+  pCfg->cacheLastSize = pCreate->cacheLastSize;
  pCfg->szBuf = (uint64_t)pCreate->buffer * 1024 * 1024;
  pCfg->isWeak = true;
  pCfg->isTsma = pCreate->isTsma;
@ -210,7 +212,8 @@ int32_t vmProcessCreateVnodeReq(SVnodeMgmt *pMgmt, SRpcMsg *pMsg) {
    return -1;
  }

-  dDebug("vgId:%d, start to create vnode, tsma:%d standby:%d", createReq.vgId, createReq.isTsma, createReq.standby);
+  dDebug("vgId:%d, start to create vnode, tsma:%d standby:%d cacheLast:%d cacheLastSize:%d", createReq.vgId,
+         createReq.isTsma, createReq.standby, createReq.cacheLast, createReq.cacheLastSize);
  vmGenerateVnodeCfg(&createReq, &vnodeCfg);

  if (vmTsmaAdjustDays(&vnodeCfg, &createReq) < 0) {
@ -370,6 +373,7 @@ SArray *vmGetMsgHandles() {
  if (dmSetMgmtHandle(pArray, TDMT_VND_ALTER_CONFIRM, vmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_VND_ALTER_HASHRANGE, vmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_VND_COMPACT, vmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
+  if (dmSetMgmtHandle(pArray, TDMT_VND_TRIM, vmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_DND_CREATE_VNODE, vmPutMsgToMgmtQueue, 0) == NULL) goto _OVER;
  if (dmSetMgmtHandle(pArray, TDMT_DND_DROP_VNODE, vmPutMsgToMgmtQueue, 0) == NULL) goto _OVER;

--- a/source/dnode/mgmt/test/vnode/vnode.cpp
+++ b/source/dnode/mgmt/test/vnode/vnode.cpp
@ -45,7 +45,7 @@ TEST_F(DndTestVnode, 01_Create_Vnode) {
    createReq.compression = 2;
    createReq.replica = 1;
    createReq.strict = 1;
-    createReq.cacheLastRow = 0;
+    createReq.cacheLast = 0;
    createReq.selfIndex = 0;
    for (int r = 0; r < createReq.replica; ++r) {
      SReplica* pReplica = &createReq.replicas[r];
@ -80,7 +80,7 @@ TEST_F(DndTestVnode, 02_Alter_Vnode) {
    alterReq.walLevel = 1;
    alterReq.replica = 1;
    alterReq.strict = 1;
-    alterReq.cacheLastRow = 0;
+    alterReq.cacheLast = 0;
    alterReq.selfIndex = 0;
    for (int r = 0; r < alterReq.replica; ++r) {
      SReplica* pReplica = &alterReq.replicas[r];
--- a/source/dnode/mnode/impl/inc/mndDef.h
+++ b/source/dnode/mnode/impl/inc/mndDef.h
@ -246,7 +246,7 @@ typedef struct {
  int32_t buffer;
  int32_t pageSize;
  int32_t pages;
-  int32_t lastRowMem;
+  int32_t cacheLastSize;
  int32_t daysPerFile;
  int32_t daysToKeep0;
  int32_t daysToKeep1;
@ -260,7 +260,7 @@ typedef struct {
  int8_t  replications;
  int8_t  strict;
  int8_t  hashMethod;  // default is 1
-  int8_t  cacheLastRow;
+  int8_t  cacheLast;
  int32_t numOfRetensions;
  SArray* pRetensions;
  int8_t  schemaless;
--- a/source/dnode/mnode/impl/inc/mndPrivilege.h
+++ b/source/dnode/mnode/impl/inc/mndPrivilege.h
@ -54,6 +54,7 @@ typedef enum {
  MND_OPER_ALTER_DB,
  MND_OPER_DROP_DB,
  MND_OPER_COMPACT_DB,
+  MND_OPER_TRIM_DB,
  MND_OPER_USE_DB,
  MND_OPER_WRITE_DB,
  MND_OPER_READ_DB,
--- a/source/dnode/mnode/impl/src/mndDb.c
+++ b/source/dnode/mnode/impl/src/mndDb.c
@ -42,6 +42,7 @@ static int32_t  mndProcessAlterDbReq(SRpcMsg *pReq);
 static int32_t  mndProcessDropDbReq(SRpcMsg *pReq);
 static int32_t  mndProcessUseDbReq(SRpcMsg *pReq);
 static int32_t  mndProcessCompactDbReq(SRpcMsg *pReq);
+static int32_t  mndProcessTrimDbReq(SRpcMsg *pReq);
 static int32_t  mndRetrieveDbs(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *pBlock, int32_t rowsCapacity);
 static void     mndCancelGetNextDb(SMnode *pMnode, void *pIter);
 static int32_t  mndProcessGetDbCfgReq(SRpcMsg *pReq);
@ -62,6 +63,7 @@ int32_t mndInitDb(SMnode *pMnode) {
  mndSetMsgHandle(pMnode, TDMT_MND_DROP_DB, mndProcessDropDbReq);
  mndSetMsgHandle(pMnode, TDMT_MND_USE_DB, mndProcessUseDbReq);
  mndSetMsgHandle(pMnode, TDMT_MND_COMPACT_DB, mndProcessCompactDbReq);
+  mndSetMsgHandle(pMnode, TDMT_MND_TRIM_DB, mndProcessTrimDbReq);
  mndSetMsgHandle(pMnode, TDMT_MND_GET_DB_CFG, mndProcessGetDbCfgReq);

  mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_DB, mndRetrieveDbs);
@ -93,7 +95,7 @@ static SSdbRaw *mndDbActionEncode(SDbObj *pDb) {
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.buffer, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.pageSize, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.pages, _OVER)
-  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.lastRowMem, _OVER)
+  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.cacheLastSize, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.daysPerFile, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.daysToKeep0, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.daysToKeep1, _OVER)
@ -106,7 +108,7 @@ static SSdbRaw *mndDbActionEncode(SDbObj *pDb) {
  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.compression, _OVER)
  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.replications, _OVER)
  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.strict, _OVER)
-  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.cacheLastRow, _OVER)
+  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.cacheLast, _OVER)
  SDB_SET_INT8(pRaw, dataPos, pDb->cfg.hashMethod, _OVER)
  SDB_SET_INT32(pRaw, dataPos, pDb->cfg.numOfRetensions, _OVER)
  for (int32_t i = 0; i < pDb->cfg.numOfRetensions; ++i) {
@ -166,7 +168,7 @@ static SSdbRow *mndDbActionDecode(SSdbRaw *pRaw) {
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.buffer, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.pageSize, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.pages, _OVER)
-  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.lastRowMem, _OVER)
+  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.cacheLastSize, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.daysPerFile, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.daysToKeep0, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.daysToKeep1, _OVER)
@ -179,7 +181,7 @@ static SSdbRow *mndDbActionDecode(SSdbRaw *pRaw) {
  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.compression, _OVER)
  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.replications, _OVER)
  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.strict, _OVER)
-  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.cacheLastRow, _OVER)
+  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.cacheLast, _OVER)
  SDB_GET_INT8(pRaw, dataPos, &pDb->cfg.hashMethod, _OVER)
  SDB_GET_INT32(pRaw, dataPos, &pDb->cfg.numOfRetensions, _OVER)
  if (pDb->cfg.numOfRetensions > 0) {
@ -234,7 +236,7 @@ static int32_t mndDbActionUpdate(SSdb *pSdb, SDbObj *pOld, SDbObj *pNew) {
  pOld->cfg.buffer = pNew->cfg.buffer;
  pOld->cfg.pageSize = pNew->cfg.pageSize;
  pOld->cfg.pages = pNew->cfg.pages;
-  pOld->cfg.lastRowMem = pNew->cfg.lastRowMem;
+  pOld->cfg.cacheLastSize = pNew->cfg.cacheLastSize;
  pOld->cfg.daysPerFile = pNew->cfg.daysPerFile;
  pOld->cfg.daysToKeep0 = pNew->cfg.daysToKeep0;
  pOld->cfg.daysToKeep1 = pNew->cfg.daysToKeep1;
@ -242,7 +244,7 @@ static int32_t mndDbActionUpdate(SSdb *pSdb, SDbObj *pOld, SDbObj *pNew) {
  pOld->cfg.fsyncPeriod = pNew->cfg.fsyncPeriod;
  pOld->cfg.walLevel = pNew->cfg.walLevel;
  pOld->cfg.strict = pNew->cfg.strict;
-  pOld->cfg.cacheLastRow = pNew->cfg.cacheLastRow;
+  pOld->cfg.cacheLast = pNew->cfg.cacheLast;
  pOld->cfg.replications = pNew->cfg.replications;
  taosWUnLockLatch(&pOld->lock);
  return 0;
@ -291,7 +293,7 @@ static int32_t mndCheckDbCfg(SMnode *pMnode, SDbCfg *pCfg) {
  if (pCfg->buffer < TSDB_MIN_BUFFER_PER_VNODE || pCfg->buffer > TSDB_MAX_BUFFER_PER_VNODE) return -1;
  if (pCfg->pageSize < TSDB_MIN_PAGESIZE_PER_VNODE || pCfg->pageSize > TSDB_MAX_PAGESIZE_PER_VNODE) return -1;
  if (pCfg->pages < TSDB_MIN_PAGES_PER_VNODE || pCfg->pages > TSDB_MAX_PAGES_PER_VNODE) return -1;
-  if (pCfg->lastRowMem < TSDB_MIN_DB_LAST_ROW_MEM || pCfg->lastRowMem > TSDB_MAX_DB_LAST_ROW_MEM) return -1;
+  if (pCfg->cacheLastSize < TSDB_MIN_DB_CACHE_LAST_SIZE || pCfg->cacheLastSize > TSDB_MAX_DB_CACHE_LAST_SIZE) return -1;
  if (pCfg->daysPerFile < TSDB_MIN_DAYS_PER_FILE || pCfg->daysPerFile > TSDB_MAX_DAYS_PER_FILE) return -1;
  if (pCfg->daysToKeep0 < TSDB_MIN_KEEP || pCfg->daysToKeep0 > TSDB_MAX_KEEP) return -1;
  if (pCfg->daysToKeep1 < TSDB_MIN_KEEP || pCfg->daysToKeep1 > TSDB_MAX_KEEP) return -1;
@ -310,7 +312,7 @@ static int32_t mndCheckDbCfg(SMnode *pMnode, SDbCfg *pCfg) {
  if (pCfg->replications != 1 && pCfg->replications != 3) return -1;
  if (pCfg->strict < TSDB_DB_STRICT_OFF || pCfg->strict > TSDB_DB_STRICT_ON) return -1;
  if (pCfg->schemaless < TSDB_DB_SCHEMALESS_OFF || pCfg->schemaless > TSDB_DB_SCHEMALESS_ON) return -1;
-  if (pCfg->cacheLastRow < TSDB_MIN_DB_CACHE_LAST_ROW || pCfg->cacheLastRow > TSDB_MAX_DB_CACHE_LAST_ROW) return -1;
+  if (pCfg->cacheLast < TSDB_MIN_DB_CACHE_LAST || pCfg->cacheLast > TSDB_MAX_DB_CACHE_LAST) return -1;
  if (pCfg->hashMethod != 1) return -1;
  if (pCfg->replications > mndGetDnodeSize(pMnode)) {
    terrno = TSDB_CODE_MND_NO_ENOUGH_DNODES;
@ -339,8 +341,8 @@ static void mndSetDefaultDbCfg(SDbCfg *pCfg) {
  if (pCfg->compression < 0) pCfg->compression = TSDB_DEFAULT_COMP_LEVEL;
  if (pCfg->replications < 0) pCfg->replications = TSDB_DEFAULT_DB_REPLICA;
  if (pCfg->strict < 0) pCfg->strict = TSDB_DEFAULT_DB_STRICT;
-  if (pCfg->cacheLastRow < 0) pCfg->cacheLastRow = TSDB_DEFAULT_CACHE_LAST_ROW;
-  if (pCfg->lastRowMem <= 0) pCfg->lastRowMem = TSDB_DEFAULT_LAST_ROW_MEM;
+  if (pCfg->cacheLast < 0) pCfg->cacheLast = TSDB_DEFAULT_CACHE_LAST;
+  if (pCfg->cacheLastSize <= 0) pCfg->cacheLastSize = TSDB_DEFAULT_CACHE_LAST_SIZE;
  if (pCfg->numOfRetensions < 0) pCfg->numOfRetensions = 0;
  if (pCfg->schemaless < 0) pCfg->schemaless = TSDB_DB_SCHEMALESS_OFF;
 }
@ -439,7 +441,7 @@ static int32_t mndCreateDb(SMnode *pMnode, SRpcMsg *pReq, SCreateDbReq *pCreate,
      .buffer = pCreate->buffer,
      .pageSize = pCreate->pageSize,
      .pages = pCreate->pages,
-      .lastRowMem = pCreate->lastRowMem,
+      .cacheLastSize = pCreate->cacheLastSize,
      .daysPerFile = pCreate->daysPerFile,
      .daysToKeep0 = pCreate->daysToKeep0,
      .daysToKeep1 = pCreate->daysToKeep1,
@ -452,7 +454,7 @@ static int32_t mndCreateDb(SMnode *pMnode, SRpcMsg *pReq, SCreateDbReq *pCreate,
      .compression = pCreate->compression,
      .replications = pCreate->replications,
      .strict = pCreate->strict,
-      .cacheLastRow = pCreate->cacheLastRow,
+      .cacheLast = pCreate->cacheLast,
      .hashMethod = 1,
      .schemaless = pCreate->schemaless,
  };
@ -623,13 +625,13 @@ static int32_t mndSetDbCfgFromAlterDbReq(SDbObj *pDb, SAlterDbReq *pAlter) {
 #endif
  }

-  if (pAlter->cacheLastRow >= 0 && pAlter->cacheLastRow != pDb->cfg.cacheLastRow) {
-    pDb->cfg.cacheLastRow = pAlter->cacheLastRow;
+  if (pAlter->cacheLast >= 0 && pAlter->cacheLast != pDb->cfg.cacheLast) {
+    pDb->cfg.cacheLast = pAlter->cacheLast;
    terrno = 0;
  }

-  if (pAlter->lastRowMem > 0 && pAlter->lastRowMem != pDb->cfg.lastRowMem) {
-    pDb->cfg.lastRowMem = pAlter->lastRowMem;
+  if (pAlter->cacheLastSize > 0 && pAlter->cacheLastSize != pDb->cfg.cacheLastSize) {
+    pDb->cfg.cacheLastSize = pAlter->cacheLastSize;
    terrno = 0;
  }

@ -801,7 +803,7 @@ static int32_t mndProcessGetDbCfgReq(SRpcMsg *pReq) {
  cfgRsp.compression = pDb->cfg.compression;
  cfgRsp.replications = pDb->cfg.replications;
  cfgRsp.strict = pDb->cfg.strict;
-  cfgRsp.cacheLastRow = pDb->cfg.cacheLastRow;
+  cfgRsp.cacheLast = pDb->cfg.cacheLast;
  cfgRsp.numOfRetensions = pDb->cfg.numOfRetensions;
  cfgRsp.pRetensions = pDb->cfg.pRetensions;
  cfgRsp.schemaless = pDb->cfg.schemaless;
@ -1268,6 +1270,8 @@ int32_t mndValidateDbInfo(SMnode *pMnode, SDbVgVersion *pDbs, int32_t numOfDbs,
  return 0;
 }

+static int32_t mndCompactDb(SMnode *pMnode, SDbObj *pDb) { return 0; }
+
 static int32_t mndProcessCompactDbReq(SRpcMsg *pReq) {
  SMnode       *pMnode = pReq->info.node;
  int32_t       code = -1;
@ -1279,7 +1283,7 @@ static int32_t mndProcessCompactDbReq(SRpcMsg *pReq) {
    goto _OVER;
  }

-  mDebug("db:%s, start to sync", compactReq.db);
+  mDebug("db:%s, start to compact", compactReq.db);

  pDb = mndAcquireDb(pMnode, compactReq.db);
  if (pDb == NULL) {
@ -1290,7 +1294,7 @@ static int32_t mndProcessCompactDbReq(SRpcMsg *pReq) {
    goto _OVER;
  }

-  // code = mndCompactDb();
+  code = mndCompactDb(pMnode, pDb);

 _OVER:
  if (code != 0) {
@ -1301,6 +1305,75 @@ _OVER:
  return code;
 }

+static int32_t mndTrimDb(SMnode *pMnode, SDbObj *pDb) {
+  SSdb       *pSdb = pMnode->pSdb;
+  SVgObj     *pVgroup = NULL;
+  void       *pIter = NULL;
+  SVTrimDbReq trimReq = {.timestamp = taosGetTimestampSec()};
+  int32_t     reqLen = tSerializeSVTrimDbReq(NULL, 0, &trimReq);
+  int32_t     contLen = reqLen + sizeof(SMsgHead);
+
+  while (1) {
+    pIter = sdbFetch(pSdb, SDB_VGROUP, pIter, (void **)&pVgroup);
+    if (pIter == NULL) break;
+
+    SMsgHead *pHead = rpcMallocCont(contLen);
+    if (pHead == NULL) {
+      sdbCancelFetch(pSdb, pVgroup);
+      sdbRelease(pSdb, pVgroup);
+      continue;
+    }
+    pHead->contLen = htonl(contLen);
+    pHead->vgId = htonl(pVgroup->vgId);
+    tSerializeSVTrimDbReq((char *)pHead + sizeof(SMsgHead), contLen, &trimReq);
+
+    SRpcMsg rpcMsg = {.msgType = TDMT_VND_TRIM, .pCont = pHead, .contLen = contLen};
+    SEpSet  epSet = mndGetVgroupEpset(pMnode, pVgroup);
+    int32_t code = tmsgSendReq(&epSet, &rpcMsg);
+    if (code != 0) {
+      mError("vgId:%d, failed to send vnode-trim request to vnode since 0x%x", pVgroup->vgId, code);
+    } else {
+      mDebug("vgId:%d, send vnode-trim request to vnode, time:%d", pVgroup->vgId, trimReq.timestamp);
+    }
+    sdbRelease(pSdb, pVgroup);
+  }
+
+  return 0;
+}
+
+static int32_t mndProcessTrimDbReq(SRpcMsg *pReq) {
+  SMnode    *pMnode = pReq->info.node;
+  int32_t    code = -1;
+  SDbObj    *pDb = NULL;
+  STrimDbReq trimReq = {0};
+
+  if (tDeserializeSTrimDbReq(pReq->pCont, pReq->contLen, &trimReq) != 0) {
+    terrno = TSDB_CODE_INVALID_MSG;
+    goto _OVER;
+  }
+
+  mDebug("db:%s, start to trim", trimReq.db);
+
+  pDb = mndAcquireDb(pMnode, trimReq.db);
+  if (pDb == NULL) {
+    goto _OVER;
+  }
+
+  if (mndCheckDbPrivilege(pMnode, pReq->info.conn.user, MND_OPER_TRIM_DB, pDb) != 0) {
+    goto _OVER;
+  }
+
+  code = mndTrimDb(pMnode, pDb);
+
+_OVER:
+  if (code != 0) {
+    mError("db:%s, failed to process trim db req since %s", trimReq.db, terrstr());
+  }
+
+  mndReleaseDb(pMnode, pDb);
+  return code;
+}
+
 const char *mndGetDbStr(const char *src) {
  char *pos = strstr(src, TS_PATH_DELIMITER);
  if (pos != NULL) ++pos;
@ -1467,7 +1540,7 @@ static void dumpDbInfoData(SSDataBlock *pBlock, SDbObj *pDb, SShowObj *pShow, in
    colDataAppend(pColInfo, rows, (const char *)&pDb->cfg.compression, false);

    pColInfo = taosArrayGet(pBlock->pDataBlock, cols++);
-    colDataAppend(pColInfo, rows, (const char *)&pDb->cfg.cacheLastRow, false);
+    colDataAppend(pColInfo, rows, (const char *)&pDb->cfg.cacheLast, false);

    const char *precStr = NULL;
    switch (pDb->cfg.precision) {
--- a/source/dnode/mnode/impl/src/mndMain.c
+++ b/source/dnode/mnode/impl/src/mndMain.c
@ -531,8 +531,7 @@ static int32_t mndCheckMnodeState(SRpcMsg *pMsg) {
  if (!IsReq(pMsg)) return 0;
  if (pMsg->msgType == TDMT_SCH_QUERY || pMsg->msgType == TDMT_SCH_MERGE_QUERY ||
      pMsg->msgType == TDMT_SCH_QUERY_CONTINUE || pMsg->msgType == TDMT_SCH_QUERY_HEARTBEAT ||
-      pMsg->msgType == TDMT_SCH_FETCH || pMsg->msgType == TDMT_SCH_MERGE_FETCH ||
-      pMsg->msgType == TDMT_SCH_DROP_TASK) {
+      pMsg->msgType == TDMT_SCH_FETCH || pMsg->msgType == TDMT_SCH_MERGE_FETCH || pMsg->msgType == TDMT_SCH_DROP_TASK) {
    return 0;
  }
  if (mndAcquireRpcRef(pMsg->info.node) == 0) return 0;
--- a/source/dnode/mnode/impl/src/mndPrivilege.c
+++ b/source/dnode/mnode/impl/src/mndPrivilege.c
@ -155,7 +155,8 @@ int32_t mndCheckDbPrivilege(SMnode *pMnode, const char *user, EOperType operType
    if (pUser->sysInfo) goto _OVER;
  }

-  if (operType == MND_OPER_ALTER_DB || operType == MND_OPER_DROP_DB || operType == MND_OPER_COMPACT_DB) {
+  if (operType == MND_OPER_ALTER_DB || operType == MND_OPER_DROP_DB || operType == MND_OPER_COMPACT_DB ||
+      operType == MND_OPER_TRIM_DB) {
    if (strcmp(pUser->user, pDb->createUser) == 0 && pUser->sysInfo) goto _OVER;
  }

--- a/source/dnode/mnode/impl/src/mndSma.c
+++ b/source/dnode/mnode/impl/src/mndSma.c
@ -204,6 +204,8 @@ _OVER:
    mError("sma:%s, failed to decode from raw:%p since %s", pSma->name, pRaw, terrstr());
    taosMemoryFreeClear(pSma->expr);
    taosMemoryFreeClear(pSma->tagsFilter);
+    taosMemoryFreeClear(pSma->sql);
+    taosMemoryFreeClear(pSma->ast);
    taosMemoryFreeClear(pRow);
    return NULL;
  }
@ -221,6 +223,8 @@ static int32_t mndSmaActionDelete(SSdb *pSdb, SSmaObj *pSma) {
  mTrace("sma:%s, perform delete action, row:%p", pSma->name, pSma);
  taosMemoryFreeClear(pSma->tagsFilter);
  taosMemoryFreeClear(pSma->expr);
+  taosMemoryFreeClear(pSma->sql);
+  taosMemoryFreeClear(pSma->ast);
  return 0;
 }

@ -527,10 +531,20 @@ static int32_t mndCreateSma(SMnode *pMnode, SRpcMsg *pReq, SMCreateSmaReq *pCrea
  streamObj.version = 1;
  streamObj.sql = pCreate->sql;
  streamObj.smaId = smaObj.uid;
-  streamObj.watermark = 0;
-  streamObj.trigger = STREAM_TRIGGER_AT_ONCE;
+  streamObj.watermark = pCreate->watermark;
+  streamObj.trigger = STREAM_TRIGGER_WINDOW_CLOSE;
+  streamObj.triggerParam = pCreate->maxDelay;
  streamObj.ast = strdup(smaObj.ast);

+  // check the maxDelay
+  if (streamObj.triggerParam < TSDB_MIN_ROLLUP_MAX_DELAY) {
+    int64_t msInterval = convertTimeFromPrecisionToUnit(pCreate->interval, pDb->cfg.precision, TIME_UNIT_MILLISECOND);
+    streamObj.triggerParam = msInterval > TSDB_MIN_ROLLUP_MAX_DELAY ? msInterval : TSDB_MIN_ROLLUP_MAX_DELAY;
+  }
+  if (streamObj.triggerParam > TSDB_MAX_ROLLUP_MAX_DELAY) {
+    streamObj.triggerParam = TSDB_MAX_ROLLUP_MAX_DELAY;
+  }
+
  if (mndAllocSmaVgroup(pMnode, pDb, &streamObj.fixedSinkVg) != 0) {
    mError("sma:%s, failed to create since %s", smaObj.name, terrstr());
    return -1;
--- a/source/dnode/mnode/impl/src/mndStb.c
+++ b/source/dnode/mnode/impl/src/mndStb.c
@ -817,12 +817,14 @@ static int32_t mndProcessTtlTimer(SRpcMsg *pReq) {
  SSdb             *pSdb = pMnode->pSdb;
  SVgObj           *pVgroup = NULL;
  void             *pIter = NULL;
+  SVDropTtlTableReq ttlReq = {.timestamp = taosGetTimestampSec()};
+  int32_t           reqLen = tSerializeSVDropTtlTableReq(NULL, 0, &ttlReq);
+  int32_t           contLen = reqLen + sizeof(SMsgHead);

  while (1) {
    pIter = sdbFetch(pSdb, SDB_VGROUP, pIter, (void **)&pVgroup);
    if (pIter == NULL) break;

-    int32_t   contLen = sizeof(SMsgHead) + sizeof(int32_t);
    SMsgHead *pHead = rpcMallocCont(contLen);
    if (pHead == NULL) {
      sdbCancelFetch(pSdb, pVgroup);
@ -831,17 +833,15 @@ static int32_t mndProcessTtlTimer(SRpcMsg *pReq) {
    }
    pHead->contLen = htonl(contLen);
    pHead->vgId = htonl(pVgroup->vgId);
-
-    int32_t t = taosGetTimestampSec();
-    *(int32_t *)((char *)pHead + sizeof(SMsgHead)) = htonl(t);
+    tSerializeSVDropTtlTableReq((char *)pHead + sizeof(SMsgHead), contLen, &ttlReq);

    SRpcMsg rpcMsg = {.msgType = TDMT_VND_DROP_TTL_TABLE, .pCont = pHead, .contLen = contLen};
    SEpSet  epSet = mndGetVgroupEpset(pMnode, pVgroup);
    int32_t code = tmsgSendReq(&epSet, &rpcMsg);
    if (code != 0) {
-      mError("failed to send ttl time seed, code:0x%x", code);
+      mError("vgId:%d, failed to send drop ttl table request to vnode since 0x%x", pVgroup->vgId, code);
    } else {
-      mDebug("send ttl time seed success, time:%d", t);
+      mDebug("vgId:%d, send drop ttl table request to vnode, time:%d", pVgroup->vgId, ttlReq.timestamp);
    }
    sdbRelease(pSdb, pVgroup);
  }
--- a/source/dnode/mnode/impl/src/mndVgroup.c
+++ b/source/dnode/mnode/impl/src/mndVgroup.c
@ -207,7 +207,7 @@ void *mndBuildCreateVnodeReq(SMnode *pMnode, SDnodeObj *pDnode, SDbObj *pDb, SVg
  createReq.buffer = pDb->cfg.buffer;
  createReq.pageSize = pDb->cfg.pageSize;
  createReq.pages = pDb->cfg.pages;
-  createReq.lastRowMem = pDb->cfg.lastRowMem;
+  createReq.cacheLastSize = pDb->cfg.cacheLastSize;
  createReq.daysPerFile = pDb->cfg.daysPerFile;
  createReq.daysToKeep0 = pDb->cfg.daysToKeep0;
  createReq.daysToKeep1 = pDb->cfg.daysToKeep1;
@ -219,7 +219,7 @@ void *mndBuildCreateVnodeReq(SMnode *pMnode, SDnodeObj *pDnode, SDbObj *pDb, SVg
  createReq.precision = pDb->cfg.precision;
  createReq.compression = pDb->cfg.compression;
  createReq.strict = pDb->cfg.strict;
-  createReq.cacheLastRow = pDb->cfg.cacheLastRow;
+  createReq.cacheLast = pDb->cfg.cacheLast;
  createReq.replica = pVgroup->replica;
  createReq.selfIndex = -1;
  createReq.hashBegin = pVgroup->hashBegin;
@ -277,7 +277,7 @@ void *mndBuildAlterVnodeReq(SMnode *pMnode, SDbObj *pDb, SVgObj *pVgroup, int32_
  alterReq.buffer = pDb->cfg.buffer;
  alterReq.pageSize = pDb->cfg.pageSize;
  alterReq.pages = pDb->cfg.pages;
-  alterReq.lastRowMem = pDb->cfg.lastRowMem;
+  alterReq.cacheLastSize = pDb->cfg.cacheLastSize;
  alterReq.daysPerFile = pDb->cfg.daysPerFile;
  alterReq.daysToKeep0 = pDb->cfg.daysToKeep0;
  alterReq.daysToKeep1 = pDb->cfg.daysToKeep1;
@ -285,7 +285,7 @@ void *mndBuildAlterVnodeReq(SMnode *pMnode, SDbObj *pDb, SVgObj *pVgroup, int32_
  alterReq.fsyncPeriod = pDb->cfg.fsyncPeriod;
  alterReq.walLevel = pDb->cfg.walLevel;
  alterReq.strict = pDb->cfg.strict;
-  alterReq.cacheLastRow = pDb->cfg.cacheLastRow;
+  alterReq.cacheLast = pDb->cfg.cacheLast;
  alterReq.replica = pVgroup->replica;

  for (int32_t v = 0; v < pVgroup->replica; ++v) {
@ -307,7 +307,7 @@ void *mndBuildAlterVnodeReq(SMnode *pMnode, SDbObj *pDb, SVgObj *pVgroup, int32_
    terrno = TSDB_CODE_OUT_OF_MEMORY;
    return NULL;
  }
-  contLen += +sizeof(SMsgHead);
+  contLen += sizeof(SMsgHead);

  void *pReq = taosMemoryMalloc(contLen);
  if (pReq == NULL) {
@ -742,8 +742,8 @@ int64_t mndGetVgroupMemory(SMnode *pMnode, SDbObj *pDbInput, SVgObj *pVgroup) {
  int64_t vgroupMemroy = 0;
  if (pDb != NULL) {
    vgroupMemroy = (int64_t)pDb->cfg.buffer * 1024 * 1024 + (int64_t)pDb->cfg.pages * pDb->cfg.pageSize * 1024;
-    if (pDb->cfg.cacheLastRow > 0) {
-      vgroupMemroy += (int64_t)pDb->cfg.lastRowMem * 1024 * 1024;
+    if (pDb->cfg.cacheLast > 0) {
+      vgroupMemroy += (int64_t)pDb->cfg.cacheLastSize * 1024 * 1024;
    }
  }

