xxq250
/
homework-jianmu
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge branch '3.0' into feat/agg_client_api

This commit is contained in:
Ganlin Zhao 2022-07-17 22:54:43 +08:00
parent 107cb15dbd e0c7137820
commit bcb7cb408d
117 changed files with 4349 additions and 1626 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
include/common/systable.h
View File

@ -35,6 +35,7 @@ extern "C" {
#define TSDB_INS_TABLE_USER_INDEXES "user_indexes"
#define TSDB_INS_TABLE_USER_STABLES "user_stables"
#define TSDB_INS_TABLE_USER_TABLES "user_tables"
#define TSDB_INS_TABLE_USER_TAGS "user_tags"
#define TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED "user_table_distributed"
#define TSDB_INS_TABLE_USER_USERS "user_users"
#define TSDB_INS_TABLE_LICENCES "grants"

20
include/common/tcommon.h
View File

@ -268,6 +268,26 @@ typedef struct SSortExecInfo {
int32_t readBytes; // read io bytes
} SSortExecInfo;
//======================================================================================================================
// for grant
typedef enum {
TSDB_GRANT_ALL,
TSDB_GRANT_TIME,
TSDB_GRANT_USER,
TSDB_GRANT_DB,
TSDB_GRANT_TIMESERIES,
TSDB_GRANT_DNODE,
TSDB_GRANT_ACCT,
TSDB_GRANT_STORAGE,
TSDB_GRANT_SPEED,
TSDB_GRANT_QUERY_TIME,
TSDB_GRANT_CONNS,
TSDB_GRANT_STREAMS,
TSDB_GRANT_CPU_CORES,
} EGrantType;
int32_t grantCheck(EGrantType grant);
#ifdef __cplusplus
}
#endif

1
include/common/tglobal.h
View File

@ -139,6 +139,7 @@ extern int32_t tsTransPullupInterval;
extern int32_t tsMqRebalanceInterval;
extern int32_t tsTtlUnit;
extern int32_t tsTtlPushInterval;
extern int32_t tsGrantHBInterval;
#define NEEDTO_COMPRESSS_MSG(size) (tsCompressMsgSize != -1 && (size) > tsCompressMsgSize)