--- a/source/dnode/mnode/impl/test/db/db.cpp
+++ b/source/dnode/mnode/impl/test/db/db.cpp
@ -50,7 +50,7 @@ TEST_F(MndTestDb, 02_Create_Alter_Drop_Db) {
    createReq.compression = 2;
    createReq.replications = 1;
    createReq.strict = 1;
-    createReq.cacheLastRow = 0;
+    createReq.cacheLast = 0;
    createReq.ignoreExist = 1;
    createReq.numOfStables = 0;
    createReq.numOfRetensions = 0;
@ -84,7 +84,7 @@ TEST_F(MndTestDb, 02_Create_Alter_Drop_Db) {
    alterdbReq.fsyncPeriod = 4000;
    alterdbReq.walLevel = 2;
    alterdbReq.strict = 1;
-    alterdbReq.cacheLastRow = 1;
+    alterdbReq.cacheLast = 1;
    alterdbReq.replications = 1;

    int32_t contLen = tSerializeSAlterDbReq(NULL, 0, &alterdbReq);
@ -146,7 +146,7 @@ TEST_F(MndTestDb, 03_Create_Use_Restart_Use_Db) {
    createReq.compression = 2;
    createReq.replications = 1;
    createReq.strict = 1;
-    createReq.cacheLastRow = 0;
+    createReq.cacheLast = 0;
    createReq.ignoreExist = 1;
    createReq.numOfStables = 0;
    createReq.numOfRetensions = 0;
--- a/source/dnode/mnode/impl/test/dnode/mdnode.cpp
+++ b/source/dnode/mnode/impl/test/dnode/mdnode.cpp
@ -288,7 +288,7 @@ TEST_F(MndTestDnode, 05_Create_Drop_Restart_Dnode) {
    createReq.compression = 2;
    createReq.replications = 1;
    createReq.strict = 1;
-    createReq.cacheLastRow = 0;
+    createReq.cacheLast = 0;
    createReq.ignoreExist = 1;
    createReq.numOfStables = 0;
    createReq.numOfRetensions = 0;
@ -319,7 +319,7 @@ TEST_F(MndTestDnode, 05_Create_Drop_Restart_Dnode) {
    alterdbReq.fsyncPeriod = 4000;
    alterdbReq.walLevel = 2;
    alterdbReq.strict = 1;
-    alterdbReq.cacheLastRow = 1;
+    alterdbReq.cacheLast = 1;
    alterdbReq.replications = 3;

    int32_t contLen = tSerializeSAlterDbReq(NULL, 0, &alterdbReq);
@ -345,7 +345,7 @@ TEST_F(MndTestDnode, 05_Create_Drop_Restart_Dnode) {
    alterdbReq.fsyncPeriod = 4000;
    alterdbReq.walLevel = 2;
    alterdbReq.strict = 1;
-    alterdbReq.cacheLastRow = 1;
+    alterdbReq.cacheLast = 1;
    alterdbReq.replications = 1;

    int32_t contLen = tSerializeSAlterDbReq(NULL, 0, &alterdbReq);
--- a/source/dnode/mnode/impl/test/sma/sma.cpp
+++ b/source/dnode/mnode/impl/test/sma/sma.cpp
@ -55,7 +55,7 @@ void* MndTestSma::BuildCreateDbReq(const char* dbname, int32_t* pContLen) {
  createReq.compression = 2;
  createReq.replications = 1;
  createReq.strict = 1;
-  createReq.cacheLastRow = 0;
+  createReq.cacheLast = 0;
  createReq.ignoreExist = 1;

  int32_t contLen = tSerializeSCreateDbReq(NULL, 0, &createReq);
--- a/source/dnode/mnode/impl/test/stb/stb.cpp
+++ b/source/dnode/mnode/impl/test/stb/stb.cpp
@ -56,7 +56,7 @@ void* MndTestStb::BuildCreateDbReq(const char* dbname, int32_t* pContLen) {
  createReq.compression = 2;
  createReq.replications = 1;
  createReq.strict = 1;
-  createReq.cacheLastRow = 0;
+  createReq.cacheLast = 0;
  createReq.ignoreExist = 1;

  int32_t contLen = tSerializeSCreateDbReq(NULL, 0, &createReq);
--- a/source/dnode/mnode/impl/test/topic/topic.cpp
+++ b/source/dnode/mnode/impl/test/topic/topic.cpp
@ -48,7 +48,7 @@ void* MndTestTopic::BuildCreateDbReq(const char* dbname, int32_t* pContLen) {
  createReq.compression = 2;
  createReq.replications = 1;
  createReq.strict = 1;
-  createReq.cacheLastRow = 0;
+  createReq.cacheLast = 0;
  createReq.ignoreExist = 1;

  int32_t contLen = tSerializeSCreateDbReq(NULL, 0, &createReq);
--- a/source/dnode/mnode/impl/test/user/user.cpp
+++ b/source/dnode/mnode/impl/test/user/user.cpp
@ -315,7 +315,7 @@ TEST_F(MndTestUser, 03_Alter_User) {
    createReq.compression = 2;
    createReq.replications = 1;
    createReq.strict = 1;
-    createReq.cacheLastRow = 0;
+    createReq.cacheLast = 0;
    createReq.ignoreExist = 1;

    int32_t contLen = tSerializeSCreateDbReq(NULL, 0, &createReq);
--- a/source/dnode/vnode/inc/vnode.h
+++ b/source/dnode/vnode/inc/vnode.h
@ -142,6 +142,9 @@ int32_t tsdbRetrieveLastRow(void *pReader, SSDataBlock *pResBlock, const int32_t
 int32_t tsdbLastrowReaderClose(void *pReader);
 int32_t tsdbGetTableSchema(SVnode *pVnode, int64_t uid, STSchema **pSchema, int64_t *suid);

+void   tsdbCacheSetCapacity(SVnode *pVnode, size_t capacity);
+size_t tsdbCacheGetCapacity(SVnode *pVnode);
+
 // tq

 typedef struct STqReader {
@ -210,11 +213,13 @@ struct SVnodeCfg {
  int32_t  vgId;
  char     dbname[TSDB_DB_FNAME_LEN];
  uint64_t dbId;
+  int32_t  cacheLastSize;
  int32_t  szPage;
  int32_t  szCache;
  uint64_t szBuf;
  bool     isHeap;
  bool     isWeak;
+  int8_t   cacheLast;
  int8_t   isTsma;
  int8_t   isRsma;
  int8_t   hashMethod;
--- a/source/dnode/vnode/src/inc/sma.h
+++ b/source/dnode/vnode/src/inc/sma.h
@ -67,7 +67,6 @@ struct SRSmaStat {
  int64_t   submitVer;
  int64_t   refId;         // shared by fetch tasks
  int8_t    triggerStat;   // shared by fetch tasks
-  int8_t    runningStat;   // for persistence task 
  SHashObj *rsmaInfoHash;  // key: stbUid, value: SRSmaInfo;
 };

@ -83,7 +82,6 @@ struct SSmaStat {
 #define SMA_RSMA_STAT(s)     (&(s)->rsmaStat)
 #define RSMA_INFO_HASH(r)    ((r)->rsmaInfoHash)
 #define RSMA_TRIGGER_STAT(r) (&(r)->triggerStat)
-#define RSMA_RUNNING_STAT(r) (&(r)->runningStat)
 #define RSMA_REF_ID(r)       ((r)->refId)
 #define RSMA_SUBMIT_VER(r)   ((r)->submitVer)

@ -93,7 +91,7 @@ enum {
  TASK_TRIGGER_STAT_INACTIVE = 2,
  TASK_TRIGGER_STAT_PAUSED = 3,
  TASK_TRIGGER_STAT_CANCELLED = 4,
-  TASK_TRIGGER_STAT_FINISHED = 5,
+  TASK_TRIGGER_STAT_DROPPED = 5,
 };

 void  tdDestroySmaEnv(SSmaEnv *pSmaEnv);
--- a/source/dnode/vnode/src/inc/tsdb.h
+++ b/source/dnode/vnode/src/inc/tsdb.h
@ -50,7 +50,6 @@ typedef struct SColData       SColData;
 typedef struct SBlockDataHdr SBlockDataHdr;
 typedef struct SBlockData    SBlockData;
 typedef struct SDelFile      SDelFile;
-typedef struct STsdbCacheFile STsdbCacheFile;
 typedef struct SHeadFile     SHeadFile;
 typedef struct SDataFile     SDataFile;
 typedef struct SLastFile     SLastFile;
@ -163,6 +162,7 @@ int32_t tGetMapData(uint8_t *p, SMapData *pMapData);
 // other
 int32_t tsdbKeyFid(TSKEY key, int32_t minutes, int8_t precision);
 void    tsdbFidKeyRange(int32_t fid, int32_t minutes, int8_t precision, TSKEY *minKey, TSKEY *maxKey);
+int32_t tsdbFidLevel(int32_t fid, STsdbKeepCfg *pKeepCfg, int64_t now);
 int32_t tsdbBuildDeleteSkyline(SArray *aDelData, int32_t sidx, int32_t eidx, SArray *aSkyline);
 void    tsdbCalcColDataSMA(SColData *pColData, SColumnDataAgg *pColAgg);
 // tsdbMemTable ==============================================================================================
@ -200,6 +200,7 @@ int32_t tsdbFSRollback(STsdbFS *pFS);

 int32_t    tsdbFSStateUpsertDelFile(STsdbFSState *pState, SDelFile *pDelFile);
 int32_t    tsdbFSStateUpsertDFileSet(STsdbFSState *pState, SDFileSet *pSet);
+void       tsdbFSStateDeleteDFileSet(STsdbFSState *pState, int32_t fid);
 SDelFile  *tsdbFSStateGetDelFile(STsdbFSState *pState);
 SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid);
 // tsdbReaderWriter.c ==============================================================================================
@ -213,6 +214,7 @@ int32_t tsdbWriteBlockData(SDataFWriter *pWriter, SBlockData *pBlockData, uint8_
                           SBlockIdx *pBlockIdx, SBlock *pBlock, int8_t cmprAlg);

 SDFileSet *tsdbDataFWriterGetWSet(SDataFWriter *pWriter);
+int32_t    tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo);
 // SDataFReader
 int32_t tsdbDataFReaderOpen(SDataFReader **ppReader, STsdb *pTsdb, SDFileSet *pSet);
 int32_t tsdbDataFReaderClose(SDataFReader **ppReader);
@ -235,17 +237,26 @@ int32_t tsdbDelFReaderClose(SDelFReader **ppReader);
 int32_t tsdbReadDelData(SDelFReader *pReader, SDelIdx *pDelIdx, SArray *aDelData, uint8_t **ppBuf);
 int32_t tsdbReadDelIdx(SDelFReader *pReader, SArray *aDelIdx, uint8_t **ppBuf);

+#define TSDB_CACHE_NO(c)       ((c).cacheLast == 0)
+#define TSDB_CACHE_LAST_ROW(c) (((c).cacheLast & 1) > 0)
+#define TSDB_CACHE_LAST(c)     (((c).cacheLast & 2) > 0)
+
 // tsdbCache
 int32_t tsdbOpenCache(STsdb *pTsdb);
 void    tsdbCloseCache(SLRUCache *pCache);
-int32_t tsdbCacheInsertLast(SLRUCache *pCache, tb_uid_t uid, STSRow *row);
+int32_t tsdbCacheInsertLast(SLRUCache *pCache, tb_uid_t uid, STSRow *row, STsdb *pTsdb);
 int32_t tsdbCacheInsertLastrow(SLRUCache *pCache, STsdb *pTsdb, tb_uid_t uid, STSRow *row, bool dup);
 int32_t tsdbCacheGetLastH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHandle **h);
 int32_t tsdbCacheGetLastrowH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHandle **h);
 int32_t tsdbCacheRelease(SLRUCache *pCache, LRUHandle *h);

+int32_t tsdbCacheDeleteLastrow(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey);
+int32_t tsdbCacheDeleteLast(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey);
 int32_t tsdbCacheDelete(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey);

+void   tsdbCacheSetCapacity(SVnode *pVnode, size_t capacity);
+size_t tsdbCacheGetCapacity(SVnode *pVnode);
+
 int32_t tsdbCacheLastArray2Row(SArray *pLastArray, STSRow **ppRow, STSchema *pSchema);

 // structs =======================
--- a/source/dnode/vnode/src/inc/vnodeInt.h
+++ b/source/dnode/vnode/src/inc/vnodeInt.h
@ -122,6 +122,7 @@ int         tsdbOpen(SVnode* pVnode, STsdb** ppTsdb, const char* dir, STsdbKeepC
 int         tsdbClose(STsdb** pTsdb);
 int32_t     tsdbBegin(STsdb* pTsdb);
 int32_t     tsdbCommit(STsdb* pTsdb);
+int32_t     tsdbDoRetention(STsdb* pTsdb, int64_t now);
 int         tsdbScanAndConvertSubmitMsg(STsdb* pTsdb, SSubmitReq* pMsg);
 int         tsdbInsertData(STsdb* pTsdb, int64_t version, SSubmitReq* pMsg, SSubmitRsp* pRsp);
 int32_t     tsdbInsertTableData(STsdb* pTsdb, int64_t version, SSubmitMsgIter* pMsgIter, SSubmitBlk* pBlock,
@ -171,8 +172,9 @@ int32_t tdProcessTSmaCreate(SSma* pSma, int64_t version, const char* msg);
 int32_t tdProcessTSmaInsert(SSma* pSma, int64_t indexUid, const char* msg);
 int64_t tdRSmaGetMaxSubmitVer(SSma* pSma, int8_t level);

-int32_t tdProcessRSmaCreate(SVnode* pVnode, SVCreateStbReq* pReq);
+int32_t tdProcessRSmaCreate(SSma* pSma, SVCreateStbReq* pReq);
 int32_t tdProcessRSmaSubmit(SSma* pSma, void* pMsg, int32_t inputType);
+int32_t tdProcessRSmaDrop(SSma* pSma, SVDropStbReq* pReq);
 int32_t tdFetchTbUidList(SSma* pSma, STbUidStore** ppStore, tb_uid_t suid, tb_uid_t uid);
 int32_t tdUpdateTbUidList(SSma* pSma, STbUidStore* pUidStore);
 void    tdUidStoreDestory(STbUidStore* pStore);
--- a/source/dnode/vnode/src/meta/metaQuery.c
+++ b/source/dnode/vnode/src/meta/metaQuery.c
@ -147,6 +147,8 @@ int metaTbCursorNext(SMTbCursor *pTbCur) {
      return -1;
    }

+    tDecoderClear(&pTbCur->mr.coder);
+
    metaGetTableEntryByVersion(&pTbCur->mr, *(int64_t *)pTbCur->pVal, *(tb_uid_t *)pTbCur->pKey);
    if (pTbCur->mr.me.type == TSDB_SUPER_TABLE) {
      continue;
--- a/source/dnode/vnode/src/sma/smaEnv.c
+++ b/source/dnode/vnode/src/sma/smaEnv.c
@ -254,26 +254,7 @@ static void tdDestroyRSmaStat(void *pRSmaStat) {
    // step 1: set rsma trigger stat cancelled
    atomic_store_8(RSMA_TRIGGER_STAT(pStat), TASK_TRIGGER_STAT_CANCELLED);

-    // step 2: wait the persistence thread to finish
-    int32_t nLoops = 0;
-    if (atomic_load_8(RSMA_RUNNING_STAT(pStat)) == 1) {
-      while (1) {
-        if (atomic_load_8(RSMA_TRIGGER_STAT(pStat)) == TASK_TRIGGER_STAT_FINISHED) {
-          smaDebug("vgId:%d, rsma persist task finished already", SMA_VID(pSma));
-          break;
-        } else {
-          smaDebug("vgId:%d, rsma persist task not finished yet since rsma stat in %" PRIi8, SMA_VID(pSma),
-                   atomic_load_8(RSMA_TRIGGER_STAT(pStat)));
-        }
-        ++nLoops;
-        if (nLoops > 1000) {
-          sched_yield();
-          nLoops = 0;
-        }
-      }
-    }
-
-    // step 3: destroy the rsma info and associated fetch tasks
+    // step 2: destroy the rsma info and associated fetch tasks
    // TODO: use taosHashSetFreeFp when taosHashSetFreeFp is ready.
    if (taosHashGetSize(RSMA_INFO_HASH(pStat)) > 0) {
      void *infoHash = taosHashIterate(RSMA_INFO_HASH(pStat), NULL);
@ -285,8 +266,8 @@ static void tdDestroyRSmaStat(void *pRSmaStat) {
    }
    taosHashCleanup(RSMA_INFO_HASH(pStat));

-    // step 5: wait all triggered fetch tasks finished
-    nLoops = 0;
+    // step 3: wait all triggered fetch tasks finished
+    int32_t nLoops = 0;
    while (1) {
      if (T_REF_VAL_GET((SSmaStat *)pStat) == 0) {
        smaDebug("vgId:%d, rsma fetch tasks all finished", SMA_VID(pSma));
--- a/source/dnode/vnode/src/sma/smaRollup.c
+++ b/source/dnode/vnode/src/sma/smaRollup.c
@ -37,8 +37,6 @@ static SRSmaInfo *tdGetRSmaInfoBySuid(SSma *pSma, int64_t suid);
 static int32_t    tdRSmaFetchAndSubmitResult(SRSmaInfoItem *pItem, STSchema *pTSchema, int64_t suid, SRSmaStat *pStat,
                                             int8_t blkType);
 static void       tdRSmaFetchTrigger(void *param, void *tmrId);
-static void       tdRSmaPersistTrigger(void *param, void *tmrId);
-static void      *tdRSmaPersistExec(void *param);
 static void       tdRSmaQTaskInfoGetFName(int32_t vid, int64_t version, char *outputName);

 static int32_t tdRSmaQTaskInfoIterInit(SRSmaQTaskInfoIter *pIter, STFile *pTFile);
@ -68,8 +66,8 @@ struct SRSmaInfo {
 static SRSmaInfo *tdGetRSmaInfoByItem(SRSmaInfoItem *pItem) {
  // adapt accordingly if definition of SRSmaInfo update
  int32_t rsmaInfoHeadLen = sizeof(int64_t) + sizeof(STSchema *);
-  ASSERT(pItem->level == 1 || pItem->level == 2);
-  return (SRSmaInfo *)POINTER_SHIFT(pItem, -sizeof(SRSmaInfoItem) * (pItem->level - 1) - rsmaInfoHeadLen);
+  ASSERT(pItem->level == 0 || pItem->level == 1);
+  return (SRSmaInfo *)POINTER_SHIFT(pItem, -sizeof(SRSmaInfoItem) * pItem->level - rsmaInfoHeadLen);
 }

 struct SRSmaQTaskInfoItem {
@ -278,7 +276,7 @@ static int32_t tdSetRSmaInfoItemParams(SSma *pSma, SRSmaParam *param, SRSmaStat
    if (pItem->maxDelay > TSDB_MAX_ROLLUP_MAX_DELAY) {
      pItem->maxDelay = TSDB_MAX_ROLLUP_MAX_DELAY;
    }
-    pItem->level = (idx == 0 ? TSDB_RETENTION_L1 : TSDB_RETENTION_L2);
+    pItem->level = idx;
    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);
@ -375,20 +373,48 @@ _err:
 /**
 * @brief Check and init qTaskInfo_t, only applicable to stable with SRSmaParam currently
 *
- * @param pVnode
+ * @param pSma
 * @param pReq
 * @return int32_t
 */
-int32_t tdProcessRSmaCreate(SVnode *pVnode, SVCreateStbReq *pReq) {
-  SSma *pSma = pVnode->pSma;
+int32_t tdProcessRSmaCreate(SSma *pSma, SVCreateStbReq *pReq) {
+  SVnode *pVnode = pSma->pVnode;
  if (!pReq->rollup) {
-    smaTrace("vgId:%d, return directly since no rollup for stable %s %" PRIi64, SMA_VID(pSma), pReq->name, pReq->suid);
+    smaTrace("vgId:%d, not create rsma for stable %s %" PRIi64 " since no rollup in req", TD_VID(pVnode), pReq->name,
+             pReq->suid);
+    return TSDB_CODE_SUCCESS;
+  }
+
+  if (!VND_IS_RSMA(pVnode)) {
+    smaTrace("vgId:%d, not create rsma for stable %s %" PRIi64 " since vnd is not rsma", TD_VID(pVnode), pReq->name,
+             pReq->suid);
    return TSDB_CODE_SUCCESS;
  }

  return tdProcessRSmaCreateImpl(pSma, &pReq->rsmaParam, pReq->suid, pReq->name);
 }

+/**
+ * @brief drop cache for stb
+ *
+ * @param pSma
+ * @param pReq
+ * @return int32_t
+ */
+int32_t tdProcessRSmaDrop(SSma *pSma,  SVDropStbReq *pReq) { 
+  SVnode *pVnode = pSma->pVnode;
+  if (!VND_IS_RSMA(pVnode)) {
+    smaTrace("vgId:%d, not create rsma for stable %s %" PRIi64 " since vnd is not rsma", TD_VID(pVnode), pReq->name,
+             pReq->suid);
+    return TSDB_CODE_SUCCESS;
+  }
+
+  
+
+  smaDebug("vgId:%d, drop rsma for table %" PRIi64 " succeed", TD_VID(pVnode), pReq->suid);
+  return TSDB_CODE_SUCCESS;
+ }
+
 /**
 * @brief store suid/[uids], prefer to use array and then hash
 *
@ -1174,123 +1200,6 @@ _err:
  return TSDB_CODE_FAILED;
 }

-static void *tdRSmaPersistExec(void *param) {
-  setThreadName("rsma-task-persist");
-  SRSmaStat *pRSmaStat = param;
-  SSma      *pSma = pRSmaStat->pSma;
-
-  int8_t triggerStat = atomic_load_8(RSMA_TRIGGER_STAT(pRSmaStat));
-
-  if (TASK_TRIGGER_STAT_CANCELLED == triggerStat || TASK_TRIGGER_STAT_PAUSED == triggerStat) {
-    goto _end;
-  }
-
-  // execution
-  tdRSmaPersistExecImpl(pRSmaStat);
-
-_end:
-  if (TASK_TRIGGER_STAT_INACTIVE == atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat),
-                                                                  TASK_TRIGGER_STAT_INACTIVE,
-                                                                  TASK_TRIGGER_STAT_ACTIVE)) {
-    smaDebug("vgId:%d, rsma persist task is active again", SMA_VID(pSma));
-  } else if (TASK_TRIGGER_STAT_CANCELLED == atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat),
-                                                                          TASK_TRIGGER_STAT_CANCELLED,
-                                                                          TASK_TRIGGER_STAT_FINISHED)) {
-    smaDebug("vgId:%d, rsma persist task is cancelled", SMA_VID(pSma));
-  } else {
-    smaWarn("vgId:%d, rsma persist task in stat %" PRIi8, SMA_VID(pSma), atomic_load_8(RSMA_TRIGGER_STAT(pRSmaStat)));
-  }
-
-  atomic_store_8(RSMA_RUNNING_STAT(pRSmaStat), 0);
-  smaDebug("vgId:%d, release rsetId rsetId:%" PRIi64 " refId:%d", SMA_VID(pSma), smaMgmt.rsetId, pRSmaStat->refId);
-  tdReleaseSmaRef(smaMgmt.rsetId, pRSmaStat->refId, __func__, __LINE__);
-  taosThreadExit(NULL);
-  return NULL;
-}
-
-static void tdRSmaPersistTask(SRSmaStat *pRSmaStat) {
-  TdThreadAttr thAttr;
-  taosThreadAttrInit(&thAttr);
-  taosThreadAttrSetDetachState(&thAttr, PTHREAD_CREATE_DETACHED);
-  TdThread tid;
-
-  if (taosThreadCreate(&tid, &thAttr, tdRSmaPersistExec, pRSmaStat) != 0) {
-    if (TASK_TRIGGER_STAT_INACTIVE == atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat),
-                                                                    TASK_TRIGGER_STAT_INACTIVE,
-                                                                    TASK_TRIGGER_STAT_ACTIVE)) {
-      smaDebug("vgId:%d, persist task is active again", SMA_VID(pRSmaStat->pSma));
-    } else if (TASK_TRIGGER_STAT_CANCELLED == atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat),
-                                                                            TASK_TRIGGER_STAT_CANCELLED,
-                                                                            TASK_TRIGGER_STAT_FINISHED)) {
-      smaDebug("vgId:%d, persist task is cancelled and set finished", SMA_VID(pRSmaStat->pSma));
-    } else {
-      smaWarn("vgId:%d, persist task in abnormal stat %" PRIi8, SMA_VID(pRSmaStat->pSma),
-              atomic_load_8(RSMA_TRIGGER_STAT(pRSmaStat)));
-    }
-    atomic_store_8(RSMA_RUNNING_STAT(pRSmaStat), 0);
-    smaDebug("vgId:%d, release rsetId rsetId:%" PRIi64 " refId:%d)", SMA_VID(pRSmaStat->pSma), smaMgmt.rsetId,
-             pRSmaStat->refId);
-    tdReleaseSmaRef(smaMgmt.rsetId, pRSmaStat->refId, __func__, __LINE__);
-  }
-
-  taosThreadAttrDestroy(&thAttr);
-}
-
-/**
- * @brief trigger to persist rsma qTaskInfo
- *
- * @param param
- * @param tmrId
- */
-static void tdRSmaPersistTrigger(void *param, void *tmrId) {
-  SRSmaStat *rsmaStat = param;
-  SRSmaStat *pRSmaStat = (SRSmaStat *)taosAcquireRef(smaMgmt.rsetId, rsmaStat->refId);
-  ASSERT(0);
-  if (!pRSmaStat) {
-    smaDebug("rsma persistence task not start since already destroyed");
-    return;
-  }
-
-  int8_t tmrStat =
-      atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_ACTIVE, TASK_TRIGGER_STAT_INACTIVE);
-  switch (tmrStat) {
-    case TASK_TRIGGER_STAT_ACTIVE: {
-      atomic_store_8(RSMA_RUNNING_STAT(pRSmaStat), 1);
-      if (TASK_TRIGGER_STAT_CANCELLED != atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat),
-                                                                       TASK_TRIGGER_STAT_CANCELLED,
-                                                                       TASK_TRIGGER_STAT_FINISHED)) {
-        smaDebug("vgId:%d, rsma persistence start since active", SMA_VID(pRSmaStat->pSma));
-
-        // start persist task
-        tdRSmaPersistTask(pRSmaStat);
-
-        // taosTmrReset(tdRSmaPersistTrigger, 5000, pRSmaStat, pRSmaStat->tmrHandle,
-        //              RSMA_TMR_ID(pRSmaStat));
-      } else {
-        atomic_store_8(RSMA_RUNNING_STAT(pRSmaStat), 0);
-      }
-      return;
-    } break;
-    case TASK_TRIGGER_STAT_CANCELLED: {
-      atomic_store_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_FINISHED);
-      smaDebug("rsma persistence not start since cancelled and finished");
-    } break;
-    case TASK_TRIGGER_STAT_PAUSED: {
-      smaDebug("rsma persistence not start since paused");
-    } break;
-    case TASK_TRIGGER_STAT_INACTIVE: {
-      smaDebug("rsma persistence not start since inactive");
-    } break;
-    case TASK_TRIGGER_STAT_INIT: {
-      smaDebug("rsma persistence not start since init");
-    } break;
-    default: {
-      smaWarn("rsma persistence not start since unknown stat %" PRIi8, tmrStat);
-    } break;
-  }
-  taosReleaseRef(smaMgmt.rsetId, rsmaStat->refId);
-}
-
 /**
 * @brief trigger to get rsma result
 *
@ -1314,8 +1223,7 @@ static void tdRSmaFetchTrigger(void *param, void *tmrId) {
  int8_t rsmaTriggerStat = atomic_load_8(RSMA_TRIGGER_STAT(pStat));
  switch (rsmaTriggerStat) {
    case TASK_TRIGGER_STAT_PAUSED:
-    case TASK_TRIGGER_STAT_CANCELLED:
-    case TASK_TRIGGER_STAT_FINISHED: {
+    case TASK_TRIGGER_STAT_CANCELLED: {
      tdReleaseSmaRef(smaMgmt.rsetId, pItem->refId, __func__, __LINE__);
      smaDebug("vgId:%d, not fetch rsma level %" PRIi8 " data since stat is %" PRIi8 ", rsetId rsetId:%" PRIi64
               " refId:%d",
@ -1328,7 +1236,7 @@ static void tdRSmaFetchTrigger(void *param, void *tmrId) {

  SRSmaInfo *pRSmaInfo = tdGetRSmaInfoByItem(pItem);

-  ASSERT(pRSmaInfo->suid > 0);
+  ASSERT(pRSmaInfo->items[pItem->level].level == pItem->level);

  int8_t fetchTriggerStat =
      atomic_val_compare_exchange_8(&pItem->triggerStat, TASK_TRIGGER_STAT_ACTIVE, TASK_TRIGGER_STAT_INACTIVE);
--- a/source/dnode/vnode/src/tq/tq.c
+++ b/source/dnode/vnode/src/tq/tq.c
@ -394,7 +394,7 @@ int32_t tqProcessPollReq(STQ* pTq, SRpcMsg* pMsg, int32_t workerId) {
      } else {
        ASSERT(pHandle->fetchMeta);
        ASSERT(IS_META_MSG(pHead->msgType));
-        tqInfo("fetch meta msg, ver:%" PRId64 ", type:%d", pHead->version, pHead->msgType);
+        tqDebug("fetch meta msg, ver:%" PRId64 ", type:%d", pHead->version, pHead->msgType);
        SMqMetaRsp metaRsp = {0};
        /*metaRsp.reqOffset = pReq->reqOffset.version;*/
        /*metaRsp.rspOffset = fetchVer;*/
--- a/source/dnode/vnode/src/tsdb/tsdbCache.c
+++ b/source/dnode/vnode/src/tsdb/tsdbCache.c
@ -15,11 +15,15 @@

 #include "tsdb.h"

+typedef struct {
+  TSKEY   ts;
+  SColVal colVal;
+} SLastCol;
+
 int32_t tsdbOpenCache(STsdb *pTsdb) {
  int32_t    code = 0;
  SLRUCache *pCache = NULL;
-  // TODO: get cfg from vnode config: pTsdb->pVnode->config.lruCapacity
-  size_t cfgCapacity = 1024 * 1024;
+  size_t     cfgCapacity = pTsdb->pVnode->config.cacheLastSize * 1024 * 1024;

  pCache = taosLRUCacheInit(cfgCapacity, -1, .5);
  if (pCache == NULL) {
@ -61,8 +65,9 @@ static void deleteTableCacheLastrow(const void *key, size_t keyLen, void *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 tsdbCacheDeleteLastrow(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
  int32_t code = 0;
+
  char key[32] = {0};
  int  keyLen = 0;

@ -83,8 +88,9 @@ static int32_t tsdbCacheDeleteLastrow(SLRUCache *pCache, tb_uid_t uid, TSKEY eKe
  return code;
 }

-static int32_t tsdbCacheDeleteLast(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
+int32_t tsdbCacheDeleteLast(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
  int32_t code = 0;
+
  char key[32] = {0};
  int  keyLen = 0;

@ -92,9 +98,69 @@ static int32_t tsdbCacheDeleteLast(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey)
  getTableCacheKey(uid, 1, key, &keyLen);
  LRUHandle *h = taosLRUCacheLookup(pCache, key, keyLen);
  if (h) {
-    // clear last cache anyway, no matter where eKey ends.
-    taosLRUCacheRelease(pCache, h, true);
+    SArray *pLast = (SArray *)taosLRUCacheValue(pCache, h);
+    bool    invalidate = false;
+    int16_t nCol = taosArrayGetSize(pLast);

+    for (int16_t iCol = 0; iCol < nCol; ++iCol) {
+      SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLast, iCol);
+      if (eKey >= tTsVal->ts) {
+        invalidate = true;
+        break;
+      }
+    }
+
+    if (invalidate) {
+      taosLRUCacheRelease(pCache, h, true);
+    } else {
+      taosLRUCacheRelease(pCache, h, false);
+    }
+    // void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
+  }
+
+  return code;
+}
+
+int32_t tsdbCacheDelete(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
+  int32_t code = 0;
+  char    key[32] = {0};
+  int     keyLen = 0;
+
+  // getTableCacheKey(uid, "lr", key, &keyLen);
+  getTableCacheKey(uid, 0, key, &keyLen);
+  LRUHandle *h = taosLRUCacheLookup(pCache, key, keyLen);
+  if (h) {
+    STSRow *pRow = (STSRow *)taosLRUCacheValue(pCache, h);
+    if (pRow->ts <= eKey) {
+      taosLRUCacheRelease(pCache, h, true);
+    } else {
+      taosLRUCacheRelease(pCache, h, false);
+    }
+
+    // void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
+  }
+
+  // getTableCacheKey(uid, "l", key, &keyLen);
+  getTableCacheKey(uid, 1, key, &keyLen);
+  h = taosLRUCacheLookup(pCache, key, keyLen);
+  if (h) {
+    SArray *pLast = (SArray *)taosLRUCacheValue(pCache, h);
+    bool    invalidate = false;
+    int16_t nCol = taosArrayGetSize(pLast);
+
+    for (int16_t iCol = 0; iCol < nCol; ++iCol) {
+      SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLast, iCol);
+      if (eKey >= tTsVal->ts) {
+        invalidate = true;
+        break;
+      }
+    }
+
+    if (invalidate) {
+      taosLRUCacheRelease(pCache, h, true);
+    } else {
+      taosLRUCacheRelease(pCache, h, false);
+    }
    // void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
  }

@ -173,20 +239,59 @@ int32_t tsdbCacheInsertLastrow(SLRUCache *pCache, STsdb *pTsdb, tb_uid_t uid, ST
  return code;
 }

-int32_t tsdbCacheInsertLast(SLRUCache *pCache, tb_uid_t uid, STSRow *row) {
+int32_t tsdbCacheInsertLast(SLRUCache *pCache, tb_uid_t uid, STSRow *row, STsdb *pTsdb) {
  int32_t code = 0;
  STSRow *cacheRow = NULL;
  char    key[32] = {0};
  int     keyLen = 0;

-  ((void)(row));
+  // ((void)(row));

  // getTableCacheKey(uid, "l", key, &keyLen);
  getTableCacheKey(uid, 1, key, &keyLen);
  LRUHandle *h = taosLRUCacheLookup(pCache, key, keyLen);
  if (h) {
+    STSchema *pTSchema = metaGetTbTSchema(pTsdb->pVnode->pMeta, uid, -1);
+    TSKEY     keyTs = row->ts;
+    bool      invalidate = false;
+
+    SArray *pLast = (SArray *)taosLRUCacheValue(pCache, h);
+    int16_t nCol = taosArrayGetSize(pLast);
+    int16_t iCol = 0;
+
+    SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLast, iCol);
+    if (keyTs > tTsVal->ts) {
+      STColumn *pTColumn = &pTSchema->columns[0];
+      SColVal   tColVal = COL_VAL_VALUE(pTColumn->colId, pTColumn->type, (SValue){.ts = keyTs});
+
+      taosArraySet(pLast, iCol, &(SLastCol){.ts = keyTs, .colVal = tColVal});
+    }
+
+    for (++iCol; iCol < nCol; ++iCol) {
+      SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLast, iCol);
+      if (keyTs >= tTsVal->ts) {
+        SColVal *tColVal = &tTsVal->colVal;
+
+        SColVal colVal = {0};
+        tTSRowGetVal(row, pTSchema, iCol, &colVal);
+        if (colVal.isNone || colVal.isNull) {
+          if (keyTs == tTsVal->ts && !tColVal->isNone && !tColVal->isNull) {
+            invalidate = true;
+
+            break;
+          }
+        } else {
+          taosArraySet(pLast, iCol, &(SLastCol){.ts = keyTs, .colVal = colVal});
+        }
+      }
+    }
+
+    taosMemoryFreeClear(pTSchema);
+
+    taosLRUCacheRelease(pCache, h, invalidate);
+
    // clear last cache anyway, lazy load when get last lookup
-    taosLRUCacheRelease(pCache, h, true);
+    // taosLRUCacheRelease(pCache, h, true);
  }

  return code;
@ -361,12 +466,13 @@ static int32_t getNextRowFromFS(void *iter, TSDBROW **ppRow) {
    case SFSNEXTROW_FS:
      state->aDFileSet = state->pTsdb->fs->cState->aDFileSet;
      state->nFileSet = taosArrayGetSize(state->aDFileSet);
-      state->iFileSet = state->nFileSet - 1;
+      state->iFileSet = state->nFileSet;

      state->pBlockData = NULL;

    case SFSNEXTROW_FILESET: {
      SDFileSet *pFileSet = NULL;
+    _next_fileset:
      if (--state->iFileSet >= 0) {
        pFileSet = (SDFileSet *)taosArrayGet(state->aDFileSet, state->iFileSet);
      } else {
@ -403,6 +509,10 @@ static int32_t getNextRowFromFS(void *iter, TSDBROW **ppRow) {
      state->pBlockIdx = taosArraySearch(state->aBlockIdx, state->pBlockIdxExp, tCmprBlockIdx, TD_EQ);
      if (code) goto _err;

+      if (!state->pBlockIdx) {
+        goto _next_fileset;
+      }
+
      tMapDataReset(&state->blockMap);
      code = tsdbReadBlock(state->pDataFReader, state->pBlockIdx, &state->blockMap, NULL);
      /* code = tsdbReadBlock(state->pDataFReader, &state->blockIdx, &state->blockMap, NULL); */
@ -516,12 +626,46 @@ typedef struct SMemNextRowIter {
  SMEMNEXTROWSTATES state;
  STbData          *pMem;  // [input]
  STbDataIter       iter;  // mem buffer skip list iterator
+  // bool              iterOpened;
+  // TSDBROW          *curRow;
 } SMemNextRowIter;

 static int32_t getNextRowFromMem(void *iter, TSDBROW **ppRow) {
+  // static int32_t getNextRowFromMem(void *iter, SArray *pRowArray) {
  SMemNextRowIter *state = (SMemNextRowIter *)iter;
  int32_t          code = 0;
+  /*
+  if (!state->iterOpened) {
+    if (state->pMem != NULL) {
+      tsdbTbDataIterOpen(state->pMem, NULL, 1, &state->iter);

+      state->iterOpened = true;
+
+      TSDBROW *pMemRow = tsdbTbDataIterGet(&state->iter);
+      if (pMemRow) {
+        state->curRow = pMemRow;
+      } else {
+        return code;
+      }
+    } else {
+      return code;
+    }
+  }
+
+  taosArrayPush(pRowArray, state->curRow);
+  while (tsdbTbDataIterNext(&state->iter)) {
+    TSDBROW *row = tsdbTbDataIterGet(&state->iter);
+
+    if (TSDBROW_TS(row) < TSDBROW_TS(state->curRow)) {
+      state->curRow = row;
+      break;
+    } else {
+      taosArrayPush(pRowArray, row);
+    }
+  }
+
+  return code;
+  */
  switch (state->state) {
    case SMEMNEXTROW_ENTER: {
      if (state->pMem != NULL) {
@ -599,7 +743,7 @@ _exit:
  return code;
 }

-static bool tsdbKeyDeleted(TSDBKEY *key, SArray *pSkyline, int *iSkyline) {
+static bool tsdbKeyDeleted(TSDBKEY *key, SArray *pSkyline, int64_t *iSkyline) {
  bool deleted = false;
  while (*iSkyline > 0) {
    TSDBKEY *pItemBack = (TSDBKEY *)taosArrayGet(pSkyline, *iSkyline);
@ -626,9 +770,11 @@ static bool tsdbKeyDeleted(TSDBKEY *key, SArray *pSkyline, int *iSkyline) {
 }

 typedef int32_t (*_next_row_fn_t)(void *iter, TSDBROW **ppRow);
+// typedef int32_t (*_next_row_fn_t)(void *iter, SArray *pRowArray);
 typedef int32_t (*_next_row_clear_fn_t)(void *iter);

-typedef struct TsdbNextRowState {
+// typedef struct TsdbNextRowState {
+typedef struct {
  TSDBROW             *pRow;
  bool                 stop;
  bool                 next;
@ -637,6 +783,388 @@ typedef struct TsdbNextRowState {
  _next_row_clear_fn_t nextRowClearFn;
 } TsdbNextRowState;

+typedef struct {
+  // STsdb  *pTsdb;
+  SArray *pSkyline;
+  int64_t iSkyline;
+
+  SBlockIdx       idx;
+  SMemNextRowIter memState;
+  SMemNextRowIter imemState;
+  SFSNextRowIter  fsState;
+  TSDBROW         memRow, imemRow, fsRow;
+
+  TsdbNextRowState input[3];
+} CacheNextRowIter;
+
+static int32_t nextRowIterOpen(CacheNextRowIter *pIter, tb_uid_t uid, STsdb *pTsdb) {
+  int code = 0;
+
+  tb_uid_t suid = getTableSuidByUid(uid, pTsdb);
+
+  STbData *pMem = NULL;
+  if (pTsdb->mem) {
+    tsdbGetTbDataFromMemTable(pTsdb->mem, suid, uid, &pMem);
+  }
+
+  STbData *pIMem = NULL;
+  if (pTsdb->imem) {
+    tsdbGetTbDataFromMemTable(pTsdb->imem, suid, uid, &pIMem);
+  }
+
+  pIter->pSkyline = taosArrayInit(32, sizeof(TSDBKEY));
+
+  SDelIdx delIdx;
+
+  SDelFile *pDelFile = tsdbFSStateGetDelFile(pTsdb->fs->cState);
+  if (pDelFile) {
+    SDelFReader *pDelFReader;
+
+    code = tsdbDelFReaderOpen(&pDelFReader, pDelFile, pTsdb, NULL);
+    if (code) goto _err;
+
+    code = getTableDelIdx(pDelFReader, suid, uid, &delIdx);
+    if (code) goto _err;
+
+    code = getTableDelSkyline(pMem, pIMem, pDelFReader, &delIdx, pIter->pSkyline);
+    if (code) goto _err;
+
+    tsdbDelFReaderClose(&pDelFReader);
+  } else {
+    code = getTableDelSkyline(pMem, pIMem, NULL, NULL, pIter->pSkyline);
+    if (code) goto _err;
+  }
+
+  pIter->iSkyline = taosArrayGetSize(pIter->pSkyline) - 1;
+
+  pIter->idx = (SBlockIdx){.suid = suid, .uid = uid};
+
+  pIter->fsState.state = SFSNEXTROW_FS;
+  pIter->fsState.pTsdb = pTsdb;
+  pIter->fsState.pBlockIdxExp = &pIter->idx;
+
+  pIter->input[0] = (TsdbNextRowState){&pIter->memRow, true, false, &pIter->memState, getNextRowFromMem, NULL};
+  pIter->input[1] = (TsdbNextRowState){&pIter->imemRow, true, false, &pIter->imemState, getNextRowFromMem, NULL};
+  pIter->input[2] =
+      (TsdbNextRowState){&pIter->fsRow, false, true, &pIter->fsState, getNextRowFromFS, clearNextRowFromFS};
+
+  if (pMem) {
+    pIter->memState.pMem = pMem;
+    pIter->memState.state = SMEMNEXTROW_ENTER;
+    pIter->input[0].stop = false;
+    pIter->input[0].next = true;
+  }
+
+  if (pIMem) {
+    pIter->imemState.pMem = pIMem;
+    pIter->imemState.state = SMEMNEXTROW_ENTER;
+    pIter->input[1].stop = false;
+    pIter->input[1].next = true;
+  }
+
+  return code;
+_err:
+  return code;
+}
+
+static int32_t nextRowIterClose(CacheNextRowIter *pIter) {
+  int code = 0;
+
+  for (int i = 0; i < 3; ++i) {
+    if (pIter->input[i].nextRowClearFn) {
+      pIter->input[i].nextRowClearFn(pIter->input[i].iter);
+    }
+  }
+
+  if (pIter->pSkyline) {
+    taosArrayDestroy(pIter->pSkyline);
+  }
+
+  return code;
+_err:
+  return code;
+}
+
+// iterate next row non deleted backward ts, version (from high to low)
+static int32_t nextRowIterGet(CacheNextRowIter *pIter, TSDBROW **ppRow) {
+  int code = 0;
+
+  for (int i = 0; i < 3; ++i) {
+    if (pIter->input[i].next && !pIter->input[i].stop) {
+      code = pIter->input[i].nextRowFn(pIter->input[i].iter, &pIter->input[i].pRow);
+      if (code) goto _err;
+
+      if (pIter->input[i].pRow == NULL) {
+        pIter->input[i].stop = true;
+        pIter->input[i].next = false;
+      }
+    }
+  }
+
+  if (pIter->input[0].stop && pIter->input[1].stop && pIter->input[2].stop) {
+    *ppRow = NULL;
+    return code;
+  }
+
+  // select maxpoint(s) from mem, imem, fs
+  TSDBROW *max[3] = {0};
+  int      iMax[3] = {-1, -1, -1};
+  int      nMax = 0;
+  TSKEY    maxKey = TSKEY_MIN;
+
+  for (int i = 0; i < 3; ++i) {
+    if (!pIter->input[i].stop && pIter->input[i].pRow != NULL) {
+      TSDBKEY key = TSDBROW_KEY(pIter->input[i].pRow);
+
+      // merging & deduplicating on client side
+      if (maxKey <= key.ts) {
+        if (maxKey < key.ts) {
+          nMax = 0;
+          maxKey = key.ts;
+        }
+
+        iMax[nMax] = i;
+        max[nMax++] = pIter->input[i].pRow;
+      }
+    }
+  }
+
+  // delete detection
+  TSDBROW *merge[3] = {0};
+  int      iMerge[3] = {-1, -1, -1};
+  int      nMerge = 0;
+  for (int i = 0; i < nMax; ++i) {
+    TSDBKEY maxKey = TSDBROW_KEY(max[i]);
+
+    bool deleted = tsdbKeyDeleted(&maxKey, pIter->pSkyline, &pIter->iSkyline);
+    if (!deleted) {
+      iMerge[nMerge] = iMax[i];
+      merge[nMerge++] = max[i];
+    }
+
+    pIter->input[iMax[i]].next = deleted;
+  }
+
+  if (nMerge > 0) {
+    pIter->input[iMerge[0]].next = true;
+
+    *ppRow = merge[0];
+  } else {
+    *ppRow = NULL;
+  }
+
+  return code;
+_err:
+  return code;
+}
+
+static int32_t mergeLastRow2(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRow) {
+  int32_t code = 0;
+
+  STSchema *pTSchema = metaGetTbTSchema(pTsdb->pVnode->pMeta, uid, -1);
+  int16_t   nCol = pTSchema->numOfCols;
+  int16_t   iCol = 0;
+  int16_t   noneCol = 0;
+  bool      setNoneCol = false;
+  SArray   *pColArray = taosArrayInit(nCol, sizeof(SColVal));
+  SColVal  *pColVal = &(SColVal){0};
+
+  // tb_uid_t suid = getTableSuidByUid(uid, pTsdb);
+
+  TSKEY lastRowTs = TSKEY_MAX;
+
+  CacheNextRowIter iter = {0};
+  nextRowIterOpen(&iter, uid, pTsdb);
+
+  do {
+    TSDBROW *pRow = NULL;
+    nextRowIterGet(&iter, &pRow);
+
+    if (!pRow) {
+      break;
+    }
+
+    if (lastRowTs == TSKEY_MAX) {
+      lastRowTs = TSDBROW_TS(pRow);
+      STColumn *pTColumn = &pTSchema->columns[0];
+
+      *pColVal = COL_VAL_VALUE(pTColumn->colId, pTColumn->type, (SValue){.ts = lastRowTs});
+      if (taosArrayPush(pColArray, pColVal) == NULL) {
+        code = TSDB_CODE_OUT_OF_MEMORY;
+        goto _err;
+      }
+
+      for (iCol = 1; iCol < nCol; ++iCol) {
+        tsdbRowGetColVal(pRow, pTSchema, iCol, pColVal);
+
+        if (taosArrayPush(pColArray, pColVal) == NULL) {
+          code = TSDB_CODE_OUT_OF_MEMORY;
+          goto _err;
+        }
+
+        if (pColVal->isNone && !setNoneCol) {
+          noneCol = iCol;
+          setNoneCol = true;
+        }
+      }
+      if (!setNoneCol) {
+        // goto build the result ts row
+        break;
+      } else {
+        continue;
+      }
+    }
+
+    if ((TSDBROW_TS(pRow) < lastRowTs)) {
+      // goto build the result ts row
+      break;
+    }
+
+    // merge into pColArray
+    setNoneCol = false;
+    for (iCol = noneCol; iCol < nCol; ++iCol) {
+      // high version's column value
+      SColVal *tColVal = (SColVal *)taosArrayGet(pColArray, iCol);
+
+      tsdbRowGetColVal(pRow, pTSchema, iCol, pColVal);
+      if (tColVal->isNone && !pColVal->isNone) {
+        taosArraySet(pColArray, iCol, pColVal);
+      } else if (tColVal->isNone && pColVal->isNone && !setNoneCol) {
+        noneCol = iCol;
+        setNoneCol = true;
+      }
+    }
+  } while (setNoneCol);
+
+  // build the result ts row here
+  *dup = false;
+  if (taosArrayGetSize(pColArray) == nCol) {
+    code = tdSTSRowNew(pColArray, pTSchema, ppRow);
+    if (code) goto _err;
+  } else {
+    *ppRow = NULL;
+  }
+
+  nextRowIterClose(&iter);
+  taosArrayDestroy(pColArray);
+  taosMemoryFreeClear(pTSchema);
+  return code;
+
+_err:
+  nextRowIterClose(&iter);
+  taosArrayDestroy(pColArray);
+  taosMemoryFreeClear(pTSchema);
+  return code;
+}
+
+static int32_t mergeLast2(tb_uid_t uid, STsdb *pTsdb, SArray **ppLastArray) {
+  int32_t code = 0;
+
+  STSchema *pTSchema = metaGetTbTSchema(pTsdb->pVnode->pMeta, uid, -1);
+  int16_t   nCol = pTSchema->numOfCols;
+  int16_t   iCol = 0;
+  int16_t   noneCol = 0;
+  bool      setNoneCol = false;
+  SArray   *pColArray = taosArrayInit(nCol, sizeof(SLastCol));
+  SColVal  *pColVal = &(SColVal){0};
+
+  // tb_uid_t suid = getTableSuidByUid(uid, pTsdb);
+
+  TSKEY lastRowTs = TSKEY_MAX;
+
+  CacheNextRowIter iter = {0};
+  nextRowIterOpen(&iter, uid, pTsdb);
+
+  do {
+    TSDBROW *pRow = NULL;
+    nextRowIterGet(&iter, &pRow);
+
+    if (!pRow) {
+      break;
+    }
+
+    TSKEY rowTs = TSDBROW_TS(pRow);
+
+    if (lastRowTs == TSKEY_MAX) {
+      lastRowTs = rowTs;
+      STColumn *pTColumn = &pTSchema->columns[0];
+
+      *pColVal = COL_VAL_VALUE(pTColumn->colId, pTColumn->type, (SValue){.ts = lastRowTs});
+      if (taosArrayPush(pColArray, &(SLastCol){.ts = lastRowTs, .colVal = *pColVal}) == NULL) {
+        code = TSDB_CODE_OUT_OF_MEMORY;
+        goto _err;
+      }
+
+      for (iCol = 1; iCol < nCol; ++iCol) {
+        tsdbRowGetColVal(pRow, pTSchema, iCol, pColVal);
+
+        if (taosArrayPush(pColArray, &(SLastCol){.ts = lastRowTs, .colVal = *pColVal}) == NULL) {
+          code = TSDB_CODE_OUT_OF_MEMORY;
+          goto _err;
+        }
+
+        if ((pColVal->isNone || pColVal->isNull) && !setNoneCol) {
+          noneCol = iCol;
+          setNoneCol = true;
+        }
+      }
+      if (!setNoneCol) {
+        // goto build the result ts row
+        break;
+      } else {
+        continue;
+      }
+    }
+    /*
+    if ((TSDBROW_TS(pRow) < lastRowTs)) {
+      // goto build the result ts row
+      break;
+    }
+    */
+    // merge into pColArray
+    setNoneCol = false;
+    for (iCol = noneCol; iCol < nCol; ++iCol) {
+      // high version's column value
+      SColVal *tColVal = (SColVal *)taosArrayGet(pColArray, iCol);
+
+      tsdbRowGetColVal(pRow, pTSchema, iCol, pColVal);
+      if ((tColVal->isNone || tColVal->isNull) && (!pColVal->isNone && !pColVal->isNull)) {
+        taosArraySet(pColArray, iCol, &(SLastCol){.ts = rowTs, .colVal = *pColVal});
+        //} else if (tColVal->isNone && pColVal->isNone && !setNoneCol) {
+      } else if ((tColVal->isNone || tColVal->isNull) && (pColVal->isNone || pColVal->isNull) && !setNoneCol) {
+        noneCol = iCol;
+        setNoneCol = true;
+      }
+    }
+  } while (setNoneCol);
+
+  // build the result ts row here
+  //*dup = false;
+  if (taosArrayGetSize(pColArray) <= 0) {
+    *ppLastArray = NULL;
+    taosArrayDestroy(pColArray);
+  } else {
+    *ppLastArray = pColArray;
+  }
+  /*  if (taosArrayGetSize(pColArray) == nCol) {
+    code = tdSTSRowNew(pColArray, pTSchema, ppRow);
+    if (code) goto _err;
+  } else {
+    *ppRow = NULL;
+    }*/
+
+  nextRowIterClose(&iter);
+  // taosArrayDestroy(pColArray);
+  taosMemoryFreeClear(pTSchema);
+  return code;
+
+_err:
+  nextRowIterClose(&iter);
+  // taosArrayDestroy(pColArray);
+  taosMemoryFreeClear(pTSchema);
+  return code;
+}
+
 static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRow) {
  int32_t code = 0;
  SArray *pSkyline = NULL;
@ -682,7 +1210,7 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo
    if (code) goto _err;
  }

-  int iSkyline = taosArrayGetSize(pSkyline) - 1;
+  int64_t iSkyline = taosArrayGetSize(pSkyline) - 1;

  SBlockIdx idx = {.suid = suid, .uid = uid};

@ -719,6 +1247,7 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo
  do {
    for (int i = 0; i < 3; ++i) {
      if (input[i].next && !input[i].stop) {
+        if (input[i].pRow == NULL) {
          code = input[i].nextRowFn(input[i].iter, &input[i].pRow);
          if (code) goto _err;

@ -728,6 +1257,7 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo
          }
        }
      }
+    }

    if (input[0].stop && input[1].stop && input[2].stop) {
      break;
@ -758,14 +1288,14 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo

    // delete detection
    TSDBROW *merge[3] = {0};
-    // int      iMerge[3] = {-1, -1, -1};
+    int      iMerge[3] = {-1, -1, -1};
    int      nMerge = 0;
    for (int i = 0; i < nMax; ++i) {
      TSDBKEY maxKey = TSDBROW_KEY(max[i]);

      bool deleted = tsdbKeyDeleted(&maxKey, pSkyline, &iSkyline);
      if (!deleted) {
-        // iMerge[nMerge] = i;
+        iMerge[nMerge] = i;
        merge[nMerge++] = max[i];
      }