143
include/common/tmsg.h
View File

@ -75,13 +75,18 @@ typedef uint16_t tmsg_t;
#define TSDB_IE_TYPE_DNODE_EXT 6
#define TSDB_IE_TYPE_DNODE_STATE 7
enum { CONN_TYPE__QUERY = 1, CONN_TYPE__TMQ, CONN_TYPE__UDFD, CONN_TYPE__MAX };
enum {
CONN_TYPE__QUERY = 1,
CONN_TYPE__TMQ,
CONN_TYPE__UDFD,
CONN_TYPE__MAX,
};
enum {
HEARTBEAT_KEY_USER_AUTHINFO = 1,
HEARTBEAT_KEY_DBINFO,
HEARTBEAT_KEY_STBINFO,
HEARTBEAT_KEY_MQ_TMP,
HEARTBEAT_KEY_TMQ,
};
typedef enum _mgmt_table {
@ -99,6 +104,7 @@ typedef enum _mgmt_table {
TSDB_MGMT_TABLE_STB,
TSDB_MGMT_TABLE_STREAMS,
TSDB_MGMT_TABLE_TABLE,
TSDB_MGMT_TABLE_TAG,
TSDB_MGMT_TABLE_USER,
TSDB_MGMT_TABLE_GRANTS,
TSDB_MGMT_TABLE_VGROUP,
@ -2146,6 +2152,15 @@ typedef struct {
char cgroup[TSDB_CGROUP_LEN];
} SMqAskEpReq;
typedef struct {
int64_t consumerId;
int32_t epoch;
} SMqHbReq;
typedef struct {
int8_t reserved;
} SMqHbRsp;
typedef struct {
int32_t key;
int32_t valueLen;
@ -2335,29 +2350,30 @@ static FORCE_INLINE int32_t tDecodeSClientHbKey(SDecoder* pDecoder, SClientHbKey
return 0;
}
typedef struct SMqHbVgInfo {
typedef struct {
int32_t vgId;
} SMqHbVgInfo;
// TODO stas
} SMqReportVgInfo;
static FORCE_INLINE int32_t taosEncodeSMqVgInfo(void** buf, const SMqHbVgInfo* pVgInfo) {
static FORCE_INLINE int32_t taosEncodeSMqVgInfo(void** buf, const SMqReportVgInfo* pVgInfo) {
int32_t tlen = 0;
tlen += taosEncodeFixedI32(buf, pVgInfo->vgId);
return tlen;
}
static FORCE_INLINE void* taosDecodeSMqVgInfo(void* buf, SMqHbVgInfo* pVgInfo) {
static FORCE_INLINE void* taosDecodeSMqVgInfo(void* buf, SMqReportVgInfo* pVgInfo) {
buf = taosDecodeFixedI32(buf, &pVgInfo->vgId);
return buf;
}
typedef struct SMqHbTopicInfo {
typedef struct {
int32_t epoch;
int64_t topicUid;
char name[TSDB_TOPIC_FNAME_LEN];
SArray* pVgInfo; // SArray<SMqHbVgInfo>
} SMqHbTopicInfo;
} SMqTopicInfo;
static FORCE_INLINE int32_t taosEncodeSMqHbTopicInfoMsg(void** buf, const SMqHbTopicInfo* pTopicInfo) {
static FORCE_INLINE int32_t taosEncodeSMqTopicInfoMsg(void** buf, const SMqTopicInfo* pTopicInfo) {
int32_t tlen = 0;
tlen += taosEncodeFixedI32(buf, pTopicInfo->epoch);
tlen += taosEncodeFixedI64(buf, pTopicInfo->topicUid);
@ -2365,35 +2381,35 @@ static FORCE_INLINE int32_t taosEncodeSMqHbTopicInfoMsg(void** buf, const SMqHbT
int32_t sz = taosArrayGetSize(pTopicInfo->pVgInfo);
tlen += taosEncodeFixedI32(buf, sz);
for (int32_t i = 0; i < sz; i++) {
SMqHbVgInfo* pVgInfo = (SMqHbVgInfo*)taosArrayGet(pTopicInfo->pVgInfo, i);
SMqReportVgInfo* pVgInfo = (SMqReportVgInfo*)taosArrayGet(pTopicInfo->pVgInfo, i);
tlen += taosEncodeSMqVgInfo(buf, pVgInfo);
}
return tlen;
}
static FORCE_INLINE void* taosDecodeSMqHbTopicInfoMsg(void* buf, SMqHbTopicInfo* pTopicInfo) {
static FORCE_INLINE void* taosDecodeSMqTopicInfoMsg(void* buf, SMqTopicInfo* pTopicInfo) {
buf = taosDecodeFixedI32(buf, &pTopicInfo->epoch);
buf = taosDecodeFixedI64(buf, &pTopicInfo->topicUid);
buf = taosDecodeStringTo(buf, pTopicInfo->name);
int32_t sz;
buf = taosDecodeFixedI32(buf, &sz);