@ -792,7 +1322,7 @@ static int32_t mergeLastRow(tb_uid_t uid, STsdb *pTsdb, bool *dup, STSRow **ppRo
      }
    }

-  } while (*ppRow == NULL);
+  } while (1);

  for (int i = 0; i < 3; ++i) {
    if (input[i].nextRowClearFn) {
@ -819,11 +1349,6 @@ _err:
  return code;
 }

-typedef struct {
-  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;
@ -873,7 +1398,7 @@ static int32_t mergeLast(tb_uid_t uid, STsdb *pTsdb, SArray **ppLastArray) {
    if (code) goto _err;
  }

-  int iSkyline = taosArrayGetSize(pSkyline) - 1;
+  int64_t iSkyline = taosArrayGetSize(pSkyline) - 1;

  SBlockIdx idx = {.suid = suid, .uid = uid};

@ -1128,7 +1653,7 @@ int32_t tsdbCacheGetLastrowH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUH
  } else {
    STSRow *pRow = NULL;
    bool    dup = false;  // which is always false for now
-    code = mergeLastRow(uid, pTsdb, &dup, &pRow);
+    code = mergeLastRow2(uid, pTsdb, &dup, &pRow);
    // if table's empty or error, return code of -1
    if (code < 0 || pRow == NULL) {
      if (!dup && pRow) {
@ -1195,7 +1720,8 @@ int32_t tsdbCacheGetLastH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHand
    // STSRow *pRow = NULL;
    // code = mergeLast(uid, pTsdb, &pRow);
    SArray *pLastArray = NULL;
-    code = mergeLast(uid, pTsdb, &pLastArray);
+    // code = mergeLast(uid, pTsdb, &pLastArray);
+    code = mergeLast2(uid, pTsdb, &pLastArray);
    // if table's empty or error, return code of -1
    // if (code < 0 || pRow == NULL) {
    if (code < 0 || pLastArray == NULL) {
@ -1219,52 +1745,6 @@ int32_t tsdbCacheGetLastH(SLRUCache *pCache, tb_uid_t uid, STsdb *pTsdb, LRUHand
  return code;
 }

-int32_t tsdbCacheDelete(SLRUCache *pCache, tb_uid_t uid, TSKEY eKey) {
-  int32_t code = 0;
-  char    key[32] = {0};
-  int     keyLen = 0;
-
-  // getTableCacheKey(uid, "lr", key, &keyLen);
-  getTableCacheKey(uid, 0, key, &keyLen);
-  LRUHandle *h = taosLRUCacheLookup(pCache, key, keyLen);
-  if (h) {
-    STSRow *pRow = (STSRow *)taosLRUCacheValue(pCache, h);
-    if (pRow->ts <= eKey) {
-      taosLRUCacheRelease(pCache, h, true);
-    } else {
-      taosLRUCacheRelease(pCache, h, false);
-    }
-
-    // void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
-  }
-
-  // getTableCacheKey(uid, "l", key, &keyLen);
-  getTableCacheKey(uid, 1, key, &keyLen);
-  h = taosLRUCacheLookup(pCache, key, keyLen);
-  if (h) {
-    SArray *pLast = (SArray *)taosLRUCacheValue(pCache, h);
-    bool    invalidate = false;
-    int16_t nCol = taosArrayGetSize(pLast);
-
-    for (int16_t iCol = 0; iCol < nCol; ++iCol) {
-      SLastCol *tTsVal = (SLastCol *)taosArrayGet(pLast, iCol);
-      if (eKey >= tTsVal->ts) {
-        invalidate = true;
-        break;
-      }
-    }
-
-    if (invalidate) {
-      taosLRUCacheRelease(pCache, h, true);
-    } else {
-      taosLRUCacheRelease(pCache, h, false);
-    }
-    // void taosLRUCacheErase(SLRUCache * cache, const void *key, size_t keyLen);
-  }
-
-  return code;
-}
-
 int32_t tsdbCacheRelease(SLRUCache *pCache, LRUHandle *h) {
  int32_t code = 0;

@ -1272,3 +1752,9 @@ int32_t tsdbCacheRelease(SLRUCache *pCache, LRUHandle *h) {

  return code;
 }
+
+void tsdbCacheSetCapacity(SVnode *pVnode, size_t capacity) {
+  taosLRUCacheSetCapacity(pVnode->pTsdb->lruCache, capacity);
+}
+
+size_t tsdbCacheGetCapacity(SVnode *pVnode) { return taosLRUCacheGetCapacity(pVnode->pTsdb->lruCache); }
--- a/source/dnode/vnode/src/tsdb/tsdbFS.c
+++ b/source/dnode/vnode/src/tsdb/tsdbFS.c
@ -688,6 +688,14 @@ _exit:
  return code;
 }

+void tsdbFSStateDeleteDFileSet(STsdbFSState *pState, int32_t fid) {
+  int32_t idx;
+
+  idx = taosArraySearchIdx(pState->aDFileSet, &(SDFileSet){.fid = fid}, tDFileSetCmprFn, TD_EQ);
+  ASSERT(idx >= 0);
+  taosArrayRemove(pState->aDFileSet, idx);
+}
+
 SDelFile *tsdbFSStateGetDelFile(STsdbFSState *pState) { return pState->pDelFile; }

 SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid) {
--- a/source/dnode/vnode/src/tsdb/tsdbMemTable.c
+++ b/source/dnode/vnode/src/tsdb/tsdbMemTable.c
@ -181,8 +181,12 @@ int32_t tsdbDeleteTableData(STsdb *pTsdb, int64_t version, tb_uid_t suid, tb_uid
  pMemTable->maxVersion = TMAX(pMemTable->maxVersion, version);
  pMemTable->nDel++;

-  if (tsdbKeyCmprFn(&lastKey, &pTbData->maxKey) >= 0) {
-    tsdbCacheDelete(pTsdb->lruCache, pTbData->uid, eKey);
+  if (TSDB_CACHE_LAST_ROW(pMemTable->pTsdb->pVnode->config) && tsdbKeyCmprFn(&lastKey, &pTbData->maxKey) >= 0) {
+    tsdbCacheDeleteLastrow(pTsdb->lruCache, pTbData->uid, eKey);
+  }
+
+  if (TSDB_CACHE_LAST(pMemTable->pTsdb->pVnode->config)) {
+    tsdbCacheDeleteLast(pTsdb->lruCache, pTbData->uid, eKey);
  }

  tsdbError("vgId:%d, delete data from table suid:%" PRId64 " uid:%" PRId64 " skey:%" PRId64 " eKey:%" PRId64
@ -556,12 +560,14 @@ static int32_t tsdbInsertTableDataImpl(SMemTable *pMemTable, STbData *pTbData, i
      pTbData->maxKey = key.ts;
    }

-    if (pLastRow != NULL) {
+    if (TSDB_CACHE_LAST_ROW(pMemTable->pTsdb->pVnode->config) && pLastRow != NULL) {
      tsdbCacheInsertLastrow(pMemTable->pTsdb->lruCache, pMemTable->pTsdb, pTbData->uid, pLastRow, true);
    }
  }

-  tsdbCacheInsertLast(pMemTable->pTsdb->lruCache, pTbData->uid, pLastRow);
+  if (TSDB_CACHE_LAST(pMemTable->pTsdb->pVnode->config)) {
+    tsdbCacheInsertLast(pMemTable->pTsdb->lruCache, pTbData->uid, pLastRow, pMemTable->pTsdb);
+  }

  pTbData->minVersion = TMIN(pTbData->minVersion, version);
  pTbData->maxVersion = TMAX(pTbData->maxVersion, version);
--- a/source/dnode/vnode/src/tsdb/tsdbRead.c
+++ b/source/dnode/vnode/src/tsdb/tsdbRead.c
@ -323,6 +323,9 @@ static bool filesetIteratorNext(SFilesetIter* pIter, STsdbReader* pReader) {

    if ((asc && (win.ekey < pReader->window.skey)) || ((!asc) && (win.skey > pReader->window.ekey))) {
      pIter->index += step;
+      if ((asc && pIter->index >= pIter->numOfFiles) || ((!asc) && pIter->index < 0)) {
+        return false;
+      }
      continue;
    }

--- a/source/dnode/vnode/src/tsdb/tsdbReaderWriter.c
+++ b/source/dnode/vnode/src/tsdb/tsdbReaderWriter.c
@ -1913,3 +1913,114 @@ _err:
  taosArrayDestroy(aBlockCol);
  return code;
 }
+
+int32_t tsdbDFileSetCopy(STsdb *pTsdb, SDFileSet *pSetFrom, SDFileSet *pSetTo) {
+  int32_t   code = 0;
+  int64_t   n;
+  int64_t   size;
+  TdFilePtr pOutFD = NULL;  // TODO
+  TdFilePtr PInFD = NULL;   // TODO
+  char      fNameFrom[TSDB_FILENAME_LEN];
+  char      fNameTo[TSDB_FILENAME_LEN];
+
+  // head
+  tsdbDataFileName(pTsdb, pSetFrom, TSDB_HEAD_FILE, fNameFrom);
+  tsdbDataFileName(pTsdb, pSetTo, TSDB_HEAD_FILE, fNameTo);
+
+  pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
+  if (pOutFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  PInFD = taosOpenFile(fNameFrom, TD_FILE_READ);
+  if (PInFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fHead.size);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+  taosCloseFile(&pOutFD);
+  taosCloseFile(&PInFD);
+
+  // data
+  tsdbDataFileName(pTsdb, pSetFrom, TSDB_DATA_FILE, fNameFrom);
+  tsdbDataFileName(pTsdb, pSetTo, TSDB_DATA_FILE, fNameTo);
+
+  pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
+  if (pOutFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  PInFD = taosOpenFile(fNameFrom, TD_FILE_READ);
+  if (PInFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fData.size);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+  taosCloseFile(&pOutFD);
+  taosCloseFile(&PInFD);
+
+  // last
+  tsdbDataFileName(pTsdb, pSetFrom, TSDB_LAST_FILE, fNameFrom);
+  tsdbDataFileName(pTsdb, pSetTo, TSDB_LAST_FILE, fNameTo);
+  pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
+  if (pOutFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  PInFD = taosOpenFile(fNameFrom, TD_FILE_READ);
+  if (PInFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fLast.size);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+  taosCloseFile(&pOutFD);
+  taosCloseFile(&PInFD);
+
+  // sma
+  tsdbDataFileName(pTsdb, pSetFrom, TSDB_SMA_FILE, fNameFrom);
+  tsdbDataFileName(pTsdb, pSetTo, TSDB_SMA_FILE, fNameTo);
+
+  pOutFD = taosOpenFile(fNameTo, TD_FILE_WRITE | TD_FILE_CREATE | TD_FILE_TRUNC);
+  if (pOutFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  PInFD = taosOpenFile(fNameFrom, TD_FILE_READ);
+  if (PInFD == NULL) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+
+  n = taosFSendFile(pOutFD, PInFD, 0, pSetFrom->fSma.size);
+  if (n < 0) {
+    code = TAOS_SYSTEM_ERROR(errno);
+    goto _err;
+  }
+  taosCloseFile(&pOutFD);
+  taosCloseFile(&PInFD);
+
+  return code;
+
+_err:
+  tsdbError("vgId:%d tsdb DFileSet copy failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
+  return code;
+}
--- a/source/dnode/vnode/src/tsdb/tsdbRetention.c
+++ b/source/dnode/vnode/src/tsdb/tsdbRetention.c
@ -15,19 +15,80 @@

 #include "tsdb.h"

+static int32_t tsdbDoRetentionImpl(STsdb *pTsdb, int64_t now, int8_t try, int8_t *canDo) {
+  int32_t       code = 0;
+  STsdbFSState *pState;
+
+  if (try) {
+    pState = pTsdb->fs->cState;
+    *canDo = 0;
+  } else {
+    pState = pTsdb->fs->nState;
+  }
+
+  for (int32_t iSet = 0; iSet < taosArrayGetSize(pState->aDFileSet); iSet++) {
+    SDFileSet *pDFileSet = (SDFileSet *)taosArrayGet(pState->aDFileSet, iSet);
+    int32_t    expLevel = tsdbFidLevel(pDFileSet->fid, &pTsdb->keepCfg, now);
+    SDiskID    did;
+
+    // check
+    if (expLevel == pDFileSet->diskId.id) continue;
+
+    // delete or move
+    if (expLevel < 0) {
+      if (try) {
+        *canDo = 1;
+      } else {
+        tsdbFSStateDeleteDFileSet(pState, pDFileSet->fid);
+        iSet--;
+      }
+    } else {
+      // alloc
+      if (tfsAllocDisk(pTsdb->pVnode->pTfs, expLevel, &did) < 0) {
+        code = terrno;
+        goto _exit;
+      }
+
+      if (did.level == pDFileSet->diskId.level) continue;
+
+      if (try) {
+        *canDo = 1;
+      } else {
+        // copy the file to new disk
+
+        SDFileSet nDFileSet = *pDFileSet;
+        nDFileSet.diskId = did;
+
+        tfsMkdirRecurAt(pTsdb->pVnode->pTfs, pTsdb->path, did);
+
+        code = tsdbDFileSetCopy(pTsdb, pDFileSet, &nDFileSet);
+        if (code) goto _exit;
+
+        code = tsdbFSStateUpsertDFileSet(pState, &nDFileSet);
+        if (code) goto _exit;
+      }
+    }
+  }
+
+_exit:
+  return code;
+}
+
 int32_t tsdbDoRetention(STsdb *pTsdb, int64_t now) {
  int32_t code = 0;
+  int8_t  canDo;
+
+  // try
+  tsdbDoRetentionImpl(pTsdb, now, 1, &canDo);
+  if (!canDo) goto _exit;

  // begin
  code = tsdbFSBegin(pTsdb->fs);
  if (code) goto _err;

  // do retention
-  for (int32_t iSet = 0; iSet < taosArrayGetSize(pTsdb->fs->nState->aDFileSet); iSet++) {
-    SDFileSet *pDFileSet = (SDFileSet *)taosArrayGet(pTsdb->fs->nState->aDFileSet, iSet);
-
-    // TODO
-  }
+  code = tsdbDoRetentionImpl(pTsdb, now, 0, NULL);
+  if (code) goto _err;

  // commit
  code = tsdbFSCommit(pTsdb->fs);
@ -38,5 +99,6 @@ _exit:

 _err:
  tsdbError("vgId:%d tsdb do retention failed since %s", TD_VID(pTsdb->pVnode), tstrerror(code));
+  tsdbFSRollback(pTsdb->fs);
  return code;
 }
--- a/source/dnode/vnode/src/tsdb/tsdbSnapshot.c
+++ b/source/dnode/vnode/src/tsdb/tsdbSnapshot.c
@ -312,6 +312,9 @@ struct STsdbSnapWriter {
  // config
  int32_t minutes;
  int8_t  precision;
+  int32_t minRow;
+  int32_t maxRow;
+  int8_t  cmprAlg;

  // for data file
  int32_t       fid;
@ -321,14 +324,18 @@ struct STsdbSnapWriter {
  SBlockIdx*    pBlockIdx;
  SMapData      mBlock;
  int32_t       iBlock;
+  SBlock*       pBlock;
+  SBlock        block;
  SBlockData    blockData;
  int32_t       iRow;

  SDataFWriter* pDataFWriter;
  SArray*       aBlockIdxN;
+  SBlockIdx*    pBlockIdxN;
  SBlockIdx     blockIdx;
  SMapData      mBlockN;
-  SBlock        block;
+  SBlock*       pBlockN;
+  SBlock        blockN;
  SBlockData    nBlockData;

  // for del file
@ -394,11 +401,112 @@ _err:
  return code;
 }

+static int32_t tsdbSnapWriteTableDataEnd(STsdbSnapWriter* pWrite) {
+  int32_t code = 0;
+  // TODO
+  return code;
+}
+
+static int32_t tsdbSnapWriteTableData(STsdbSnapWriter* pWriter, uint8_t* pData, uint32_t nData) {
+  int32_t code = 0;
+  TABLEID id = {0};  // TODO
+
+  // skip
+  while (pWriter->pBlockIdx && tTABLEIDCmprFn(&id, pWriter->pBlockIdx) < 0) {
+    code = tsdbSnapWriteTableDataEnd(pWriter);
+    if (code) goto _err;
+
+    pWriter->iBlockIdx++;
+    if (pWriter->iBlockIdx < taosArrayGetSize(pWriter->aBlockIdx)) {
+      pWriter->pBlockIdx = (SBlockIdx*)taosArrayGet(pWriter->aBlockIdx, pWriter->iBlockIdx);
+    } else {
+      pWriter->pBlockIdx = NULL;
+    }
+  }
+
+  // new or merge
+  if (pWriter->pBlockIdx == NULL || tTABLEIDCmprFn(&id, pWriter->pBlockIdx) < 0) {
+    int32_t c;
+
+    if (pWriter->pBlockIdxN && ((c = tTABLEIDCmprFn(&id, pWriter->pBlockIdxN)) != 0)) {
+      ASSERT(c > 0);
+
+      code = tsdbSnapWriteTableDataEnd(pWriter);
+      if (code) goto _err;
+    }
+
+    if (pWriter->pBlockIdxN == NULL) {
+      pWriter->pBlockIdx = &pWriter->blockIdx;
+      pWriter->pBlockIdx->suid = id.suid;
+      pWriter->pBlockIdx->uid = id.uid;
+    }
+
+    // loop to write the data
+    TSDBROW*    pRow = NULL;        // todo
+    int32_t     nRow = 0;           // todo
+    SBlockData* pBlockData = NULL;  // todo
+    for (int32_t iRow = 0; iRow < nRow; iRow++) {
+      code = tBlockDataAppendRow(&pWriter->nBlockData, &tsdbRowFromBlockData(pBlockData, iRow), NULL);
+      if (code) goto _err;
+
+      if (pWriter->nBlockData.nRow > pWriter->maxRow * 4 / 5) {
+        code = tsdbWriteBlockData(pWriter->pDataFWriter, &pWriter->nBlockData, NULL, NULL, pWriter->pBlockIdxN,
+                                  pWriter->pBlockN, pWriter->cmprAlg);
+        if (code) goto _err;
+      }
+    }
+  } else {
+    // skip
+    while (true) {
+      if (pWriter->pBlock == NULL) break;
+      if (pWriter->pBlock->last) break;
+      if (tBlockCmprFn(&(SBlock){.minKey = {0}, .maxKey = {0}}, pWriter->pBlock) >= 0) break;
+
+      code = tMapDataPutItem(&pWriter->mBlockN, pWriter->pBlock, tPutBlock);
+      if (code) goto _err;
+    }
+
+    if (pWriter->pBlock) {
+      if (pWriter->pBlock->last) {
+        // load the last block and merge with the data (todo)
+      } else {
+        int32_t c = tBlockCmprFn(&(SBlock){0 /*TODO*/}, pWriter->pBlock);
+
+        if (c > 0) {
+          // commit until pWriter->pBlock (todo)
+        } else {
+          // load the block and merge with the data (todo)
+        }
+      }
+    } else {
+      int32_t     nRow = 0;
+      SBlockData* pBlockData = NULL;
+
+      for (int32_t iRow = 0; iRow < nRow; iRow++) {
+        code = tBlockDataAppendRow(&pWriter->nBlockData, &tsdbRowFromBlockData(pBlockData, iRow), NULL);
+        if (code) goto _err;
+
+        if (pWriter->nBlockData.nRow >= pWriter->maxRow * 4 / 5) {
+          code = tsdbWriteBlockData(pWriter->pDataFWriter, &pWriter->nBlockData, NULL, NULL, pWriter->pBlockIdxN,
+                                    pWriter->pBlockN, pWriter->cmprAlg);
+          if (code) goto _err;
+
+          tBlockDataClearData(&pWriter->nBlockData);
+        }
+      }
+    }
+  }
+
+  return code;
+
+_err:
+  tsdbError("vgId:%d tsdb snapshot write table data failed since %s", TD_VID(pWriter->pTsdb->pVnode), tstrerror(code));
+  return code;
+}
+
 static int32_t tsdbSnapWriteData(STsdbSnapWriter* pWriter, uint8_t* pData, uint32_t nData) {
  int32_t code = 0;
  STsdb*  pTsdb = pWriter->pTsdb;
-  int64_t suid = 0;  // todo
-  int64_t uid = 0;   // todo
  int64_t skey;  // todo
  int64_t ekey;  // todo

@ -440,48 +548,9 @@ static int32_t tsdbSnapWriteData(STsdbSnapWriter* pWriter, uint8_t* pData, uint3
    taosArrayClear(pWriter->aBlockIdxN);
  }

-  // process
-  TABLEID id = {0};    // TODO
-  TSKEY   minKey = 0;  // TODO
-  TSKEY   maxKey = 0;  // TODO
-
-  while (true) {
-    if (pWriter->pBlockIdx) {
-      int32_t c = tTABLEIDCmprFn(&id, pWriter->pBlockIdx);
-
-      if (c == 0) {
-      } else if (c < 0) {
-        // keep merge
-      } else {
-        // code = tsdbSnapWriteTableDataEnd(pWriter);
+  code = tsdbSnapWriteTableData(pWriter, pData, nData);
  if (code) goto _err;

-        pWriter->iBlockIdx++;
-        if (pWriter->iBlockIdx < taosArrayGetSize(pWriter->aBlockIdx)) {
-          pWriter->pBlockIdx = (SBlockIdx*)taosArrayGet(pWriter->aBlockIdx, pWriter->iBlockIdx);
-        } else {
-          pWriter->pBlockIdx = NULL;
-        }
-
-        if (pWriter->pBlockIdx) {
-          code = tsdbReadBlock(pWriter->pDataFReader, pWriter->pBlockIdx, &pWriter->mBlock, NULL);
-          if (code) goto _err;
-        }
-      }
-    } else {
-      int32_t c = tTABLEIDCmprFn(&id, &pWriter->blockIdx);
-
-      if (c == 0) {
-        // merge commit the block data
-      } else if (c > 0) {
-        // code = tsdbSnapWriteTableDataEnd(pWriter);
-        if (code) goto _err;
-      } else {
-        ASSERT(0);
-      }
-    }
-  }
-
  return code;

 _err:
--- a/source/dnode/vnode/src/tsdb/tsdbUtil.c
+++ b/source/dnode/vnode/src/tsdb/tsdbUtil.c
@ -465,17 +465,37 @@ void tsdbFidKeyRange(int32_t fid, int32_t minutes, int8_t precision, TSKEY *minK
  *maxKey = *minKey + minutes * tsTickPerMin[precision] - 1;
 }

-// int tsdFidLevel(int fid, TSKEY now, minute) {
-//   if (fid >= pRtn->maxFid) {
-//     return 0;
-//   } else if (fid >= pRtn->midFid) {
-//     return 1;
-//   } else if (fid >= pRtn->minFid) {
-//     return 2;
-//   } else {
-//     return -1;
-//   }
-// }
+int32_t tsdbFidLevel(int32_t fid, STsdbKeepCfg *pKeepCfg, int64_t now) {
+  int32_t aFid[3];
+  TSKEY   key;
+
+  if (pKeepCfg->precision == TSDB_TIME_PRECISION_MILLI) {
+    now = now * 1000;
+  } else if (pKeepCfg->precision == TSDB_TIME_PRECISION_MICRO) {
+    now = now * 1000000l;
+  } else if (pKeepCfg->precision == TSDB_TIME_PRECISION_NANO) {
+    now = now * 1000000000l;
+  } else {
+    ASSERT(0);
+  }
+
+  key = now - pKeepCfg->keep0 * tsTickPerMin[pKeepCfg->precision];
+  aFid[0] = tsdbKeyFid(key, pKeepCfg->days, pKeepCfg->precision);
+  key = now - pKeepCfg->keep1 * tsTickPerMin[pKeepCfg->precision];
+  aFid[1] = tsdbKeyFid(key, pKeepCfg->days, pKeepCfg->precision);
+  key = now - pKeepCfg->keep2 * tsTickPerMin[pKeepCfg->precision];
+  aFid[2] = tsdbKeyFid(key, pKeepCfg->days, pKeepCfg->precision);
+
+  if (fid >= aFid[0]) {
+    return 0;
+  } else if (fid >= aFid[1]) {
+    return 1;
+  } else if (fid >= aFid[2]) {
+    return 2;
+  } else {
+    return -1;
+  }
+}

 // TSDBROW ======================================================
 void tsdbRowGetColVal(TSDBROW *pRow, STSchema *pTSchema, int32_t iCol, SColVal *pColVal) {
--- a/source/dnode/vnode/src/vnd/vnodeCfg.c
+++ b/source/dnode/vnode/src/vnd/vnodeCfg.c
@ -15,12 +15,13 @@

 #include "vnd.h"

-const SVnodeCfg vnodeCfgDefault = {
-    .vgId = -1,
+const SVnodeCfg vnodeCfgDefault = {.vgId = -1,
                                   .dbname = "",
                                   .dbId = 0,
                                   .szPage = 4096,
                                   .szCache = 256,
+                                   .cacheLast = 3,
+                                   .cacheLastSize = 8,
                                   .szBuf = 96 * 1024 * 1024,
                                   .isHeap = false,
                                   .isWeak = 0,
@ -35,7 +36,15 @@ const SVnodeCfg vnodeCfgDefault = {
                                               .keep0 = 5256000,
                                               .keep1 = 5256000},
                                   .walCfg =
-        {.vgId = -1, .fsyncPeriod = 0, .retentionPeriod = 0, .rollPeriod = 0, .segSize = 0, .level = TAOS_WAL_WRITE},
+                                       {
+                                           .vgId = -1,
+                                           .fsyncPeriod = 0,
+                                           .retentionPeriod = -1,
+                                           .rollPeriod = -1,
+                                           .segSize = -1,
+                                           .retentionSize = -1,
+                                           .level = TAOS_WAL_WRITE,
+                                       },
                                   .hashBegin = 0,
                                   .hashEnd = 0,
                                   .hashMethod = 0};
@ -53,6 +62,8 @@ int vnodeEncodeConfig(const void *pObj, SJson *pJson) {
  if (tjsonAddIntegerToObject(pJson, "dbId", pCfg->dbId) < 0) return -1;
  if (tjsonAddIntegerToObject(pJson, "szPage", pCfg->szPage) < 0) return -1;
  if (tjsonAddIntegerToObject(pJson, "szCache", pCfg->szCache) < 0) return -1;
+  if (tjsonAddIntegerToObject(pJson, "cacheLast", pCfg->cacheLast) < 0) return -1;
+  if (tjsonAddIntegerToObject(pJson, "cacheLastSize", pCfg->cacheLastSize) < 0) return -1;
  if (tjsonAddIntegerToObject(pJson, "szBuf", pCfg->szBuf) < 0) return -1;
  if (tjsonAddIntegerToObject(pJson, "isHeap", pCfg->isHeap) < 0) return -1;
  if (tjsonAddIntegerToObject(pJson, "isWeak", pCfg->isWeak) < 0) return -1;
@ -126,6 +137,10 @@ int vnodeDecodeConfig(const SJson *pJson, void *pObj) {
  if (code < 0) return -1;
  tjsonGetNumberValue(pJson, "szCache", pCfg->szCache, code);
  if (code < 0) return -1;
+  tjsonGetNumberValue(pJson, "cacheLast", pCfg->cacheLast, code);
+  if (code < 0) return -1;
+  tjsonGetNumberValue(pJson, "cacheLastSize", pCfg->cacheLastSize, code);
+  if (code < 0) return -1;
  tjsonGetNumberValue(pJson, "szBuf", pCfg->szBuf, code);
  if (code < 0) return -1;
  tjsonGetNumberValue(pJson, "isHeap", pCfg->isHeap, code);
--- a/source/dnode/vnode/src/vnd/vnodeCommit.c
+++ b/source/dnode/vnode/src/vnd/vnodeCommit.c
@ -230,6 +230,7 @@ int vnodeCommit(SVnode *pVnode) {
    ASSERT(0);
    return -1;
  }
+  walBeginSnapshot(pVnode->pWal, pVnode->state.applied);

  // preCommit
  smaPreCommit(pVnode->pSma);
@ -278,6 +279,7 @@ int vnodeCommit(SVnode *pVnode) {
  smaPostCommit(pVnode->pSma);

  // apply the commit (TODO)
+  walEndSnapshot(pVnode->pWal);
  vnodeBufPoolReset(pVnode->onCommit);
  pVnode->onCommit->next = pVnode->pPool;
  pVnode->pPool = pVnode->onCommit;
--- a/source/dnode/vnode/src/vnd/vnodeOpen.c
+++ b/source/dnode/vnode/src/vnd/vnodeOpen.c
@ -28,7 +28,7 @@ int vnodeCreate(const char *path, SVnodeCfg *pCfg, STfs *pTfs) {
  }

  // create vnode env
-  if (tfsMkdir(pTfs, path) < 0) {
+  if (tfsMkdirAt(pTfs, path, (SDiskID){0}) < 0) {
    vError("vgId:%d, failed to create vnode since: %s", pCfg->vgId, tstrerror(terrno));
    return -1;
  }
@ -117,6 +117,13 @@ SVnode *vnodeOpen(const char *path, STfs *pTfs, SMsgCb msgCb) {
  // open wal
  sprintf(tdir, "%s%s%s", dir, TD_DIRSEP, VNODE_WAL_DIR);
  taosRealPath(tdir, NULL, sizeof(tdir));
+
+// for test tsdb snapshot
+#if 0
+  pVnode->config.walCfg.segSize = 200;
+  pVnode->config.walCfg.retentionSize = 2000;
+#endif
+
  pVnode->pWal = walOpen(tdir, &(pVnode->config.walCfg));
  if (pVnode->pWal == NULL) {
    vError("vgId:%d, failed to open vnode wal since %s", TD_VID(pVnode), tstrerror(terrno));
--- a/source/dnode/vnode/src/vnd/vnodeSvr.c
+++ b/source/dnode/vnode/src/vnd/vnodeSvr.c
@ -24,8 +24,10 @@ static int32_t vnodeProcessDropTbReq(SVnode *pVnode, int64_t version, void *pReq
 static int32_t vnodeProcessSubmitReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
 static int32_t vnodeProcessCreateTSmaReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
 static int32_t vnodeProcessAlterConfirmReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
-static int32_t vnodeProcessAlterHasnRangeReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
+static int32_t vnodeProcessAlterHashRangeReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
+static int32_t vnodeProcessAlterConfigReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
 static int32_t vnodeProcessDropTtlTbReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
+static int32_t vnodeProcessTrimReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);
 static int32_t vnodeProcessDeleteReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp);

 int32_t vnodePreProcessWriteMsg(SVnode *pVnode, SRpcMsg *pMsg) {
@ -172,9 +174,12 @@ int32_t vnodeProcessWriteMsg(SVnode *pVnode, SRpcMsg *pMsg, int64_t version, SRp
    case TDMT_VND_DROP_TTL_TABLE:
      if (vnodeProcessDropTtlTbReq(pVnode, version, pReq, len, pRsp) < 0) goto _err;
      break;
-    case TDMT_VND_CREATE_SMA: {
+    case TDMT_VND_TRIM:
+      if (vnodeProcessTrimReq(pVnode, version, pReq, len, pRsp) < 0) goto _err;
+      break;
+    case TDMT_VND_CREATE_SMA:
      if (vnodeProcessCreateTSmaReq(pVnode, version, pReq, len, pRsp) < 0) goto _err;
-    } break;
+      break;
    /* TSDB */
    case TDMT_VND_SUBMIT:
      if (vnodeProcessSubmitReq(pVnode, version, pMsg->pCont, pMsg->contLen, pRsp) < 0) goto _err;
@ -215,9 +220,10 @@ int32_t vnodeProcessWriteMsg(SVnode *pVnode, SRpcMsg *pMsg, int64_t version, SRp
      vnodeProcessAlterConfirmReq(pVnode, version, pReq, len, pRsp);
      break;
    case TDMT_VND_ALTER_HASHRANGE:
-      vnodeProcessAlterHasnRangeReq(pVnode, version, pReq, len, pRsp);
+      vnodeProcessAlterHashRangeReq(pVnode, version, pReq, len, pRsp);
      break;
    case TDMT_VND_ALTER_CONFIG:
+      vnodeProcessAlterConfigReq(pVnode, version, pReq, len, pRsp);
      break;
    case TDMT_VND_COMMIT:
      goto _do_commit;
@ -345,13 +351,38 @@ void vnodeUpdateMetaRsp(SVnode *pVnode, STableMetaRsp *pMetaRsp) {
  pMetaRsp->precision = pVnode->config.tsdbCfg.precision;
 }

+static int32_t vnodeProcessTrimReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
+  int32_t     code = 0;
+  SVTrimDbReq trimReq = {0};
+
+  vInfo("vgId:%d, trim vnode request will be processed, time:%d", pVnode->config.vgId, trimReq.timestamp);
+
+  // decode
+  if (tDeserializeSVTrimDbReq(pReq, len, &trimReq) != 0) {
+    code = TSDB_CODE_INVALID_MSG;
+    goto _exit;
+  }
+
+  // process
+  code = tsdbDoRetention(pVnode->pTsdb, trimReq.timestamp);
+  if (code) goto _exit;
+
+_exit:
+  return code;
+}
+
 static int32_t vnodeProcessDropTtlTbReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
  SArray *tbUids = taosArrayInit(8, sizeof(int64_t));
  if (tbUids == NULL) return TSDB_CODE_OUT_OF_MEMORY;

-  int32_t t = ntohl(*(int32_t *)pReq);
-  vDebug("rec ttl time:%d", t);
-  int32_t ret = metaTtlDropTable(pVnode->pMeta, t, tbUids);
+  SVDropTtlTableReq ttlReq = {0};
+  if (tDeserializeSVDropTtlTableReq(pReq, len, &ttlReq) != 0) {
+    terrno = TSDB_CODE_INVALID_MSG;
+    goto end;
+  }
+
+  vInfo("vgId:%d, drop ttl table req will be processed, time:%d", pVnode->config.vgId, ttlReq.timestamp);
+  int32_t ret = metaTtlDropTable(pVnode->pMeta, ttlReq.timestamp, tbUids);
  if (ret != 0) {
    goto end;
  }
@ -386,7 +417,7 @@ static int32_t vnodeProcessCreateStbReq(SVnode *pVnode, int64_t version, void *p
    goto _err;
  }

-  if (tdProcessRSmaCreate(pVnode, &req) < 0) {
+  if (tdProcessRSmaCreate(pVnode->pSma, &req) < 0) {
    pRsp->code = terrno;
    goto _err;
  }
@ -542,6 +573,11 @@ static int32_t vnodeProcessDropStbReq(SVnode *pVnode, int64_t version, void *pRe
    goto _exit;
  }

+  if (tdProcessRSmaDrop(pVnode->pSma, &req) < 0) {
+    rcode = terrno;
+    goto _exit;
+  }
+
  // return rsp
 _exit:
  pRsp->code = rcode;
@ -886,7 +922,7 @@ static int32_t vnodeProcessAlterConfirmReq(SVnode *pVnode, int64_t version, void
  return 0;
 }

-static int32_t vnodeProcessAlterHasnRangeReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
+static int32_t vnodeProcessAlterHashRangeReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
  vInfo("vgId:%d, alter hashrange msg will be processed", TD_VID(pVnode));

  // todo
@ -896,6 +932,23 @@ static int32_t vnodeProcessAlterHasnRangeReq(SVnode *pVnode, int64_t version, vo
  return 0;
 }

+static int32_t vnodeProcessAlterConfigReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
+  SAlterVnodeReq alterReq = {0};
+  if (tDeserializeSAlterVnodeReq(pReq, len, &alterReq) != 0) {
+    terrno = TSDB_CODE_INVALID_MSG;
+    return TSDB_CODE_INVALID_MSG;
+  }
+
+  vInfo("vgId:%d, start to alter vnode config, cacheLast:%d cacheLastSize:%d", TD_VID(pVnode), alterReq.cacheLast,
+        alterReq.cacheLastSize);
+  if (pVnode->config.cacheLastSize != alterReq.cacheLastSize) {
+    pVnode->config.cacheLastSize = alterReq.cacheLastSize;
+    // TODO: save config
+    tsdbCacheSetCapacity(pVnode, (size_t)pVnode->config.cacheLastSize * 1024 * 1024);
+  }
+  return 0;
+}
+
 static int32_t vnodeProcessDeleteReq(SVnode *pVnode, int64_t version, void *pReq, int32_t len, SRpcMsg *pRsp) {
  int32_t     code = 0;
  SDecoder   *pCoder = &(SDecoder){0};
--- a/source/libs/catalog/inc/catalogInt.h
+++ b/source/libs/catalog/inc/catalogInt.h
@ -480,37 +480,35 @@ typedef struct SCtgOperation {

 #define TD_RWLATCH_WRITE_FLAG_COPY 0x40000000

-#define CTG_IS_LOCKED(_lock) atomic_load_32((_lock))
-
 #define CTG_LOCK(type, _lock) do {   \
  if (CTG_READ == (type)) {          \
-    assert(atomic_load_32((_lock)) >= 0);  \
-    CTG_LOCK_DEBUG("CTG RLOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) >= 0);  \
+    CTG_LOCK_DEBUG("CTG RLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
    taosRLockLatch(_lock);           \
-    CTG_LOCK_DEBUG("CTG RLOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-    assert(atomic_load_32((_lock)) > 0);  \
+    CTG_LOCK_DEBUG("CTG RLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) > 0);  \
  } else {                                                \
-    assert(atomic_load_32((_lock)) >= 0);  \
-    CTG_LOCK_DEBUG("CTG WLOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__);  \
+    assert(atomic_load_64((_lock)) >= 0);  \
+    CTG_LOCK_DEBUG("CTG WLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__);  \
    taosWLockLatch(_lock);                                \
-    CTG_LOCK_DEBUG("CTG WLOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__);  \
-    assert(atomic_load_32((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);  \
+    CTG_LOCK_DEBUG("CTG WLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__);  \
+    assert(atomic_load_64((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);  \
  }                                                       \
 } while (0)

 #define CTG_UNLOCK(type, _lock) do {                       \
  if (CTG_READ == (type)) {                                \
-    assert(atomic_load_32((_lock)) > 0);  \
-    CTG_LOCK_DEBUG("CTG RULOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) > 0);  \
+    CTG_LOCK_DEBUG("CTG RULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
    taosRUnLockLatch(_lock);                              \
-    CTG_LOCK_DEBUG("CTG RULOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-    assert(atomic_load_32((_lock)) >= 0);  \
+    CTG_LOCK_DEBUG("CTG RULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) >= 0);  \
  } else {                                                \
-    assert(atomic_load_32((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);  \
-    CTG_LOCK_DEBUG("CTG WULOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);  \
+    CTG_LOCK_DEBUG("CTG WULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
    taosWUnLockLatch(_lock);                              \
-    CTG_LOCK_DEBUG("CTG WULOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-    assert(atomic_load_32((_lock)) >= 0);  \
+    CTG_LOCK_DEBUG("CTG WULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) >= 0);  \
  }                                                       \
 } while (0)

--- a/source/libs/catalog/src/ctgAsync.c
+++ b/source/libs/catalog/src/ctgAsync.c
@ -790,8 +790,12 @@ _return:
 int32_t ctgCallUserCb(void* param) {
  SCtgJob* pJob = (SCtgJob*)param;

+  qDebug("QID:0x%" PRIx64 " ctg start to call user cb with rsp %s", pJob->queryId, tstrerror(pJob->jobResCode));
+  
  (*pJob->userFp)(&pJob->jobRes, pJob->userParam, pJob->jobResCode);

+  qDebug("QID:0x%" PRIx64 " ctg end to call user cb", pJob->queryId);
+
  taosRemoveRef(gCtgMgmt.jobPool, pJob->refId);

  return TSDB_CODE_SUCCESS;
@ -822,8 +826,6 @@ int32_t ctgHandleTaskEnd(SCtgTask* pTask, int32_t rspCode) {

 _return:

-  qDebug("QID:0x%" PRIx64 " ctg call user callback with rsp %s", pJob->queryId, tstrerror(code));
-
  pJob->jobResCode = code;

  //taosSsleep(2);
--- a/source/libs/catalog/test/catalogTests.cpp
+++ b/source/libs/catalog/test/catalogTests.cpp
@ -109,7 +109,7 @@ void sendCreateDbMsg(void *shandle, SEpSet *pEpSet) {
  createReq.compression = 2;
  createReq.replications = 1;
  createReq.strict = 1;
-  createReq.cacheLastRow = 0;
+  createReq.cacheLast = 0;
  createReq.ignoreExist = 1;

  int32_t contLen = tSerializeSCreateDbReq(NULL, 0, &createReq);
--- a/source/libs/command/src/command.c
+++ b/source/libs/command/src/command.c
@ -223,7 +223,7 @@ static void setCreateDBResultIntoDataBlock(SSDataBlock* pBlock, char* dbFName, S
                 "CREATE DATABASE `%s` BUFFER %d CACHELAST %d COMP %d DURATION %dm "
                 "FSYNC %d MAXROWS %d MINROWS %d KEEP %dm,%dm,%dm PAGES %d PAGESIZE %d PRECISION '%s' REPLICA %d "
                 "STRICT %d WAL %d VGROUPS %d SINGLE_STABLE %d",
-                 dbFName, pCfg->buffer, pCfg->cacheLastRow, pCfg->compression, pCfg->daysPerFile, pCfg->fsyncPeriod,
+                 dbFName, pCfg->buffer, pCfg->cacheLast, pCfg->compression, pCfg->daysPerFile, pCfg->fsyncPeriod,
                 pCfg->maxRows, pCfg->minRows, pCfg->daysToKeep0, pCfg->daysToKeep1, pCfg->daysToKeep2, pCfg->pages,
                 pCfg->pageSize, prec, pCfg->replications, pCfg->strict, pCfg->walLevel, pCfg->numOfVgroups,
                 1 == pCfg->numOfStables);
--- a/source/libs/executor/inc/executorimpl.h
+++ b/source/libs/executor/inc/executorimpl.h
@ -540,6 +540,9 @@ typedef struct SIndefOperatorInfo {
  SArray*            pPseudoColInfo;
  SExprSupp          scalarSup;
  SNode*             pCondition;
+  uint64_t           groupId;
+
+  SSDataBlock*       pNextGroupRes;
 } SIndefOperatorInfo;

 typedef struct SFillOperatorInfo {
@ -551,6 +554,8 @@ typedef struct SFillOperatorInfo {
  bool              multigroupResult;
  STimeWindow       win;
  SNode*            pCondition;
+  SArray*           pColMatchColInfo;
+  int32_t           primaryTsCol;
 } SFillOperatorInfo;

 typedef struct SGroupbyOperatorInfo {
@ -774,6 +779,8 @@ int32_t extractDataBlockFromFetchRsp(SSDataBlock* pRes, SLoadRemoteDataInfo* pLo
                                  int32_t compLen, int32_t numOfOutput, int64_t startTs, uint64_t* total,
                                  SArray* pColList);
 void    getAlignQueryTimeWindow(SInterval* pInterval, int32_t precision, int64_t key, STimeWindow* win);
+STimeWindow getFirstQualifiedTimeWindow(int64_t ts, STimeWindow* pWindow, SInterval* pInterval, int32_t order);
+
 int32_t getTableScanInfo(SOperatorInfo* pOperator, int32_t *order, int32_t* scanFlag);
 int32_t getBufferPgSize(int32_t rowSize, uint32_t* defaultPgsz, uint32_t* defaultBufsz);

--- a/source/libs/executor/src/cachescanoperator.c
+++ b/source/libs/executor/src/cachescanoperator.c
@ -0,0 +1,145 @@
+/*
+ * 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 "os.h"
+#include "function.h"
+#include "tname.h"
+
+#include "tdatablock.h"
+#include "tmsg.h"
+
+#include "executorimpl.h"
+#include "tcompare.h"
+#include "thash.h"
+#include "ttypes.h"
+#include "executorInt.h"
+
+static SSDataBlock* doScanLastrow(SOperatorInfo* pOperator);
+static void destroyLastrowScanOperator(void* param, int32_t numOfOutput);
+static int32_t extractTargetSlotId(const SArray* pColMatchInfo, SExecTaskInfo* pTaskInfo, int32_t** pSlotIds);
+
+SOperatorInfo* createLastrowScanOperator(SLastRowScanPhysiNode* pScanNode, SReadHandle* readHandle, SArray* pTableList,
+                                         SExecTaskInfo* pTaskInfo) {
+  SLastrowScanInfo* pInfo = taosMemoryCalloc(1, sizeof(SLastrowScanInfo));
+  SOperatorInfo*    pOperator = taosMemoryCalloc(1, sizeof(SOperatorInfo));
+  if (pInfo == NULL || pOperator == NULL) {
+    goto _error;
+  }
+
+  pInfo->pTableList = pTableList;
+  pInfo->readHandle = *readHandle;
+  pInfo->pRes = createResDataBlock(pScanNode->node.pOutputDataBlockDesc);
+
+  int32_t numOfCols = 0;
+  pInfo->pColMatchInfo = extractColMatchInfo(pScanNode->pScanCols, pScanNode->node.pOutputDataBlockDesc, &numOfCols,
+                                             COL_MATCH_FROM_COL_ID);
+  int32_t* pCols = taosMemoryMalloc(numOfCols * sizeof(int32_t));
+  for (int32_t i = 0; i < numOfCols; ++i) {
+    SColMatchInfo* pColMatch = taosArrayGet(pInfo->pColMatchInfo, i);
+    pCols[i] = pColMatch->colId;
+  }
+
+  int32_t code = extractTargetSlotId(pInfo->pColMatchInfo, pTaskInfo, &pInfo->pSlotIds);
+  if (code != TSDB_CODE_SUCCESS) {
+    goto _error;
+  }
+
+  tsdbLastRowReaderOpen(readHandle->vnode, LASTROW_RETRIEVE_TYPE_ALL, pTableList, pCols, numOfCols,
+                        &pInfo->pLastrowReader);
+  taosMemoryFree(pCols);
+
+  pOperator->name = "LastrowScanOperator";
+  pOperator->operatorType = QUERY_NODE_PHYSICAL_PLAN_LAST_ROW_SCAN;
+  pOperator->blocking = false;
+  pOperator->status = OP_NOT_OPENED;
+  pOperator->info = pInfo;
+  pOperator->pTaskInfo = pTaskInfo;
+  pOperator->exprSupp.numOfExprs = taosArrayGetSize(pInfo->pRes->pDataBlock);
+
+  initResultSizeInfo(pOperator, 1024);
+  blockDataEnsureCapacity(pInfo->pRes, pOperator->resultInfo.capacity);
+
+  pOperator->fpSet =
+      createOperatorFpSet(operatorDummyOpenFn, doScanLastrow, NULL, NULL, destroyLastrowScanOperator, NULL, NULL, NULL);
+  pOperator->cost.openCost = 0;
+  return pOperator;
+
+  _error:
+  pTaskInfo->code = TSDB_CODE_OUT_OF_MEMORY;
+  taosMemoryFree(pInfo);
+  taosMemoryFree(pOperator);
+  return NULL;
+}
+
+SSDataBlock* doScanLastrow(SOperatorInfo* pOperator) {
+  if (pOperator->status == OP_EXEC_DONE) {
+    return NULL;
+  }
+
+  SLastrowScanInfo* pInfo = pOperator->info;
+  SExecTaskInfo*    pTaskInfo = pOperator->pTaskInfo;
+
+  int32_t size = taosArrayGetSize(pInfo->pTableList);
+  if (size == 0) {
+    setTaskStatus(pTaskInfo, TASK_COMPLETED);
+    return NULL;
+  }
+
+  // check if it is a group by tbname
+  if (size == taosArrayGetSize(pInfo->pTableList)) {
+    blockDataCleanup(pInfo->pRes);
+    tsdbRetrieveLastRow(pInfo->pLastrowReader, pInfo->pRes, pInfo->pSlotIds);
+    return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
+  } else {
+    // todo fetch the result for each group
+  }
+
+  return pInfo->pRes->info.rows == 0 ? NULL : pInfo->pRes;
+}
+
+void destroyLastrowScanOperator(void* param, int32_t numOfOutput) {
+  SLastrowScanInfo* pInfo = (SLastrowScanInfo*)param;
+  blockDataDestroy(pInfo->pRes);
+  tsdbLastrowReaderClose(pInfo->pLastrowReader);
+
+  taosMemoryFreeClear(param);
+}
+
+int32_t extractTargetSlotId(const SArray* pColMatchInfo, SExecTaskInfo* pTaskInfo, int32_t** pSlotIds) {
+  size_t   numOfCols = taosArrayGetSize(pColMatchInfo);
+
+  *pSlotIds = taosMemoryMalloc(numOfCols * sizeof(int32_t));
+  if (*pSlotIds == NULL)  {
+    return TSDB_CODE_OUT_OF_MEMORY;
+  }
+
+  for (int32_t i = 0; i < numOfCols; ++i) {
+    SColMatchInfo* pColMatch = taosArrayGet(pColMatchInfo, i);
+    for (int32_t j = 0; j < pTaskInfo->schemaVer.sw->nCols; ++j) {
+      if (pColMatch->colId == pTaskInfo->schemaVer.sw->pSchema[j].colId &&
+          pColMatch->colId == PRIMARYKEY_TIMESTAMP_COL_ID) {
+        (*pSlotIds)[pColMatch->targetSlotId] = -1;
+        break;
+      }
+
+      if (pColMatch->colId == pTaskInfo->schemaVer.sw->pSchema[j].colId) {
+        (*pSlotIds)[pColMatch->targetSlotId] = j;
+        break;
+      }
+    }
+  }
+
+  return TSDB_CODE_SUCCESS;
+}
--- a/source/libs/executor/src/executil.c
+++ b/source/libs/executor/src/executil.c
@ -869,7 +869,7 @@ static STimeWindow doCalculateTimeWindow(int64_t ts, SInterval* pInterval) {
  return w;
 }

-static STimeWindow getFirstQualifiedTimeWindow(int64_t ts, STimeWindow* pWindow, SInterval* pInterval, int32_t order) {
+STimeWindow getFirstQualifiedTimeWindow(int64_t ts, STimeWindow* pWindow, SInterval* pInterval, int32_t order) {
  int32_t factor = (order == TSDB_ORDER_ASC)? -1:1;

  STimeWindow win = *pWindow;
--- a/source/libs/executor/src/executorimpl.c
+++ b/source/libs/executor/src/executorimpl.c
@ -545,9 +545,7 @@ static int32_t doAggregateImpl(SOperatorInfo* pOperator, TSKEY startTs, SqlFunct
      if (pCtx[k].fpSet.process == NULL) {
        continue;
      }
-#ifdef BUF_PAGE_DEBUG
-      qDebug("page_process");
-#endif
+
      int32_t code = pCtx[k].fpSet.process(&pCtx[k]);
      if (code != TSDB_CODE_SUCCESS) {
        qError("%s aggregate function error happens, code: %s", GET_TASKID(pOperator->pTaskInfo), tstrerror(code));
@ -571,8 +569,8 @@ int32_t projectApplyFunctions(SExprInfo* pExpr, SSDataBlock* pResult, SSDataBloc
  setPseudoOutputColInfo(pResult, pCtx, pPseudoList);
  pResult->info.groupId = pSrcBlock->info.groupId;

-  // if the source equals to the destination, it is to create a new column as the result of scalar function or some
-  // operators.
+  // if the source equals to the destination, it is to create a new column as the result of scalar
+  // function or some operators.
  bool createNewColModel = (pResult == pSrcBlock);

  int32_t numOfRows = 0;
@ -580,17 +578,18 @@ int32_t projectApplyFunctions(SExprInfo* pExpr, SSDataBlock* pResult, SSDataBloc
  for (int32_t k = 0; k < numOfOutput; ++k) {
    int32_t               outputSlotId = pExpr[k].base.resSchema.slotId;
    SqlFunctionCtx*       pfCtx = &pCtx[k];
+    SInputColumnInfoData* pInputData = &pfCtx->input;

    if (pExpr[k].pExpr->nodeType == QUERY_NODE_COLUMN) {  // it is a project query
      SColumnInfoData* pColInfoData = taosArrayGet(pResult->pDataBlock, outputSlotId);
      if (pResult->info.rows > 0 && !createNewColModel) {
-        colDataMergeCol(pColInfoData, pResult->info.rows, &pResult->info.capacity, pfCtx->input.pData[0],
-                        pfCtx->input.numOfRows);
+        colDataMergeCol(pColInfoData, pResult->info.rows, &pResult->info.capacity, pInputData->pData[0],
+                        pInputData->numOfRows);
      } else {
-        colDataAssign(pColInfoData, pfCtx->input.pData[0], pfCtx->input.numOfRows, &pResult->info);
+        colDataAssign(pColInfoData, pInputData->pData[0], pInputData->numOfRows, &pResult->info);
      }

-      numOfRows = pfCtx->input.numOfRows;
+      numOfRows = pInputData->numOfRows;
    } else if (pExpr[k].pExpr->nodeType == QUERY_NODE_VALUE) {
      SColumnInfoData* pColInfoData = taosArrayGet(pResult->pDataBlock, outputSlotId);

@ -623,14 +622,12 @@ int32_t projectApplyFunctions(SExprInfo* pExpr, SSDataBlock* pResult, SSDataBloc
      numOfRows = dest.numOfRows;
      taosArrayDestroy(pBlockList);
    } else if (pExpr[k].pExpr->nodeType == QUERY_NODE_FUNCTION) {
-      ASSERT(!fmIsAggFunc(pfCtx->functionId));
-
      // _rowts/_c0, not tbname column
      if (fmIsPseudoColumnFunc(pfCtx->functionId) && (!fmIsScanPseudoColumnFunc(pfCtx->functionId))) {
        // do nothing
      } else if (fmIsIndefiniteRowsFunc(pfCtx->functionId)) {
-        SResultRowEntryInfo* pResInfo = GET_RES_INFO(&pCtx[k]);
-        pfCtx->fpSet.init(&pCtx[k], pResInfo);
+        SResultRowEntryInfo* pResInfo = GET_RES_INFO(pfCtx);
+        pfCtx->fpSet.init(pfCtx, pResInfo);

        pfCtx->pOutput = taosArrayGet(pResult->pDataBlock, outputSlotId);
        pfCtx->offset = createNewColModel ? 0 : pResult->info.rows;  // set the start offset
@ -642,6 +639,23 @@ int32_t projectApplyFunctions(SExprInfo* pExpr, SSDataBlock* pResult, SSDataBloc
        }

        numOfRows = pfCtx->fpSet.process(pfCtx);
+      } else if (fmIsAggFunc(pfCtx->functionId)) {
+        // _group_key function for "partition by tbname" + csum(col_name) query
+        SColumnInfoData* pOutput = taosArrayGet(pResult->pDataBlock, outputSlotId);
+        int32_t          slotId = pfCtx->param[0].pCol->slotId;
+
+        // todo handle the json tag
+        SColumnInfoData* pInput = taosArrayGet(pSrcBlock->pDataBlock, slotId);
+        for (int32_t f = 0; f < pSrcBlock->info.rows; ++f) {
+          bool isNull = colDataIsNull_s(pInput, f);
+          if (isNull) {
+            colDataAppendNULL(pOutput, pResult->info.rows + f);
+          } else {
+            char* data = colDataGetData(pInput, f);
+            colDataAppend(pOutput, pResult->info.rows + f, data, isNull);
+          }
+        }
+
      } else {
        SArray* pBlockList = taosArrayInit(4, POINTER_BYTES);
        taosArrayPush(pBlockList, &pSrcBlock);
@ -675,25 +689,6 @@ int32_t projectApplyFunctions(SExprInfo* pExpr, SSDataBlock* pResult, SSDataBloc
  return TSDB_CODE_SUCCESS;
 }

-static void setResultRowKey(SResultRow* pResultRow, char* pData, int16_t type) {
-  if (IS_VAR_DATA_TYPE(type)) {
-    // todo disable this
-
-    //    if (pResultRow->key == NULL) {
-    //      pResultRow->key = taosMemoryMalloc(varDataTLen(pData));
-    //      varDataCopy(pResultRow->key, pData);
-    //    } else {
-    //      ASSERT(memcmp(pResultRow->key, pData, varDataTLen(pData)) == 0);
-    //    }
-  } else {
-    int64_t v = -1;
-    GET_TYPED_DATA(v, int64_t, type, pData);
-
-    pResultRow->win.skey = v;
-    pResultRow->win.ekey = v;
-  }
-}
-
 bool functionNeedToExecute(SqlFunctionCtx* pCtx) {
  struct SResultRowEntryInfo* pResInfo = GET_RES_INFO(pCtx);

@ -2447,7 +2442,6 @@ _error:
    doDestroyExchangeOperatorInfo(pInfo);
  }

-  taosMemoryFreeClear(pInfo);
  taosMemoryFreeClear(pOperator);
  pTaskInfo->code = code;
  return NULL;
@ -3397,6 +3391,8 @@ static SSDataBlock* doFillImpl(SOperatorInfo* pOperator) {
      assert(pBlock != NULL);
    }

+    blockDataUpdateTsWindow(pBlock, pInfo->primaryTsCol);
+
    if (*newgroup && pInfo->totalInputRows > 0) {  // there are already processed current group data block
      pInfo->existNewGroupBlock = pBlock;
      *newgroup = false;
@ -3508,11 +3504,7 @@ static void destroyOperatorInfo(SOperatorInfo* pOperator) {
    pOperator->numOfDownstream = 0;
  }

-  if (pOperator->exprSupp.pExprInfo != NULL) {
-    destroyExprInfo(pOperator->exprSupp.pExprInfo, pOperator->exprSupp.numOfExprs);
-  }
-
-  taosMemoryFreeClear(pOperator->exprSupp.pExprInfo);
+  cleanupExprSupp(&pOperator->exprSupp);
  taosMemoryFreeClear(pOperator);
 }

@ -3591,6 +3583,25 @@ void initBasicInfo(SOptrBasicInfo* pInfo, SSDataBlock* pBlock) {
  initResultRowInfo(&pInfo->resultRowInfo);
 }

+static void* destroySqlFunctionCtx(SqlFunctionCtx* pCtx, int32_t numOfOutput) {
+  if (pCtx == NULL) {
+    return NULL;
+  }
+
+  for (int32_t i = 0; i < numOfOutput; ++i) {
+    for (int32_t j = 0; j < pCtx[i].numOfParams; ++j) {
+      taosVariantDestroy(&pCtx[i].param[j].param);
+    }
+
+    taosMemoryFreeClear(pCtx[i].subsidiaries.pCtx);
+    taosMemoryFree(pCtx[i].input.pData);
+    taosMemoryFree(pCtx[i].input.pColumnDataAgg);
+  }
+
+  taosMemoryFreeClear(pCtx);
+  return NULL;
+}
+
 int32_t initExprSupp(SExprSupp* pSup, SExprInfo* pExprInfo, int32_t numOfExpr) {
  pSup->pExprInfo = pExprInfo;
  pSup->numOfExprs = numOfExpr;
@ -3604,6 +3615,16 @@ int32_t initExprSupp(SExprSupp* pSup, SExprInfo* pExprInfo, int32_t numOfExpr) {
  return TSDB_CODE_SUCCESS;
 }

+void cleanupExprSupp(SExprSupp* pSupp) {
+  destroySqlFunctionCtx(pSupp->pCtx, pSupp->numOfExprs);
+  if (pSupp->pExprInfo != NULL) {
+    destroyExprInfo(pSupp->pExprInfo, pSupp->numOfExprs);
+  }
+
+  taosMemoryFreeClear(pSupp->pExprInfo);
+  taosMemoryFree(pSupp->rowEntryInfoOffset);
+}
+
 SOperatorInfo* createAggregateOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
                                           SSDataBlock* pResultBlock, SNode* pCondition, SExprInfo* pScalarExprInfo,
                                           int32_t numOfScalarExpr, SExecTaskInfo* pTaskInfo) {
@ -3654,25 +3675,6 @@ _error:
  return NULL;
 }

-static void* destroySqlFunctionCtx(SqlFunctionCtx* pCtx, int32_t numOfOutput) {
-  if (pCtx == NULL) {
-    return NULL;
-  }
-
-  for (int32_t i = 0; i < numOfOutput; ++i) {
-    for (int32_t j = 0; j < pCtx[i].numOfParams; ++j) {
-      taosVariantDestroy(&pCtx[i].param[j].param);
-    }
-
-    taosMemoryFreeClear(pCtx[i].subsidiaries.pCtx);
-    taosMemoryFree(pCtx[i].input.pData);
-    taosMemoryFree(pCtx[i].input.pColumnDataAgg);
-  }
-
-  taosMemoryFreeClear(pCtx);
-  return NULL;
-}
-
 void cleanupBasicInfo(SOptrBasicInfo* pInfo) {
  assert(pInfo != NULL);
  cleanupResultRowInfo(&pInfo->resultRowInfo);
@ -3714,13 +3716,6 @@ static void destroyProjectOperatorInfo(void* param, int32_t numOfOutput) {
  taosMemoryFreeClear(param);
 }

-void cleanupExprSupp(SExprSupp* pSupp) {
-  destroySqlFunctionCtx(pSupp->pCtx, pSupp->numOfExprs);
-  destroyExprInfo(pSupp->pExprInfo, pSupp->numOfExprs);
-
-  taosMemoryFree(pSupp->rowEntryInfoOffset);
-}
-
 static void destroyIndefinitOperatorInfo(void* param, int32_t numOfOutput) {
  SIndefOperatorInfo* pInfo = (SIndefOperatorInfo*)param;
  cleanupBasicInfo(&pInfo->binfo);
@ -3825,39 +3820,17 @@ _error:
  return NULL;
 }

-static SSDataBlock* doApplyIndefinitFunction(SOperatorInfo* pOperator) {
+static void doHandleDataBlock(SOperatorInfo* pOperator, SSDataBlock* pBlock, SOperatorInfo* downstream,
+                              SExecTaskInfo* pTaskInfo) {
+  int32_t order = 0;
+  int32_t scanFlag = 0;
+
  SIndefOperatorInfo* pIndefInfo = pOperator->info;
  SOptrBasicInfo*     pInfo = &pIndefInfo->binfo;
  SExprSupp*          pSup = &pOperator->exprSupp;

-  SSDataBlock* pRes = pInfo->pRes;
-  blockDataCleanup(pRes);
-
-  SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
-  if (pOperator->status == OP_EXEC_DONE) {
-    return NULL;
-  }
-
-  int64_t st = 0;
-  int32_t order = 0;
-  int32_t scanFlag = 0;
-
-  if (pOperator->cost.openCost == 0) {
-    st = taosGetTimestampUs();
-  }
-
-  SOperatorInfo* downstream = pOperator->pDownstream[0];
-
-  while (1) {
-    // The downstream exec may change the value of the newgroup, so use a local variable instead.
-    SSDataBlock* pBlock = downstream->fpSet.getNextFn(downstream);
-    if (pBlock == NULL) {
-      doSetOperatorCompleted(pOperator);
-      break;
-    }
-
  // the pDataBlock are always the same one, no need to call this again
-    int32_t code = getTableScanInfo(pOperator->pDownstream[0], &order, &scanFlag);
+  int32_t code = getTableScanInfo(downstream, &order, &scanFlag);
  if (code != TSDB_CODE_SUCCESS) {
    longjmp(pTaskInfo->env, code);
  }
@ -3875,14 +3848,81 @@ static SSDataBlock* doApplyIndefinitFunction(SOperatorInfo* pOperator) {
  setInputDataBlock(pOperator, pSup->pCtx, pBlock, order, scanFlag, false);
  blockDataEnsureCapacity(pInfo->pRes, pInfo->pRes->info.rows + pBlock->info.rows);

-    code = projectApplyFunctions(pOperator->exprSupp.pExprInfo, pInfo->pRes, pBlock, pSup->pCtx,
-                                 pOperator->exprSupp.numOfExprs, pIndefInfo->pPseudoColInfo);
+  code = projectApplyFunctions(pSup->pExprInfo, pInfo->pRes, pBlock, pSup->pCtx, pSup->numOfExprs,
+                               pIndefInfo->pPseudoColInfo);
  if (code != TSDB_CODE_SUCCESS) {
    longjmp(pTaskInfo->env, code);
  }
 }

+static SSDataBlock* doApplyIndefinitFunction(SOperatorInfo* pOperator) {
+  SIndefOperatorInfo* pIndefInfo = pOperator->info;
+  SOptrBasicInfo*     pInfo = &pIndefInfo->binfo;
+  SExprSupp*          pSup = &pOperator->exprSupp;
+
+  SSDataBlock* pRes = pInfo->pRes;
+  blockDataCleanup(pRes);
+
+  SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
+  if (pOperator->status == OP_EXEC_DONE) {
+    return NULL;
+  }
+
+  int64_t st = 0;
+
+  if (pOperator->cost.openCost == 0) {
+    st = taosGetTimestampUs();
+  }
+
+  SOperatorInfo* downstream = pOperator->pDownstream[0];
+
+  while (1) {
+    // here we need to handle the existsed group results
+    if (pIndefInfo->pNextGroupRes != NULL) {  // todo extract method
+      for (int32_t k = 0; k < pSup->numOfExprs; ++k) {
+        SqlFunctionCtx* pCtx = &pSup->pCtx[k];
+
+        SResultRowEntryInfo* pResInfo = GET_RES_INFO(pCtx);
+        pResInfo->initialized = false;
+        pCtx->pOutput = NULL;
+      }
+
+      doHandleDataBlock(pOperator, pIndefInfo->pNextGroupRes, downstream, pTaskInfo);
+      pIndefInfo->pNextGroupRes = NULL;
+    }
+
+    if (pInfo->pRes->info.rows < pOperator->resultInfo.threshold) {
+      while (1) {
+        // The downstream exec may change the value of the newgroup, so use a local variable instead.
+        SSDataBlock* pBlock = downstream->fpSet.getNextFn(downstream);
+        if (pBlock == NULL) {
+          doSetOperatorCompleted(pOperator);
+          break;
+        }
+
+        if (pIndefInfo->groupId == 0 && pBlock->info.groupId != 0) {
+          pIndefInfo->groupId = pBlock->info.groupId;  // this is the initial group result
+        } else {
+          if (pIndefInfo->groupId != pBlock->info.groupId) {  // reset output buffer and computing status
+            pIndefInfo->groupId = pBlock->info.groupId;
+            pIndefInfo->pNextGroupRes = pBlock;
+            break;
+          }
+        }
+
+        doHandleDataBlock(pOperator, pBlock, downstream, pTaskInfo);
+        if (pInfo->pRes->info.rows >= pOperator->resultInfo.threshold) {
+          break;
+        }
+      }
+    }
+
    doFilter(pIndefInfo->pCondition, pInfo->pRes);
+    size_t rows = pInfo->pRes->info.rows;
+    if (rows >= 0) {
+      break;
+    }
+  }

  size_t rows = pInfo->pRes->info.rows;
  pOperator->resultInfo.totalRows += rows;
@ -3928,24 +3968,23 @@ SOperatorInfo* createIndefinitOutputOperatorInfo(SOperatorInfo* downstream, SPhy
  if (numOfRows * pResBlock->info.rowSize > TWOMB) {
    numOfRows = TWOMB / pResBlock->info.rowSize;
  }
+
  initResultSizeInfo(pOperator, numOfRows);

-  initAggInfo(&pOperator->exprSupp, &pInfo->aggSup, pExprInfo, numOfExpr, keyBufSize, pTaskInfo->id.str);
+  initAggInfo(pSup, &pInfo->aggSup, pExprInfo, numOfExpr, keyBufSize, pTaskInfo->id.str);
  initBasicInfo(&pInfo->binfo, pResBlock);

  setFunctionResultOutput(pOperator, &pInfo->binfo, &pInfo->aggSup, MAIN_SCAN, numOfExpr);

  pInfo->binfo.pRes = pResBlock;
-  pInfo->pPseudoColInfo = setRowTsColumnOutputInfo(pSup->pCtx, numOfExpr);
  pInfo->pCondition = pPhyNode->node.pConditions;
+  pInfo->pPseudoColInfo = setRowTsColumnOutputInfo(pSup->pCtx, numOfExpr);

  pOperator->name = "IndefinitOperator";
-  pOperator->operatorType = QUERY_NODE_PHYSICAL_PLAN_PROJECT;
+  pOperator->operatorType = QUERY_NODE_PHYSICAL_PLAN_INDEF_ROWS_FUNC;
  pOperator->blocking = false;
  pOperator->status = OP_NOT_OPENED;
  pOperator->info = pInfo;
-  pOperator->exprSupp.pExprInfo = pExprInfo;
-  pOperator->exprSupp.numOfExprs = numOfExpr;
  pOperator->pTaskInfo = pTaskInfo;

  pOperator->fpSet = createOperatorFpSet(operatorDummyOpenFn, doApplyIndefinitFunction, NULL, NULL,
@ -3971,6 +4010,7 @@ static int32_t initFillInfo(SFillOperatorInfo* pInfo, SExprInfo* pExpr, int32_t

  STimeWindow w = TSWINDOW_INITIALIZER;
  getAlignQueryTimeWindow(pInterval, pInterval->precision, win.skey, &w);
+  w = getFirstQualifiedTimeWindow(win.skey, &w, pInterval, TSDB_ORDER_ASC);

  int32_t order = TSDB_ORDER_ASC;
  pInfo->pFillInfo = taosCreateFillInfo(order, w.skey, 0, capacity, numOfCols, pInterval, fillType, pColInfo, id);
@ -4001,10 +4041,16 @@ SOperatorInfo* createFillOperatorInfo(SOperatorInfo* downstream, SFillPhysiNode*
      QUERY_NODE_PHYSICAL_PLAN_MERGE_ALIGNED_INTERVAL == downstream->operatorType
            ? &((SMergeAlignedIntervalAggOperatorInfo*)downstream->info)->intervalAggOperatorInfo->interval
            : &((SIntervalAggOperatorInfo*)downstream->info)->interval;
+
  int32_t type = convertFillType(pPhyFillNode->mode);

  SResultInfo* pResultInfo = &pOperator->resultInfo;
  initResultSizeInfo(pOperator, 4096);
+  pInfo->primaryTsCol = ((SColumnNode*)pPhyFillNode->pWStartTs)->slotId;
+
+  int32_t numOfOutputCols = 0;
+  SArray* pColMatchColInfo = extractColMatchInfo(pPhyFillNode->pTargets, pPhyFillNode->node.pOutputDataBlockDesc,
+                                                 &numOfOutputCols, COL_MATCH_FROM_SLOT_ID);

  int32_t code = initFillInfo(pInfo, pExprInfo, num, (SNodeListNode*)pPhyFillNode->pValues, pPhyFillNode->timeRange,
                              pResultInfo->capacity, pTaskInfo->id.str, pInterval, type);
@ -4015,6 +4061,7 @@ SOperatorInfo* createFillOperatorInfo(SOperatorInfo* downstream, SFillPhysiNode*
  pInfo->pRes = pResBlock;
  pInfo->multigroupResult = multigroupResult;
  pInfo->pCondition = pPhyFillNode->node.pConditions;
+  pInfo->pColMatchColInfo = pColMatchColInfo;
  pOperator->name = "FillOperator";
  pOperator->blocking = false;
  pOperator->status = OP_NOT_OPENED;
@ -4072,6 +4119,8 @@ int32_t extractTableSchemaInfo(SReadHandle* pHandle, uint64_t uid, SExecTaskInfo
    pTaskInfo->schemaVer.sw = tCloneSSchemaWrapper(&mr.me.stbEntry.schemaRow);
    pTaskInfo->schemaVer.tversion = mr.me.stbEntry.schemaTag.version;
  } else if (mr.me.type == TSDB_CHILD_TABLE) {
+    tDecoderClear(&mr.coder);
+
    tb_uid_t suid = mr.me.ctbEntry.suid;
    metaGetTableEntryByUid(&mr, suid);
    pTaskInfo->schemaVer.sw = tCloneSSchemaWrapper(&mr.me.stbEntry.schemaRow);
--- a/source/libs/executor/src/groupoperator.c
+++ b/source/libs/executor/src/groupoperator.c
@ -637,6 +637,7 @@ static SSDataBlock* buildPartitionResult(SOperatorInfo* pOperator) {
  int32_t* pageId = taosArrayGet(pGroupInfo->pPageList, pInfo->pageIndex);
  void* page = getBufPage(pInfo->pBuf, *pageId);

+  blockDataEnsureCapacity(pInfo->binfo.pRes, pInfo->rowCapacity);
  blockDataFromBuf1(pInfo->binfo.pRes, page, pInfo->rowCapacity);

  pInfo->pageIndex += 1;
--- a/source/libs/executor/src/scanoperator.c
+++ b/source/libs/executor/src/scanoperator.c
@ -578,6 +578,7 @@ static void destroyTableScanOperatorInfo(void* param, int32_t numOfOutput) {
    taosArrayDestroy(pTableScanInfo->pColMatchInfo);
  }

+  cleanupExprSupp(&pTableScanInfo->pseudoSup);
  taosMemoryFreeClear(param);
 }

@ -1134,12 +1135,6 @@ static int32_t setBlockIntoRes(SStreamScanInfo* pInfo, const SSDataBlock* pBlock
  pInfo->pRes->info.type = STREAM_NORMAL;
  pInfo->pRes->info.capacity = pBlock->info.rows;

-  // 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 = pBlock->info.uid;
-  }
-
  uint64_t* groupIdPre = taosHashGet(pOperator->pTaskInfo->tableqinfoList.map, &pBlock->info.uid, sizeof(int64_t));
  if (groupIdPre) {
    pInfo->pRes->info.groupId = *groupIdPre;
@ -1147,6 +1142,12 @@ static int32_t setBlockIntoRes(SStreamScanInfo* pInfo, const SSDataBlock* pBlock
    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 = pBlock->info.uid;
+  }
+
  // todo extract method
  for (int32_t i = 0; i < taosArrayGetSize(pInfo->pColMatchInfo); ++i) {
    SColMatchInfo* pColMatchInfo = taosArrayGet(pInfo->pColMatchInfo, i);
--- a/source/libs/executor/src/sortoperator.c
+++ b/source/libs/executor/src/sortoperator.c
@ -217,6 +217,7 @@ SSDataBlock* doSort(SOperatorInfo* pOperator) {
      doSetOperatorCompleted(pOperator);
      break;
    }
+
    if (blockDataGetNumOfRows(pBlock) > 0) {
      break;
    }
@ -601,8 +602,7 @@ SSDataBlock* getMultiwaySortedBlockData(SSortHandle* pHandle, SSDataBlock* pData
      break;
    }

-    if (pInfo->groupSort)
-    {
+    if (pInfo->groupSort) {
      uint64_t tupleGroupId = tsortGetGroupId(pTupleHandle);
      if (!pInfo->hasGroupId) {
        pInfo->groupId = tupleGroupId;
--- a/source/libs/executor/src/tfill.c
+++ b/source/libs/executor/src/tfill.c
@ -50,8 +50,11 @@ static void setTagsValue(SFillInfo* pFillInfo, void** data, int32_t genRows) {

 static void setNullRow(SSDataBlock* pBlock, int32_t numOfCol, int32_t rowIndex) {
  // the first are always the timestamp column, so start from the second column.
-  for (int32_t i = 1; i < taosArrayGetSize(pBlock->pDataBlock); ++i) {
+  for (int32_t i = 0; i < taosArrayGetSize(pBlock->pDataBlock); ++i) {
    SColumnInfoData* p = taosArrayGet(pBlock->pDataBlock, i);
+    if (p->info.type == TSDB_DATA_TYPE_TIMESTAMP && i == 0) {
+      continue;
+    }
    colDataAppendNULL(p, rowIndex);
  }
 }
--- a/source/libs/function/inc/builtinsimpl.h
+++ b/source/libs/function/inc/builtinsimpl.h
@ -157,6 +157,7 @@ int32_t elapsedCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx);
 bool getHistogramFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
 bool histogramFunctionSetup(SqlFunctionCtx *pCtx, SResultRowEntryInfo* pResultInfo);
 int32_t histogramFunction(SqlFunctionCtx* pCtx);
+int32_t histogramFunctionPartial(SqlFunctionCtx* pCtx);
 int32_t histogramFunctionMerge(SqlFunctionCtx* pCtx);
 int32_t histogramFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
 int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
--- a/source/libs/function/src/builtins.c
+++ b/source/libs/function/src/builtins.c
@ -48,8 +48,8 @@ static int32_t validateTimeUnitParam(uint8_t dbPrec, const SValueNode* pVal) {
    return TIME_UNIT_INVALID;
  }

-  if (TSDB_TIME_PRECISION_MILLI == dbPrec && (0 == strcasecmp(pVal->literal, "1u") ||
-                                              0 == strcasecmp(pVal->literal, "1b"))) {
+  if (TSDB_TIME_PRECISION_MILLI == dbPrec &&
+      (0 == strcasecmp(pVal->literal, "1u") || 0 == strcasecmp(pVal->literal, "1b"))) {
    return TIME_UNIT_TOO_SMALL;
  }

@ -57,10 +57,9 @@ static int32_t validateTimeUnitParam(uint8_t dbPrec, const SValueNode* pVal) {
    return TIME_UNIT_TOO_SMALL;
  }

-  if (pVal->literal[0] != '1' || (pVal->literal[1] != 'u' && pVal->literal[1] != 'a' &&
-                                  pVal->literal[1] != 's' && pVal->literal[1] != 'm' &&
-                                  pVal->literal[1] != 'h' && pVal->literal[1] != 'd' &&
-                                  pVal->literal[1] != 'w' && pVal->literal[1] != 'b')) {
+  if (pVal->literal[0] != '1' ||
+      (pVal->literal[1] != 'u' && pVal->literal[1] != 'a' && pVal->literal[1] != 's' && pVal->literal[1] != 'm' &&
+       pVal->literal[1] != 'h' && pVal->literal[1] != 'd' && pVal->literal[1] != 'w' && pVal->literal[1] != 'b')) {
    return TIME_UNIT_INVALID;
  }

@ -678,9 +677,10 @@ static int32_t translateElapsed(SFunctionNode* pFunc, char* pErrBuf, int32_t len
    return invaildFuncParaNumErrMsg(pErrBuf, len, pFunc->functionName);
  }

-  uint8_t paraType = ((SExprNode*)nodesListGetNode(pFunc->pParameterList, 0))->resType.type;
-  if (TSDB_DATA_TYPE_TIMESTAMP != paraType) {
-    return invaildFuncParaTypeErrMsg(pErrBuf, len, pFunc->functionName);
+  SNode* pPara1 = nodesListGetNode(pFunc->pParameterList, 0);
+  if (QUERY_NODE_COLUMN != nodeType(pPara1) || PRIMARYKEY_TIMESTAMP_COL_ID != ((SColumnNode*)pPara1)->colId) {
+    return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
+                           "The first parameter of the ELAPSED function can only be the timestamp primary key");
  }

  // param1
@ -694,8 +694,7 @@ static int32_t translateElapsed(SFunctionNode* pFunc, char* pErrBuf, int32_t len

    pValue->notReserved = true;

-    paraType = ((SExprNode*)nodesListGetNode(pFunc->pParameterList, 1))->resType.type;
-    if (!IS_INTEGER_TYPE(paraType)) {
+    if (!IS_INTEGER_TYPE(pValue->node.resType.type)) {
      return invaildFuncParaTypeErrMsg(pErrBuf, len, pFunc->functionName);
    }

@ -706,7 +705,8 @@ static int32_t translateElapsed(SFunctionNode* pFunc, char* pErrBuf, int32_t len
      return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
                             "ELAPSED function time unit parameter should be greater than db precision");
    } else if (ret == TIME_UNIT_INVALID) {
-      return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
+      return buildFuncErrMsg(
+          pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
          "ELAPSED function time unit parameter should be one of the following: [1b, 1u, 1a, 1s, 1m, 1h, 1d, 1w]");
    }
  }
@ -1229,7 +1229,8 @@ static int32_t translateStateDuration(SFunctionNode* pFunc, char* pErrBuf, int32
                             "STATEDURATION function time unit parameter should be greater than db precision");
    } else if (ret == TIME_UNIT_INVALID) {
      return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
-                             "STATEDURATION function time unit parameter should be one of the following: [1b, 1u, 1a, 1s, 1m, 1h, 1d, 1w]");
+                             "STATEDURATION function time unit parameter should be one of the following: [1b, 1u, 1a, "
+                             "1s, 1m, 1h, 1d, 1w]");
    }
  }

@ -1426,9 +1427,12 @@ static int32_t translateIrate(SFunctionNode* pFunc, char* pErrBuf, int32_t len)
 }

 static int32_t translateFirstLast(SFunctionNode* pFunc, char* pErrBuf, int32_t len) {
-  // first(col_list) will be rewritten as first(col)
-  if (1 != LIST_LENGTH(pFunc->pParameterList)) {
-    return TSDB_CODE_SUCCESS;
+  int32_t numOfParams = LIST_LENGTH(pFunc->pParameterList);
+  for (int32_t i = 0; i < numOfParams; ++i) {
+    SNode* pParamNode = nodesListGetNode(pFunc->pParameterList, i);
+    if (QUERY_NODE_VALUE == nodeType(pParamNode)) {
+      return invaildFuncParaValueErrMsg(pErrBuf, len, pFunc->functionName);
+    }
  }

  pFunc->node.resType = ((SExprNode*)nodesListGetNode(pFunc->pParameterList, 0))->resType;
@ -1740,7 +1744,8 @@ static int32_t translateTimeTruncate(SFunctionNode* pFunc, char* pErrBuf, int32_
    return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
                           "TIMETRUNCATE function time unit parameter should be greater than db precision");
  } else if (ret == TIME_UNIT_INVALID) {
-    return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
+    return buildFuncErrMsg(
+        pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
        "TIMETRUNCATE function time unit parameter should be one of the following: [1b, 1u, 1a, 1s, 1m, 1h, 1d, 1w]");
  }

@ -1779,7 +1784,8 @@ static int32_t translateTimeDiff(SFunctionNode* pFunc, char* pErrBuf, int32_t le
      return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
                             "TIMEDIFF function time unit parameter should be greater than db precision");
    } else if (ret == TIME_UNIT_INVALID) {
-      return buildFuncErrMsg(pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
+      return buildFuncErrMsg(
+          pErrBuf, len, TSDB_CODE_FUNC_FUNTION_ERROR,
          "TIMEDIFF function time unit parameter should be one of the following: [1b, 1u, 1a, 1s, 1m, 1h, 1d, 1w]");
    }
  }
@ -2320,7 +2326,7 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
    .translateFunc = translateHistogramPartial,
    .getEnvFunc   = getHistogramFuncEnv,
    .initFunc     = histogramFunctionSetup,
-    .processFunc  = histogramFunction,
+    .processFunc  = histogramFunctionPartial,
    .finalizeFunc = histogramPartialFinalize,
    .invertFunc   = NULL,
    .combineFunc  = histogramCombine,
--- a/source/libs/function/src/builtinsimpl.c
+++ b/source/libs/function/src/builtinsimpl.c
@ -4098,7 +4098,7 @@ bool histogramFunctionSetup(SqlFunctionCtx* pCtx, SResultRowEntryInfo* pResultIn
  return true;
 }

-int32_t histogramFunction(SqlFunctionCtx* pCtx) {
+static int32_t histogramFunctionImpl(SqlFunctionCtx* pCtx, bool isPartial) {
  SHistoFuncInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));

  SInputColumnInfoData* pInput = &pCtx->input;
@ -4130,10 +4130,22 @@ int32_t histogramFunction(SqlFunctionCtx* pCtx) {
    }
  }

+  if (!isPartial) {
    SET_VAL(GET_RES_INFO(pCtx), numOfElems, pInfo->numOfBins);
+  } else {
+    SET_VAL(GET_RES_INFO(pCtx), numOfElems, 1);
+  }
  return TSDB_CODE_SUCCESS;
 }

+int32_t histogramFunction(SqlFunctionCtx* pCtx) {
+  return histogramFunctionImpl(pCtx, false);
+}
+
+int32_t histogramFunctionPartial(SqlFunctionCtx* pCtx) {
+  return histogramFunctionImpl(pCtx, true);
+}
+
 static void histogramTransferInfo(SHistoFuncInfo* pInput, SHistoFuncInfo* pOutput) {
  pOutput->normalized = pInput->normalized;
  pOutput->numOfBins = pInput->numOfBins;
@ -4153,10 +4165,12 @@ int32_t histogramFunctionMerge(SqlFunctionCtx* pCtx) {
  SHistoFuncInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));

  int32_t         start = pInput->startRowIndex;
-  char*           data = colDataGetData(pCol, start);
-  SHistoFuncInfo* pInputInfo = (SHistoFuncInfo*)varDataVal(data);

+  for(int32_t i = start; i < start + pInput->numOfRows; ++i) {
+    char*       data = colDataGetData(pCol, i);
+    SHistoFuncInfo* pInputInfo = (SHistoFuncInfo*)varDataVal(data);
    histogramTransferInfo(pInputInfo, pInfo);
+  }

  SET_VAL(GET_RES_INFO(pCtx), pInfo->numOfBins, pInfo->numOfBins);
  return TSDB_CODE_SUCCESS;
@ -4199,6 +4213,7 @@ int32_t histogramFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
 }

 int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
+  SResultRowEntryInfo* pResInfo = GET_RES_INFO(pCtx);
  SHistoFuncInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));
  int32_t         resultBytes = getHistogramInfoSize();
  char*           res = taosMemoryCalloc(resultBytes + VARSTR_HEADER_SIZE, sizeof(char));
@ -4212,7 +4227,7 @@ int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
  colDataAppend(pCol, pBlock->info.rows, res, false);

  taosMemoryFree(res);
-  return 1;
+  return pResInfo->numOfRes;
 }

 int32_t histogramCombine(SqlFunctionCtx* pDestCtx, SqlFunctionCtx* pSourceCtx) {
--- a/source/libs/function/src/functionMgt.c
+++ b/source/libs/function/src/functionMgt.c
@ -139,7 +139,7 @@ bool fmIsAggFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MG

 bool fmIsScalarFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MGT_SCALAR_FUNC); }

-bool fmIsVectorFunc(int32_t funcId) { return !fmIsScalarFunc(funcId) && !fmIsScanPseudoColumnFunc(funcId); }
+bool fmIsVectorFunc(int32_t funcId) { return !fmIsScalarFunc(funcId) && !fmIsPseudoColumnFunc(funcId); }

 bool fmIsSelectFunc(int32_t funcId) { return isSpecificClassifyFunc(funcId, FUNC_MGT_SELECT_FUNC); }

--- a/source/libs/nodes/src/nodesUtilFuncs.c
+++ b/source/libs/nodes/src/nodesUtilFuncs.c
@ -105,6 +105,8 @@ SNode* nodesMakeNode(ENodeType type) {
      return makeNode(type, sizeof(SAlterDatabaseStmt));
    case QUERY_NODE_FLUSH_DATABASE_STMT:
      return makeNode(type, sizeof(SFlushDatabaseStmt));
+    case QUERY_NODE_TRIM_DATABASE_STMT:
+      return makeNode(type, sizeof(STrimDatabaseStmt));
    case QUERY_NODE_CREATE_TABLE_STMT:
      return makeNode(type, sizeof(SCreateTableStmt));
    case QUERY_NODE_CREATE_SUBTABLE_CLAUSE:
@ -548,6 +550,7 @@ void nodesDestroyNode(SNode* pNode) {
      nodesDestroyNode((SNode*)((SAlterDatabaseStmt*)pNode)->pOptions);
      break;
    case QUERY_NODE_FLUSH_DATABASE_STMT:  // no pointer field
+    case QUERY_NODE_TRIM_DATABASE_STMT:   // no pointer field
      break;
    case QUERY_NODE_CREATE_TABLE_STMT: {
      SCreateTableStmt* pStmt = (SCreateTableStmt*)pNode;
@ -1790,7 +1793,7 @@ static EDealRes classifyConditionImpl(SNode* pNode, void* pContext) {
    } else if (pCol->hasIndex) {
      pCxt->hasTagIndexCol = true;
      pCxt->hasTagCol = true;
-    } else if (COLUMN_TYPE_TAG == pCol->colType) {
+    } else if (COLUMN_TYPE_TAG == pCol->colType || COLUMN_TYPE_TBNAME == pCol->colType) {
      pCxt->hasTagCol = true;
    } else {
      pCxt->hasOtherCol = true;
--- a/source/libs/parser/inc/parAst.h
+++ b/source/libs/parser/inc/parAst.h
@ -137,6 +137,7 @@ SNode* createCreateDatabaseStmt(SAstCreateContext* pCxt, bool ignoreExists, STok
 SNode* createDropDatabaseStmt(SAstCreateContext* pCxt, bool ignoreNotExists, SToken* pDbName);
 SNode* createAlterDatabaseStmt(SAstCreateContext* pCxt, SToken* pDbName, SNode* pOptions);
 SNode* createFlushDatabaseStmt(SAstCreateContext* pCxt, SToken* pDbName);
+SNode* createTrimDatabaseStmt(SAstCreateContext* pCxt, SToken* pDbName);
 SNode* createDefaultTableOptions(SAstCreateContext* pCxt);
 SNode* createAlterTableOptions(SAstCreateContext* pCxt);
 SNode* setTableOption(SAstCreateContext* pCxt, SNode* pOptions, ETableOptionType type, void* pVal);
--- a/source/libs/parser/inc/parInsertData.h
+++ b/source/libs/parser/inc/parInsertData.h
@ -20,6 +20,7 @@
 #include "os.h"
 #include "tname.h"
 #include "ttypes.h"
+#include "query.h"

 #define IS_DATA_COL_ORDERED(spd) ((spd->orderStatus) == (int8_t)ORDER_STATUS_ORDERED)

--- a/source/libs/parser/inc/sql.y
+++ b/source/libs/parser/inc/sql.y
@ -158,6 +158,7 @@ cmd ::= DROP DATABASE exists_opt(A) db_name(B).
 cmd ::= USE db_name(A).                                                           { pCxt->pRootNode = createUseDatabaseStmt(pCxt, &A); }
 cmd ::= ALTER DATABASE db_name(A) alter_db_options(B).                            { pCxt->pRootNode = createAlterDatabaseStmt(pCxt, &A, B); }
 cmd ::= FLUSH DATABASE db_name(A).                                                { pCxt->pRootNode = createFlushDatabaseStmt(pCxt, &A); }
+cmd ::= TRIM DATABASE db_name(A).                                                 { pCxt->pRootNode = createTrimDatabaseStmt(pCxt, &A); }

 %type not_exists_opt                                                              { bool }
 %destructor not_exists_opt                                                        { }
@ -934,7 +935,11 @@ query_expression_body(A) ::=
 query_primary(A) ::= query_specification(B).                                      { A = B; }
 query_primary(A) ::=
  NK_LP query_expression_body(B) 
-    order_by_clause_opt slimit_clause_opt limit_clause_opt NK_RP.                 { A = B; }
+    order_by_clause_opt(C) slimit_clause_opt(D) limit_clause_opt(E) NK_RP.        { 
+                                                                                    A = addOrderByClause(pCxt, B, C);
+                                                                                    A = addSlimitClause(pCxt, A, D);
+                                                                                    A = addLimitClause(pCxt, A, E);
+                                                                                  }

 %type order_by_clause_opt                                                         { SNodeList* }
 %destructor order_by_clause_opt                                                   { nodesDestroyList($$); }
--- a/source/libs/parser/src/parAstCreater.c
+++ b/source/libs/parser/src/parAstCreater.c
@ -339,6 +339,10 @@ SNode* createDefaultDatabaseCondValue(SAstCreateContext* pCxt) {

 SNode* createPlaceholderValueNode(SAstCreateContext* pCxt, const SToken* pLiteral) {
  CHECK_PARSER_STATUS(pCxt);
+  if (NULL == pCxt->pQueryCxt->pStmtCb) {
+    pCxt->errCode = generateSyntaxErrMsg(&pCxt->msgBuf, TSDB_CODE_PAR_SYNTAX_ERROR, pLiteral->z);
+    return NULL;
+  }
  SValueNode* val = (SValueNode*)nodesMakeNode(QUERY_NODE_VALUE);
  CHECK_OUT_OF_MEM(val);
  val->literal = strndup(pLiteral->z, pLiteral->n);
@ -665,6 +669,9 @@ SNode* addHavingClause(SAstCreateContext* pCxt, SNode* pStmt, SNode* pHaving) {

 SNode* addOrderByClause(SAstCreateContext* pCxt, SNode* pStmt, SNodeList* pOrderByList) {
  CHECK_PARSER_STATUS(pCxt);
+  if (NULL == pOrderByList) {
+    return pStmt;
+  }
  if (QUERY_NODE_SELECT_STMT == nodeType(pStmt)) {
    ((SSelectStmt*)pStmt)->pOrderByList = pOrderByList;
  } else {
@ -675,6 +682,9 @@ SNode* addOrderByClause(SAstCreateContext* pCxt, SNode* pStmt, SNodeList* pOrder

 SNode* addSlimitClause(SAstCreateContext* pCxt, SNode* pStmt, SNode* pSlimit) {
  CHECK_PARSER_STATUS(pCxt);
+  if (NULL == pSlimit) {
+    return pStmt;
+  }
  if (QUERY_NODE_SELECT_STMT == nodeType(pStmt)) {
    ((SSelectStmt*)pStmt)->pSlimit = (SLimitNode*)pSlimit;
  }
@ -683,6 +693,9 @@ SNode* addSlimitClause(SAstCreateContext* pCxt, SNode* pStmt, SNode* pSlimit) {

 SNode* addLimitClause(SAstCreateContext* pCxt, SNode* pStmt, SNode* pLimit) {
  CHECK_PARSER_STATUS(pCxt);
+  if (NULL == pLimit) {
+    return pStmt;
+  }
  if (QUERY_NODE_SELECT_STMT == nodeType(pStmt)) {
    ((SSelectStmt*)pStmt)->pLimit = (SLimitNode*)pLimit;
  } else {
@ -746,8 +759,8 @@ 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->cacheLastSize = TSDB_DEFAULT_LAST_ROW_MEM;
+  pOptions->cacheLast = TSDB_DEFAULT_CACHE_LAST;
+  pOptions->cacheLastSize = TSDB_DEFAULT_CACHE_LAST_SIZE;
  pOptions->compressionLevel = TSDB_DEFAULT_COMP_LEVEL;
  pOptions->daysPerFile = TSDB_DEFAULT_DAYS_PER_FILE;
  pOptions->fsyncPeriod = TSDB_DEFAULT_FSYNC_PERIOD;
@ -922,7 +935,18 @@ SNode* createFlushDatabaseStmt(SAstCreateContext* pCxt, SToken* pDbName) {
  if (!checkDbName(pCxt, pDbName, false)) {
    return NULL;
  }
-  SAlterDatabaseStmt* pStmt = (SAlterDatabaseStmt*)nodesMakeNode(QUERY_NODE_FLUSH_DATABASE_STMT);
+  SFlushDatabaseStmt* pStmt = (SFlushDatabaseStmt*)nodesMakeNode(QUERY_NODE_FLUSH_DATABASE_STMT);
+  CHECK_OUT_OF_MEM(pStmt);
+  COPY_STRING_FORM_ID_TOKEN(pStmt->dbName, pDbName);
+  return (SNode*)pStmt;
+}
+
+SNode* createTrimDatabaseStmt(SAstCreateContext* pCxt, SToken* pDbName) {
+  CHECK_PARSER_STATUS(pCxt);
+  if (!checkDbName(pCxt, pDbName, false)) {
+    return NULL;
+  }
+  STrimDatabaseStmt* pStmt = (STrimDatabaseStmt*)nodesMakeNode(QUERY_NODE_TRIM_DATABASE_STMT);
  CHECK_OUT_OF_MEM(pStmt);
  COPY_STRING_FORM_ID_TOKEN(pStmt->dbName, pDbName);
  return (SNode*)pStmt;
--- a/source/libs/parser/src/parInsertData.c
+++ b/source/libs/parser/src/parInsertData.c
@ -630,6 +630,17 @@ int32_t qCloneStmtDataBlock(void** pDst, void* pSrc) {
  memcpy(*pDst, pSrc, sizeof(STableDataBlocks));
  ((STableDataBlocks*)(*pDst))->cloned = true;

+  STableDataBlocks* pBlock = (STableDataBlocks*)(*pDst);
+  if (pBlock->pTableMeta) {
+    void *pNewMeta = taosMemoryMalloc(TABLE_META_SIZE(pBlock->pTableMeta));
+    if (NULL == pNewMeta) {
+      taosMemoryFreeClear(*pDst);
+      return TSDB_CODE_OUT_OF_MEMORY;
+    }
+    memcpy(pNewMeta, pBlock->pTableMeta, TABLE_META_SIZE(pBlock->pTableMeta));
+    pBlock->pTableMeta = pNewMeta;
+  }
+
  return qResetStmtDataBlock(*pDst, false);
 }

--- a/source/libs/parser/src/parTokenizer.c
+++ b/source/libs/parser/src/parTokenizer.c
@ -216,6 +216,7 @@ static SKeyword keywordTable[] = {
    {"TRANSACTION",    TK_TRANSACTION},
    {"TRANSACTIONS",   TK_TRANSACTIONS},
    {"TRIGGER",        TK_TRIGGER},
+    {"TRIM",           TK_TRIM},
    {"TSERIES",        TK_TSERIES},
    {"TTL",            TK_TTL},
    {"UNION",          TK_UNION},
--- a/source/libs/parser/src/parTranslater.c
+++ b/source/libs/parser/src/parTranslater.c
@ -461,12 +461,10 @@ static bool isDistinctOrderBy(STranslateContext* pCxt) {
          ((SSelectStmt*)pCxt->pCurrStmt)->isDistinct);
 }

-static bool belongTable(const char* currentDb, const SColumnNode* pCol, const STableNode* pTable) {
+static bool belongTable(const SColumnNode* pCol, const STableNode* pTable) {
  int cmp = 0;
  if ('\0' != pCol->dbName[0]) {
    cmp = strcmp(pCol->dbName, pTable->dbName);
-  } else {
-    cmp = (QUERY_NODE_REAL_TABLE == nodeType(pTable) ? strcmp(currentDb, pTable->dbName) : 0);
  }
  if (0 == cmp) {
    cmp = strcmp(pCol->tableAlias, pTable->tableAlias);
@ -630,7 +628,7 @@ static EDealRes translateColumnWithPrefix(STranslateContext* pCxt, SColumnNode**
  bool    foundTable = false;
  for (size_t i = 0; i < nums; ++i) {
    STableNode* pTable = taosArrayGetP(pTables, i);
-    if (belongTable(pCxt->pParseCxt->db, (*pCol), pTable)) {
+    if (belongTable((*pCol), pTable)) {
      foundTable = true;
      bool foundCol = false;
      pCxt->errCode = findAndSetColumn(pCxt, pCol, pTable, &foundCol);
@ -1189,7 +1187,7 @@ static void setFuncClassification(SNode* pCurrStmt, SFunctionNode* pFunc) {
    if (fmIsSelectFunc(pFunc->funcId)) {
      pSelect->hasSelectFunc = true;
      ++(pSelect->selectFuncNum);
-    } else if (fmIsAggFunc(pFunc->funcId) || fmIsIndefiniteRowsFunc(pFunc->funcId)) {
+    } else if (fmIsVectorFunc(pFunc->funcId)) {
      pSelect->hasOtherVectorFunc = true;
    }
    pSelect->hasUniqueFunc = pSelect->hasUniqueFunc ? true : (FUNCTION_TYPE_UNIQUE == pFunc->funcType);
@ -1514,18 +1512,11 @@ static int32_t rewriteColsToSelectValFunc(STranslateContext* pCxt, SSelectStmt*
 typedef struct CheckAggColCoexistCxt {
  STranslateContext* pTranslateCxt;
  bool               existCol;
-  int32_t            selectFuncNum;
-  bool               existOtherVectorFunc;
 } CheckAggColCoexistCxt;

 static EDealRes doCheckAggColCoexist(SNode** pNode, void* pContext) {
  CheckAggColCoexistCxt* pCxt = (CheckAggColCoexistCxt*)pContext;
  if (isVectorFunc(*pNode)) {
-    if (isSelectFunc(*pNode)) {
-      ++(pCxt->selectFuncNum);
-    } else {
-      pCxt->existOtherVectorFunc = true;
-    }
    return DEAL_RES_IGNORE_CHILD;
  }
  SNode* pPartKey = NULL;
@ -1542,16 +1533,15 @@ static EDealRes doCheckAggColCoexist(SNode** pNode, void* pContext) {

 static int32_t checkAggColCoexist(STranslateContext* pCxt, SSelectStmt* pSelect) {
  if (NULL != pSelect->pGroupByList || NULL != pSelect->pWindow ||
-      (!pSelect->hasAggFuncs && !pSelect->hasIndefiniteRowsFunc)) {
+      (!pSelect->hasAggFuncs && !pSelect->hasIndefiniteRowsFunc && !pSelect->hasInterpFunc)) {
    return TSDB_CODE_SUCCESS;
  }
-  CheckAggColCoexistCxt cxt = {
-      .pTranslateCxt = pCxt, .existCol = false, .selectFuncNum = 0, .existOtherVectorFunc = false};
+  CheckAggColCoexistCxt cxt = {.pTranslateCxt = pCxt, .existCol = false};
  nodesRewriteExprs(pSelect->pProjectionList, doCheckAggColCoexist, &cxt);
  if (!pSelect->isDistinct) {
    nodesRewriteExprs(pSelect->pOrderByList, doCheckAggColCoexist, &cxt);
  }
-  if (1 == cxt.selectFuncNum && !cxt.existOtherVectorFunc) {
+  if (1 == pSelect->selectFuncNum && !pSelect->hasOtherVectorFunc) {
    return rewriteColsToSelectValFunc(pCxt, pSelect);
  }
  if (cxt.existCol) {
@ -2846,8 +2836,8 @@ 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->lastRowMem = pStmt->pOptions->cacheLastSize;
+  pReq->cacheLast = pStmt->pOptions->cacheLast;
+  pReq->cacheLastSize = pStmt->pOptions->cacheLastSize;
  pReq->schemaless = pStmt->pOptions->schemaless;
  pReq->ignoreExist = pStmt->ignoreExists;
  return buildCreateDbRetentions(pStmt->pOptions->pRetentions, pReq);
@ -3008,12 +2998,12 @@ 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,
-                            TSDB_MAX_DB_CACHE_LAST_ROW);
+    code = checkRangeOption(pCxt, "cacheLast", pOptions->cacheLast, TSDB_MIN_DB_CACHE_LAST,
+                            TSDB_MAX_DB_CACHE_LAST);
  }
  if (TSDB_CODE_SUCCESS == code) {
-    code = checkRangeOption(pCxt, "cacheLastSize", pOptions->cacheLastSize, TSDB_MIN_DB_LAST_ROW_MEM,
-                            TSDB_MAX_DB_LAST_ROW_MEM);
+    code = checkRangeOption(pCxt, "cacheLastSize", pOptions->cacheLastSize, TSDB_MIN_DB_CACHE_LAST_SIZE,
+                            TSDB_MAX_DB_CACHE_LAST_SIZE);
  }
  if (TSDB_CODE_SUCCESS == code) {
    code = checkRangeOption(pCxt, "compression", pOptions->compressionLevel, TSDB_MIN_COMP_LEVEL, TSDB_MAX_COMP_LEVEL);
@ -3126,7 +3116,7 @@ static void buildAlterDbReq(STranslateContext* pCxt, SAlterDatabaseStmt* pStmt,
  pReq->buffer = pStmt->pOptions->buffer;
  pReq->pageSize = -1;
  pReq->pages = pStmt->pOptions->pages;
-  pReq->lastRowMem = -1;
+  pReq->cacheLastSize = -1;
  pReq->daysPerFile = -1;
  pReq->daysToKeep0 = pStmt->pOptions->keep[0];
  pReq->daysToKeep1 = pStmt->pOptions->keep[1];
@ -3134,8 +3124,8 @@ 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->lastRowMem = pStmt->pOptions->cacheLastSize;
+  pReq->cacheLast = pStmt->pOptions->cacheLast;
+  pReq->cacheLastSize = pStmt->pOptions->cacheLastSize;
  pReq->replications = pStmt->pOptions->replica;
  return;
 }
@ -3152,6 +3142,14 @@ static int32_t translateAlterDatabase(STranslateContext* pCxt, SAlterDatabaseStm
  return buildCmdMsg(pCxt, TDMT_MND_ALTER_DB, (FSerializeFunc)tSerializeSAlterDbReq, &alterReq);
 }

+static int32_t translateTrimDatabase(STranslateContext* pCxt, STrimDatabaseStmt* pStmt) {
+  STrimDbReq req = {0};
+  SName      name = {0};
+  tNameSetDbName(&name, pCxt->pParseCxt->acctId, pStmt->dbName, strlen(pStmt->dbName));
+  tNameGetFullDbName(&name, req.db);
+  return buildCmdMsg(pCxt, TDMT_MND_TRIM_DB, (FSerializeFunc)tSerializeSTrimDbReq, &req);
+}
+
 static int32_t columnDefNodeToField(SNodeList* pList, SArray** pArray) {
  *pArray = taosArrayInit(LIST_LENGTH(pList), sizeof(SField));
  SNode* pNode;
@ -4017,8 +4015,15 @@ static int32_t buildCreateSmaReq(STranslateContext* pCxt, SCreateIndexStmt* pStm
      (NULL != pStmt->pOptions->pSliding ? ((SValueNode*)pStmt->pOptions->pSliding)->unit : pReq->intervalUnit);
  if (NULL != pStmt->pOptions->pStreamOptions) {
    SStreamOptions* pStreamOpt = (SStreamOptions*)pStmt->pOptions->pStreamOptions;
-    pReq->maxDelay = (NULL != pStreamOpt->pDelay ? ((SValueNode*)pStreamOpt->pDelay)->datum.i : 0);
-    pReq->watermark = (NULL != pStreamOpt->pWatermark ? ((SValueNode*)pStreamOpt->pWatermark)->datum.i : 0);
+    pReq->maxDelay = (NULL != pStreamOpt->pDelay ? ((SValueNode*)pStreamOpt->pDelay)->datum.i : -1);
+    pReq->watermark = (NULL != pStreamOpt->pWatermark ? ((SValueNode*)pStreamOpt->pWatermark)->datum.i
+                                                      : TSDB_DEFAULT_ROLLUP_WATERMARK);
+    if (pReq->watermark < TSDB_MIN_ROLLUP_WATERMARK) {
+      pReq->watermark = TSDB_MIN_ROLLUP_WATERMARK;
+    }
+    if (pReq->watermark > TSDB_MAX_ROLLUP_WATERMARK) {
+      pReq->watermark = TSDB_MAX_ROLLUP_WATERMARK;
+    }
  }

  int32_t code = getSmaIndexDstVgId(pCxt, pStmt->tableName, &pReq->dstVgId);
@ -4584,6 +4589,9 @@ static int32_t translateQuery(STranslateContext* pCxt, SNode* pNode) {
    case QUERY_NODE_ALTER_DATABASE_STMT:
      code = translateAlterDatabase(pCxt, (SAlterDatabaseStmt*)pNode);
      break;
+    case QUERY_NODE_TRIM_DATABASE_STMT:
+      code = translateTrimDatabase(pCxt, (STrimDatabaseStmt*)pNode);
+      break;
    case QUERY_NODE_CREATE_TABLE_STMT:
      code = translateCreateSuperTable(pCxt, (SCreateTableStmt*)pNode);
      break;
--- a/source/libs/parser/src/parser.c
+++ b/source/libs/parser/src/parser.c
@ -41,7 +41,7 @@ bool qIsInsertValuesSql(const char* pStr, size_t length) {
    } else if (TK_SELECT == t.type) {
      return false;
    }
-    if (0 == t.type) {
+    if (0 == t.type || 0 == t.n) {
      break;
    }
  } while (pStr - pSql < length);
--- a/source/libs/parser/src/sql.c
+++ b/source/libs/parser/src/sql.c
--- a/source/libs/parser/test/parInitialCTest.cpp
+++ b/source/libs/parser/test/parInitialCTest.cpp
@ -76,8 +76,8 @@ TEST_F(ParserInitialCTest, createDatabase) {
    expect.db[len] = '\0';
    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.cacheLast = TSDB_DEFAULT_CACHE_LAST;
+    expect.cacheLastSize = TSDB_DEFAULT_CACHE_LAST_SIZE;
    expect.compression = TSDB_DEFAULT_COMP_LEVEL;
    expect.daysPerFile = TSDB_DEFAULT_DAYS_PER_FILE;
    expect.fsyncPeriod = TSDB_DEFAULT_FSYNC_PERIOD;
@ -98,8 +98,8 @@ TEST_F(ParserInitialCTest, createDatabase) {
  };

  auto setDbBufferFunc = [&](int32_t buffer) { expect.buffer = buffer; };
-  auto setDbCachelastFunc = [&](int8_t cachelast) { expect.cacheLastRow = cachelast; };
-  auto setDbCachelastSize = [&](int8_t cachelastSize) { expect.lastRowMem = cachelastSize; };
+  auto setDbCachelastFunc = [&](int8_t cachelast) { expect.cacheLast = cachelast; };
+  auto setDbCachelastSize = [&](int8_t cachelastSize) { expect.cacheLastSize = 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; };
@ -155,8 +155,8 @@ TEST_F(ParserInitialCTest, createDatabase) {
    ASSERT_EQ(req.compression, expect.compression);
    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.cacheLast, expect.cacheLast);
+    ASSERT_EQ(req.cacheLastSize, expect.cacheLastSize);
    // ASSERT_EQ(req.schemaless, expect.schemaless);
    ASSERT_EQ(req.ignoreExist, expect.ignoreExist);
    ASSERT_EQ(req.numOfRetensions, expect.numOfRetensions);
--- a/source/libs/parser/test/parSelectTest.cpp
+++ b/source/libs/parser/test/parSelectTest.cpp
@ -245,13 +245,21 @@ TEST_F(ParserSelectTest, orderBy) {
 TEST_F(ParserSelectTest, distinct) {
  useDb("root", "test");

-  // run("SELECT distinct c1, c2 FROM t1 WHERE c1 > 0 order by c1");
+  run("SELECT distinct c1, c2 FROM t1 WHERE c1 > 0 order by c1");

-  // run("SELECT distinct c1 + 10, c2 FROM t1 WHERE c1 > 0 order by c1 + 10, c2");
+  run("SELECT distinct c1 + 10, c2 FROM t1 WHERE c1 > 0 order by c1 + 10, c2");

-  // run("SELECT distinct c1 + 10 cc1, c2 cc2 FROM t1 WHERE c1 > 0 order by cc1, c2");
+  run("SELECT distinct c1 + 10 cc1, c2 cc2 FROM t1 WHERE c1 > 0 order by cc1, c2");

-  // run("SELECT distinct COUNT(c2) FROM t1 WHERE c1 > 0 GROUP BY c1 order by COUNT(c2)");
+  run("SELECT distinct COUNT(c2) FROM t1 WHERE c1 > 0 GROUP BY c1 order by COUNT(c2)");
+}
+
+TEST_F(ParserSelectTest, limit) {
+  useDb("root", "test");
+
+  run("SELECT c1, c2 FROM t1 LIMIT 10");
+
+  run("(SELECT c1, c2 FROM t1 LIMIT 10)");
 }

 // INTERVAL(interval_val [, interval_offset]) [SLIDING (sliding_val)] [FILL(fill_mod_and_val)]
@ -329,70 +337,69 @@ TEST_F(ParserSelectTest, semanticCheck) {
  useDb("root", "test");

  // TSDB_CODE_PAR_INVALID_COLUMN
-  run("SELECT c1, cc1 FROM t1", TSDB_CODE_PAR_INVALID_COLUMN, PARSER_STAGE_TRANSLATE);
+  run("SELECT c1, cc1 FROM t1", TSDB_CODE_PAR_INVALID_COLUMN);

-  run("SELECT t1.c1, t1.cc1 FROM t1", TSDB_CODE_PAR_INVALID_COLUMN, PARSER_STAGE_TRANSLATE);
+  run("SELECT t1.c1, t1.cc1 FROM t1", TSDB_CODE_PAR_INVALID_COLUMN);

  // TSDB_CODE_PAR_TABLE_NOT_EXIST
-  run("SELECT * FROM t10", TSDB_CODE_PAR_TABLE_NOT_EXIST, PARSER_STAGE_TRANSLATE);
+  run("SELECT * FROM t10", TSDB_CODE_PAR_TABLE_NOT_EXIST);

-  run("SELECT * FROM test.t10", TSDB_CODE_PAR_TABLE_NOT_EXIST, PARSER_STAGE_TRANSLATE);
+  run("SELECT * FROM test.t10", TSDB_CODE_PAR_TABLE_NOT_EXIST);

-  run("SELECT t2.c1 FROM t1", TSDB_CODE_PAR_TABLE_NOT_EXIST, PARSER_STAGE_TRANSLATE);
+  run("SELECT t2.c1 FROM t1", TSDB_CODE_PAR_TABLE_NOT_EXIST);

  // TSDB_CODE_PAR_AMBIGUOUS_COLUMN
-  run("SELECT c2 FROM t1 tt1, t1 tt2 WHERE tt1.c1 = tt2.c1", TSDB_CODE_PAR_AMBIGUOUS_COLUMN, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 tt1, t1 tt2 WHERE tt1.c1 = tt2.c1", TSDB_CODE_PAR_AMBIGUOUS_COLUMN);

-  run("SELECT c2 FROM (SELECT c1 c2, c2 FROM t1)", TSDB_CODE_PAR_AMBIGUOUS_COLUMN, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM (SELECT c1 c2, c2 FROM t1)", TSDB_CODE_PAR_AMBIGUOUS_COLUMN);

  // TSDB_CODE_PAR_WRONG_VALUE_TYPE
-  run("SELECT timestamp '2010a' FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE, PARSER_STAGE_TRANSLATE);
+  run("SELECT timestamp '2010a' FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE);

-  run("SELECT LAST(*) + SUM(c1) FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE, PARSER_STAGE_TRANSLATE);
+  run("SELECT LAST(*) + SUM(c1) FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE);

-  run("SELECT CEIL(LAST(ts, c1)) FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE, PARSER_STAGE_TRANSLATE);
+  run("SELECT CEIL(LAST(ts, c1)) FROM t1", TSDB_CODE_PAR_WRONG_VALUE_TYPE);

  // TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION
-  run("SELECT c2 FROM t1 tt1 join t1 tt2 on COUNT(*) > 0", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 tt1 join t1 tt2 on COUNT(*) > 0", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION);

-  run("SELECT c2 FROM t1 WHERE COUNT(*) > 0", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 WHERE COUNT(*) > 0", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION);

-  run("SELECT c2 FROM t1 GROUP BY COUNT(*)", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 GROUP BY COUNT(*)", TSDB_CODE_PAR_ILLEGAL_USE_AGG_FUNCTION);

  // TSDB_CODE_PAR_WRONG_NUMBER_OF_SELECT
-  run("SELECT c2 FROM t1 order by 0", TSDB_CODE_PAR_WRONG_NUMBER_OF_SELECT, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 order by 0", TSDB_CODE_PAR_WRONG_NUMBER_OF_SELECT);

-  run("SELECT c2 FROM t1 order by 2", TSDB_CODE_PAR_WRONG_NUMBER_OF_SELECT, PARSER_STAGE_TRANSLATE);
+  run("SELECT c2 FROM t1 order by 2", TSDB_CODE_PAR_WRONG_NUMBER_OF_SELECT);

  // TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION
-  run("SELECT COUNT(*) cnt FROM t1 having c1 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION, PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*) cnt FROM t1 having c1 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION);

-  run("SELECT COUNT(*) cnt FROM t1 GROUP BY c2 having c1 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*) cnt FROM t1 GROUP BY c2 having c1 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION);

-  run("SELECT COUNT(*), c1 cnt FROM t1 GROUP BY c2 having c2 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*), c1 cnt FROM t1 GROUP BY c2 having c2 > 0", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION);

-  run("SELECT COUNT(*) cnt FROM t1 GROUP BY c2 having c2 > 0 order by c1", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*) cnt FROM t1 GROUP BY c2 having c2 > 0 order by c1", TSDB_CODE_PAR_GROUPBY_LACK_EXPRESSION);

  // TSDB_CODE_PAR_NOT_SINGLE_GROUP
-  run("SELECT COUNT(*), c1 FROM t1", TSDB_CODE_PAR_NOT_SINGLE_GROUP, PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*), c1 FROM t1", TSDB_CODE_PAR_NOT_SINGLE_GROUP);

-  run("SELECT COUNT(*) FROM t1 order by c1", TSDB_CODE_PAR_NOT_SINGLE_GROUP, PARSER_STAGE_TRANSLATE);
+  run("SELECT COUNT(*) FROM t1 order by c1", TSDB_CODE_PAR_NOT_SINGLE_GROUP);

-  run("SELECT c1 FROM t1 order by COUNT(*)", TSDB_CODE_PAR_NOT_SINGLE_GROUP, PARSER_STAGE_TRANSLATE);
+  run("SELECT c1 FROM t1 order by COUNT(*)", TSDB_CODE_PAR_NOT_SINGLE_GROUP);

  // TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION
-  run("SELECT distinct c1, c2 FROM t1 WHERE c1 > 0 order by ts", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT distinct c1, c2 FROM t1 WHERE c1 > 0 order by ts", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION);

-  run("SELECT distinct c1 FROM t1 WHERE c1 > 0 order by COUNT(c2)", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT distinct c1 FROM t1 WHERE c1 > 0 order by COUNT(c2)", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION);

-  run("SELECT distinct c2 FROM t1 WHERE c1 > 0 order by COUNT(c2)", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION,
-      PARSER_STAGE_TRANSLATE);
+  run("SELECT distinct c2 FROM t1 WHERE c1 > 0 order by COUNT(c2)", TSDB_CODE_PAR_NOT_SELECTED_EXPRESSION);
+}
+
+TEST_F(ParserSelectTest, syntaxError) {
+  useDb("root", "test");
+
+  run("SELECT CAST(? AS BINARY(10)) FROM t1", TSDB_CODE_PAR_SYNTAX_ERROR, PARSER_STAGE_PARSE);
 }

 TEST_F(ParserSelectTest, setOperator) {
--- a/source/libs/parser/test/parShowToUse.cpp
+++ b/source/libs/parser/test/parShowToUse.cpp
@ -222,6 +222,25 @@ TEST_F(ParserShowToUseTest, splitVgroup) {
  run("SPLIT VGROUP 15");
 }

+TEST_F(ParserShowToUseTest, trimDatabase) {
+  useDb("root", "test");
+
+  STrimDbReq expect = {0};
+
+  auto setTrimDbReq = [&](const char* pDb) { snprintf(expect.db, sizeof(expect.db), "0.%s", pDb); };
+
+  setCheckDdlFunc([&](const SQuery* pQuery, ParserStage stage) {
+    ASSERT_EQ(nodeType(pQuery->pRoot), QUERY_NODE_TRIM_DATABASE_STMT);
+    ASSERT_EQ(pQuery->pCmdMsg->msgType, TDMT_MND_TRIM_DB);
+    STrimDbReq req = {0};
+    ASSERT_EQ(tDeserializeSTrimDbReq(pQuery->pCmdMsg->pMsg, pQuery->pCmdMsg->msgLen, &req), TSDB_CODE_SUCCESS);
+    ASSERT_EQ(std::string(req.db), std::string(expect.db));
+  });
+
+  setTrimDbReq("wxy_db");
+  run("TRIM DATABASE wxy_db");
+}
+
 TEST_F(ParserShowToUseTest, useDatabase) {
  useDb("root", "test");

--- a/source/libs/planner/src/planLogicCreater.c
+++ b/source/libs/planner/src/planLogicCreater.c
@ -476,12 +476,12 @@ static int32_t createAggLogicNode(SLogicPlanContext* pCxt, SSelectStmt* pSelect,
  int32_t code = TSDB_CODE_SUCCESS;

  // set grouyp keys, agg funcs and having conditions
-  if (TSDB_CODE_SUCCESS == code && pSelect->hasAggFuncs) {
+  if (TSDB_CODE_SUCCESS == code) {
    code = nodesCollectFuncs(pSelect, SQL_CLAUSE_GROUP_BY, fmIsAggFunc, &pAgg->pAggFuncs);
  }

  // rewrite the expression in subsequent clauses
-  if (TSDB_CODE_SUCCESS == code) {
+  if (TSDB_CODE_SUCCESS == code && NULL != pAgg->pAggFuncs) {
    code = rewriteExprsForSelect(pAgg->pAggFuncs, pSelect, SQL_CLAUSE_GROUP_BY);
  }

--- a/source/libs/planner/src/planOptimizer.c
+++ b/source/libs/planner/src/planOptimizer.c
@ -80,6 +80,23 @@ static void optResetParent(SLogicNode* pNode) {
  FOREACH(pChild, pNode->pChildren) { ((SLogicNode*)pChild)->pParent = pNode; }
 }

+static EDealRes optRebuildTbanme(SNode** pNode, void* pContext) {
+  if (QUERY_NODE_COLUMN == nodeType(*pNode) && COLUMN_TYPE_TBNAME == ((SColumnNode*)*pNode)->colType) {
+    SFunctionNode* pFunc = (SFunctionNode*)nodesMakeNode(QUERY_NODE_FUNCTION);
+    if (NULL == pFunc) {
+      *(int32_t*)pContext = TSDB_CODE_OUT_OF_MEMORY;
+      return DEAL_RES_ERROR;
+    }
+    strcpy(pFunc->functionName, "tbname");
+    pFunc->funcType = FUNCTION_TYPE_TBNAME;
+    pFunc->node.resType = ((SColumnNode*)*pNode)->node.resType;
+    nodesDestroyNode(*pNode);
+    *pNode = (SNode*)pFunc;
+    return DEAL_RES_IGNORE_CHILD;
+  }
+  return DEAL_RES_CONTINUE;
+}
+
 EDealRes scanPathOptHaveNormalColImpl(SNode* pNode, void* pContext) {
  if (QUERY_NODE_COLUMN == nodeType(pNode)) {
    // *((bool*)pContext) = (COLUMN_TYPE_TAG != ((SColumnNode*)pNode)->colType);
@ -312,6 +329,12 @@ static int32_t pushDownCondOptCalcTimeRange(SOptimizeContext* pCxt, SScanLogicNo
  return code;
 }

+static int32_t pushDownCondOptRebuildTbanme(SNode** pTagCond) {
+  int32_t code = TSDB_CODE_SUCCESS;
+  nodesRewriteExpr(pTagCond, optRebuildTbanme, &code);
+  return code;
+}
+
 static int32_t pushDownCondOptDealScan(SOptimizeContext* pCxt, SScanLogicNode* pScan) {
  if (NULL == pScan->node.pConditions ||
      OPTIMIZE_FLAG_TEST_MASK(pScan->node.optimizedFlag, OPTIMIZE_FLAG_PUSH_DOWN_CONDE) ||
@ -323,6 +346,9 @@ static int32_t pushDownCondOptDealScan(SOptimizeContext* pCxt, SScanLogicNode* p
  SNode*  pOtherCond = NULL;
  int32_t code = nodesPartitionCond(&pScan->node.pConditions, &pPrimaryKeyCond, &pScan->pTagIndexCond, &pScan->pTagCond,
                                    &pOtherCond);
+  if (TSDB_CODE_SUCCESS == code && NULL != pScan->pTagCond) {
+    code = pushDownCondOptRebuildTbanme(&pScan->pTagCond);
+  }
  if (TSDB_CODE_SUCCESS == code && NULL != pPrimaryKeyCond) {
    code = pushDownCondOptCalcTimeRange(pCxt, pScan, &pPrimaryKeyCond, &pOtherCond);
  }
@ -1338,9 +1364,9 @@ static EDealRes partTagsOptHasColImpl(SNode* pNode, void* pContext) {
  return DEAL_RES_CONTINUE;
 }

-static bool partTagsOptHasCol(SNodeList* pPartKeys) {
+static bool planOptNodeListHasCol(SNodeList* pKeys) {
  bool hasCol = false;
-  nodesWalkExprs(pPartKeys, partTagsOptHasColImpl, &hasCol);
+  nodesWalkExprs(pKeys, partTagsOptHasColImpl, &hasCol);
  return hasCol;
 }

@ -1383,29 +1409,12 @@ static bool partTagsOptMayBeOptimized(SLogicNode* pNode) {
    return false;
  }

-  return !partTagsOptHasCol(partTagsGetPartKeys(pNode)) && partTagsOptAreSupportedFuncs(partTagsGetFuncs(pNode));
-}
-
-static EDealRes partTagsOptRebuildTbanmeImpl(SNode** pNode, void* pContext) {
-  if (QUERY_NODE_COLUMN == nodeType(*pNode) && COLUMN_TYPE_TBNAME == ((SColumnNode*)*pNode)->colType) {
-    SFunctionNode* pFunc = (SFunctionNode*)nodesMakeNode(QUERY_NODE_FUNCTION);
-    if (NULL == pFunc) {
-      *(int32_t*)pContext = TSDB_CODE_OUT_OF_MEMORY;
-      return DEAL_RES_ERROR;
-    }
-    strcpy(pFunc->functionName, "tbname");
-    pFunc->funcType = FUNCTION_TYPE_TBNAME;
-    pFunc->node.resType = ((SColumnNode*)*pNode)->node.resType;
-    nodesDestroyNode(*pNode);
-    *pNode = (SNode*)pFunc;
-    return DEAL_RES_IGNORE_CHILD;
-  }
-  return DEAL_RES_CONTINUE;
+  return !planOptNodeListHasCol(partTagsGetPartKeys(pNode)) && partTagsOptAreSupportedFuncs(partTagsGetFuncs(pNode));
 }

 static int32_t partTagsOptRebuildTbanme(SNodeList* pPartKeys) {
  int32_t code = TSDB_CODE_SUCCESS;
-  nodesRewriteExprs(pPartKeys, partTagsOptRebuildTbanmeImpl, &code);
+  nodesRewriteExprs(pPartKeys, optRebuildTbanme, &code);
  return code;
 }

@ -1977,7 +1986,8 @@ static bool lastRowScanOptMayBeOptimized(SLogicNode* pNode) {

  SNode* pFunc = NULL;
  FOREACH(pFunc, ((SAggLogicNode*)pNode)->pAggFuncs) {
-    if (FUNCTION_TYPE_LAST_ROW != ((SFunctionNode*)pFunc)->funcType) {
+    if (FUNCTION_TYPE_LAST_ROW != ((SFunctionNode*)pFunc)->funcType &&
+        FUNCTION_TYPE_SELECT_VALUE != ((SFunctionNode*)pFunc)->funcType) {
      return false;
    }
  }
@ -2086,6 +2096,37 @@ static int32_t mergeProjectsOptimize(SOptimizeContext* pCxt, SLogicSubplan* pLog
  return mergeProjectsOptimizeImpl(pCxt, pLogicSubplan, pProjectNode);
 }

+static bool tagScanMayBeOptimized(SLogicNode* pNode) {
+  if (QUERY_NODE_LOGIC_PLAN_SCAN != nodeType(pNode) || (SCAN_TYPE_TAG == ((SScanLogicNode*)pNode)->scanType)) {
+    return false;
+  }
+  SScanLogicNode *pScan = (SScanLogicNode*)pNode;
+  if (NULL != pScan->pScanCols) {
+    return false;
+  }
+  if (NULL == pNode->pParent || QUERY_NODE_LOGIC_PLAN_AGG != nodeType(pNode->pParent) || 1 != LIST_LENGTH(pNode->pParent->pChildren)) {
+    return false;
+  }
+
+  SAggLogicNode* pAgg = (SAggLogicNode*)(pNode->pParent);
+  if (NULL == pAgg->pGroupKeys || NULL != pAgg->pAggFuncs || planOptNodeListHasCol(pAgg->pGroupKeys)) {
+    return false;
+  }
+
+  return true;
+}
+
+static int32_t tagScanOptimize(SOptimizeContext* pCxt, SLogicSubplan* pLogicSubplan) {
+  SScanLogicNode* pScanNode = (SScanLogicNode*)optFindPossibleNode(pLogicSubplan->pNode, tagScanMayBeOptimized);
+  if (NULL == pScanNode) {
+    return TSDB_CODE_SUCCESS;
+  }
+
+  pScanNode->scanType = SCAN_TYPE_TAG;
+  pCxt->optimized = true;
+  return TSDB_CODE_SUCCESS;
+}
+
 // clang-format off
 static const SOptimizeRule optimizeRuleSet[] = {
  {.pName = "ScanPath",                   .optimizeFunc = scanPathOptimize},
@ -2098,7 +2139,8 @@ static const SOptimizeRule optimizeRuleSet[] = {
  {.pName = "EliminateSetOperator",       .optimizeFunc = eliminateSetOpOptimize},
  {.pName = "RewriteTail",                .optimizeFunc = rewriteTailOptimize},
  {.pName = "RewriteUnique",              .optimizeFunc = rewriteUniqueOptimize},
-  {.pName = "LastRowScan",                .optimizeFunc = lastRowScanOptimize}
+  {.pName = "LastRowScan",               .optimizeFunc = lastRowScanOptimize},
+  {.pName = "TagScan",                   .optimizeFunc = tagScanOptimize}
 };
 // clang-format on

--- a/source/libs/planner/src/planPhysiCreater.c
+++ b/source/libs/planner/src/planPhysiCreater.c
@ -1519,6 +1519,7 @@ static SSubplan* makeSubplan(SPhysiPlanContext* pCxt, SLogicSubplan* pLogicSubpl

 static int32_t buildInsertValuesSubplan(SPhysiPlanContext* pCxt, SVnodeModifyLogicNode* pModify, SSubplan* pSubplan) {
  pSubplan->msgType = pModify->msgType;
+  pSubplan->execNode.nodeId = pModify->pVgDataBlocks->vg.vgId;
  pSubplan->execNode.epSet = pModify->pVgDataBlocks->vg.epSet;
  return createDataInserter(pCxt, pModify->pVgDataBlocks, &pSubplan->pDataSink);
 }
--- a/source/libs/planner/src/planSpliter.c
+++ b/source/libs/planner/src/planSpliter.c
@ -877,7 +877,7 @@ static int32_t stbSplSplitSortNode(SSplitContext* pCxt, SStableSplitInfo* pInfo)
  return code;
 }

-static int32_t stbSplSplitScanNode(SSplitContext* pCxt, SStableSplitInfo* pInfo) {
+static int32_t stbSplSplitScanNodeWithoutPartTags(SSplitContext* pCxt, SStableSplitInfo* pInfo) {
  int32_t code = splCreateExchangeNodeForSubplan(pCxt, pInfo->pSubplan, pInfo->pSplitNode, SUBPLAN_TYPE_MERGE);
  if (TSDB_CODE_SUCCESS == code) {
    code = nodesListMakeStrictAppend(&pInfo->pSubplan->pChildren,
@ -887,6 +887,25 @@ static int32_t stbSplSplitScanNode(SSplitContext* pCxt, SStableSplitInfo* pInfo)
  return code;
 }

+static int32_t stbSplSplitScanNodeWithPartTags(SSplitContext* pCxt, SStableSplitInfo* pInfo) {
+  int32_t code = stbSplCreateMergeNode(pCxt, pInfo->pSubplan, pInfo->pSplitNode, NULL, pInfo->pSplitNode, true);
+  if (TSDB_CODE_SUCCESS == code) {
+    code = nodesListMakeStrictAppend(&pInfo->pSubplan->pChildren,
+                                     (SNode*)splCreateScanSubplan(pCxt, pInfo->pSplitNode, SPLIT_FLAG_STABLE_SPLIT));
+  }
+  pInfo->pSubplan->subplanType = SUBPLAN_TYPE_MERGE;
+  ++(pCxt->groupId);
+  return code;
+}
+
+static int32_t stbSplSplitScanNode(SSplitContext* pCxt, SStableSplitInfo* pInfo) {
+  SScanLogicNode* pScan = (SScanLogicNode*)pInfo->pSplitNode;
+  if (NULL != pScan->pGroupTags) {
+    return stbSplSplitScanNodeWithPartTags(pCxt, pInfo);
+  }
+  return stbSplSplitScanNodeWithoutPartTags(pCxt, pInfo);
+}
+
 static SNode* stbSplFindPrimaryKeyFromScan(SScanLogicNode* pScan) {
  SNode* pCol = NULL;
  FOREACH(pCol, pScan->pScanCols) {
--- a/source/libs/planner/test/planOptimizeTest.cpp
+++ b/source/libs/planner/test/planOptimizeTest.cpp
@ -37,6 +37,8 @@ TEST_F(PlanOptimizeTest, pushDownCondition) {

  run("SELECT ts, c1 FROM st1 WHERE tag1 > 4");

+  run("SELECT ts, c1 FROM st1 WHERE TBNAME = 'st1s1'");
+
  run("SELECT ts, c1 FROM st1 WHERE tag1 > 4 or tag1 < 2");

  run("SELECT ts, c1 FROM st1 WHERE tag1 > 4 AND tag2 = 'hello'");
@ -86,3 +88,10 @@ TEST_F(PlanOptimizeTest, pushDownProjectCond) {
  useDb("root", "test");
  run("select 1-abs(c1) from (select unique(c1) c1 from st1s3) where 1-c1>5 order by 1 nulls first");
 }
+
+TEST_F(PlanOptimizeTest, tagScan) {
+  useDb("root", "test");
+  run("select tag1 from st1 group by tag1");
+  run("select distinct tag1 from st1");
+  run("select tag1*tag1 from st1 group by tag1*tag1");
+}
--- a/source/libs/planner/test/planPartByTest.cpp
+++ b/source/libs/planner/test/planPartByTest.cpp
@ -59,4 +59,6 @@ TEST_F(PlanPartitionByTest, withGroupBy) {
  useDb("root", "test");

  run("select count(*) from t1 partition by c1 group by c2");
+
+  run("SELECT TBNAME, c1 FROM st1 PARTITION BY TBNAME GROUP BY c1");
 }
--- a/source/libs/planner/test/planTestUtil.cpp
+++ b/source/libs/planner/test/planTestUtil.cpp
@ -330,6 +330,10 @@ class PlannerTestBaseImpl {
    cxt.pMsg = stmtEnv_.msgBuf_.data();
    cxt.msgLen = stmtEnv_.msgBuf_.max_size();
    cxt.svrVer = "3.0.0.0";
+    if (prepare) {
+      SStmtCallback stmtCb = {0};
+      cxt.pStmtCb = &stmtCb;
+    }

    DO_WITH_THROW(qParseSql, &cxt, pQuery);
    if (prepare) {
--- a/source/libs/qworker/inc/qwInt.h
+++ b/source/libs/qworker/inc/qwInt.h
@ -316,34 +316,34 @@ typedef struct SQWorkerMgmt {
 #define QW_LOCK(type, _lock)                                                                       \
  do {                                                                                             \
    if (QW_READ == (type)) {                                                                       \
-      assert(atomic_load_32((_lock)) >= 0);                                                        \
-      QW_LOCK_DEBUG("QW RLOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) >= 0);                                                        \
+      QW_LOCK_DEBUG("QW RLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
      taosRLockLatch(_lock);                                                                       \
-      QW_LOCK_DEBUG("QW RLOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-      assert(atomic_load_32((_lock)) > 0);                                                         \
+      QW_LOCK_DEBUG("QW RLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) > 0);                                                         \
    } else {                                                                                       \
-      assert(atomic_load_32((_lock)) >= 0);                                                        \
-      QW_LOCK_DEBUG("QW WLOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) >= 0);                                                        \
+      QW_LOCK_DEBUG("QW WLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
      taosWLockLatch(_lock);                                                                       \
-      QW_LOCK_DEBUG("QW WLOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-      assert(atomic_load_32((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);                               \
+      QW_LOCK_DEBUG("QW WLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);                               \
    }                                                                                              \
  } while (0)

 #define QW_UNLOCK(type, _lock)                                                                      \
  do {                                                                                              \
    if (QW_READ == (type)) {                                                                        \
-      assert(atomic_load_32((_lock)) > 0);                                                          \
-      QW_LOCK_DEBUG("QW RULOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) > 0);                                                          \
+      QW_LOCK_DEBUG("QW RULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
      taosRUnLockLatch(_lock);                                                                      \
-      QW_LOCK_DEBUG("QW RULOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-      assert(atomic_load_32((_lock)) >= 0);                                                         \
+      QW_LOCK_DEBUG("QW RULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) >= 0);                                                         \
    } else {                                                                                        \
-      assert(atomic_load_32((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);                                \
-      QW_LOCK_DEBUG("QW WULOCK%p:%d, %s:%d B", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) == TD_RWLATCH_WRITE_FLAG_COPY);                                \
+      QW_LOCK_DEBUG("QW WULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
      taosWUnLockLatch(_lock);                                                                      \
-      QW_LOCK_DEBUG("QW WULOCK%p:%d, %s:%d E", (_lock), atomic_load_32(_lock), __FILE__, __LINE__); \
-      assert(atomic_load_32((_lock)) >= 0);                                                         \
+      QW_LOCK_DEBUG("QW WULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+      assert(atomic_load_64((_lock)) >= 0);                                                         \
    }                                                                                               \
  } while (0)

--- a/source/libs/scalar/src/filter.c
+++ b/source/libs/scalar/src/filter.c
@ -3623,7 +3623,8 @@ EDealRes fltReviseRewriter(SNode** pNode, void* pContext) {
      return DEAL_RES_CONTINUE;
    }

-    if (FILTER_GET_FLAG(stat->info->options, FLT_OPTION_TIMESTAMP) && node->opType >= OP_TYPE_NOT_EQUAL) {
+    if (FILTER_GET_FLAG(stat->info->options, FLT_OPTION_TIMESTAMP) && 
+        (node->opType >= OP_TYPE_NOT_EQUAL) && (node->opType != OP_TYPE_IS_NULL && node->opType != OP_TYPE_IS_NOT_NULL)) {
      stat->scalarMode = true;
      return DEAL_RES_CONTINUE;
    }
--- a/source/libs/scheduler/inc/schInt.h
+++ b/source/libs/scheduler/inc/schInt.h
@ -54,6 +54,11 @@ typedef enum {
  SCH_OP_GET_STATUS,
 } SCH_OP_TYPE;

+typedef struct SSchDebug {
+  bool     lockEnable;
+  bool     apiEnable;
+} SSchDebug;
+
 typedef struct SSchTrans {
  void *pTrans;
  void *pHandle;
@ -186,7 +191,7 @@ typedef struct SSchTaskProfile {

 typedef struct SSchTask {
  uint64_t             taskId;         // task id
-  SRWLatch             lock;           // task lock
+  SRWLatch             lock;           // task reentrant lock
  int32_t              maxExecTimes;   // task may exec times
  int32_t              execId;        // task current execute try index
  SSchLevel           *level;          // level
@ -356,8 +361,41 @@ extern SSchedulerMgmt schMgmt;
 #define SCH_RET(c) do { int32_t _code = c; if (_code != TSDB_CODE_SUCCESS) { SCH_SET_ERRNO(_code); } return _code; } while (0)
 #define SCH_ERR_JRET(c) do { code = c; if (code != TSDB_CODE_SUCCESS) { SCH_SET_ERRNO(code); goto _return; } } while (0)

-#define SCH_LOCK(type, _lock) (SCH_READ == (type) ? taosRLockLatch(_lock) : taosWLockLatch(_lock))
-#define SCH_UNLOCK(type, _lock) (SCH_READ == (type) ? taosRUnLockLatch(_lock) : taosWUnLockLatch(_lock))
+#define SCH_LOCK_DEBUG(...) do { if (gSCHDebug.lockEnable) { qDebug(__VA_ARGS__); } } while (0)
+
+#define TD_RWLATCH_WRITE_FLAG_COPY 0x40000000
+
+#define SCH_LOCK(type, _lock) do {   \
+  if (SCH_READ == (type)) {          \
+    assert(atomic_load_64(_lock) >= 0);  \
+    SCH_LOCK_DEBUG("SCH RLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    taosRLockLatch(_lock);           \
+    SCH_LOCK_DEBUG("SCH RLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64(_lock) > 0);  \
+  } else {                                                \
+    assert(atomic_load_64(_lock) >= 0);  \
+    SCH_LOCK_DEBUG("SCH WLOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__);  \
+    taosWLockLatch(_lock);                                \
+    SCH_LOCK_DEBUG("SCH WLOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__);  \
+    assert(atomic_load_64(_lock) & TD_RWLATCH_WRITE_FLAG_COPY);  \
+  }                                                       \
+} while (0)
+
+#define SCH_UNLOCK(type, _lock) do {                       \
+  if (SCH_READ == (type)) {                                \
+    assert(atomic_load_64((_lock)) > 0);  \
+    SCH_LOCK_DEBUG("SCH RULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    taosRUnLockLatch(_lock);                              \
+    SCH_LOCK_DEBUG("SCH RULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) >= 0);  \
+  } else {                                                \
+    assert(atomic_load_64((_lock)) & TD_RWLATCH_WRITE_FLAG_COPY);  \
+    SCH_LOCK_DEBUG("SCH WULOCK%p:%" PRIx64 ", %s:%d B", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    taosWUnLockLatch(_lock);                              \
+    SCH_LOCK_DEBUG("SCH WULOCK%p:%" PRIx64 ", %s:%d E", (_lock), atomic_load_64(_lock), __FILE__, __LINE__); \
+    assert(atomic_load_64((_lock)) >= 0);  \
+  }                                                       \
+} while (0)


 void    schDeregisterTaskHb(SSchJob *pJob, SSchTask *pTask);
@ -434,6 +472,9 @@ int32_t schLaunchLevelTasks(SSchJob *pJob, SSchLevel *level);
 int32_t schGetTaskFromList(SHashObj *pTaskList, uint64_t taskId, SSchTask **pTask);
 int32_t schInitTask(SSchJob *pJob, SSchTask *pTask, SSubplan *pPlan, SSchLevel *pLevel, int32_t levelNum);
 int32_t schSwitchTaskCandidateAddr(SSchJob *pJob, SSchTask *pTask);
+void    schDirectPostJobRes(SSchedulerReq* pReq, int32_t errCode);
+
+extern SSchDebug gSCHDebug;


 #ifdef __cplusplus
--- a/Show More
+++ b/Show More