pTopicInfo->pVgInfo = taosArrayInit(sz, sizeof(SMqHbVgInfo));
pTopicInfo->pVgInfo = taosArrayInit(sz, sizeof(SMqReportVgInfo));
for (int32_t i = 0; i < sz; i++) {
SMqHbVgInfo vgInfo;
SMqReportVgInfo vgInfo;
buf = taosDecodeSMqVgInfo(buf, &vgInfo);
taosArrayPush(pTopicInfo->pVgInfo, &vgInfo);
}
return buf;
}
typedef struct SMqHbMsg {
typedef struct {
int32_t status; // ask hb endpoint
int32_t epoch;
int64_t consumerId;
SArray* pTopics; // SArray<SMqHbTopicInfo>
} SMqHbMsg;
} SMqReportReq;
static FORCE_INLINE int32_t taosEncodeSMqMsg(void** buf, const SMqHbMsg* pMsg) {
static FORCE_INLINE int32_t taosEncodeSMqReportMsg(void** buf, const SMqReportReq* pMsg) {
int32_t tlen = 0;
tlen += taosEncodeFixedI32(buf, pMsg->status);
tlen += taosEncodeFixedI32(buf, pMsg->epoch);
@ -2401,22 +2417,22 @@ static FORCE_INLINE int32_t taosEncodeSMqMsg(void** buf, const SMqHbMsg* pMsg) {
int32_t sz = taosArrayGetSize(pMsg->pTopics);
tlen += taosEncodeFixedI32(buf, sz);
for (int32_t i = 0; i < sz; i++) {
SMqHbTopicInfo* topicInfo = (SMqHbTopicInfo*)taosArrayGet(pMsg->pTopics, i);
tlen += taosEncodeSMqHbTopicInfoMsg(buf, topicInfo);
SMqTopicInfo* topicInfo = (SMqTopicInfo*)taosArrayGet(pMsg->pTopics, i);
tlen += taosEncodeSMqTopicInfoMsg(buf, topicInfo);
}
return tlen;
}
static FORCE_INLINE void* taosDecodeSMqMsg(void* buf, SMqHbMsg* pMsg) {
static FORCE_INLINE void* taosDecodeSMqReportMsg(void* buf, SMqReportReq* pMsg) {
buf = taosDecodeFixedI32(buf, &pMsg->status);
buf = taosDecodeFixedI32(buf, &pMsg->epoch);
buf = taosDecodeFixedI64(buf, &pMsg->consumerId);
int32_t sz;
buf = taosDecodeFixedI32(buf, &sz);
pMsg->pTopics = taosArrayInit(sz, sizeof(SMqHbTopicInfo));
pMsg->pTopics = taosArrayInit(sz, sizeof(SMqTopicInfo));
for (int32_t i = 0; i < sz; i++) {
SMqHbTopicInfo topicInfo;
buf = taosDecodeSMqHbTopicInfoMsg(buf, &topicInfo);
SMqTopicInfo topicInfo;
buf = taosDecodeSMqTopicInfoMsg(buf, &topicInfo);
taosArrayPush(pMsg->pTopics, &topicInfo);
}
return buf;
@ -2921,89 +2937,6 @@ typedef struct {
int32_t tEncodeSMqDataRsp(SEncoder* pEncoder, const SMqDataRsp* pRsp);
int32_t tDecodeSMqDataRsp(SDecoder* pDecoder, SMqDataRsp* pRsp);
#if 0
typedef struct {
SMqRspHead head;
int64_t reqOffset;
int64_t rspOffset;
int32_t skipLogNum;
int32_t blockNum;
int8_t withTbName;
int8_t withSchema;
SArray* blockDataLen; // SArray<int32_t>
SArray* blockData; // SArray<SRetrieveTableRsp*>
SArray* blockTbName; // SArray<char*>
SArray* blockSchema; // SArray<SSchemaWrapper>
} SMqDataBlkRsp;
static FORCE_INLINE int32_t tEncodeSMqDataBlkRsp(void** buf, const SMqDataBlkRsp* pRsp) {
int32_t tlen = 0;
tlen += taosEncodeFixedI64(buf, pRsp->reqOffset);
tlen += taosEncodeFixedI64(buf, pRsp->rspOffset);
tlen += taosEncodeFixedI32(buf, pRsp->skipLogNum);
tlen += taosEncodeFixedI32(buf, pRsp->blockNum);
if (pRsp->blockNum != 0) {
tlen += taosEncodeFixedI8(buf, pRsp->withTbName);
tlen += taosEncodeFixedI8(buf, pRsp->withSchema);
for (int32_t i = 0; i < pRsp->blockNum; i++) {
int32_t bLen = *(int32_t*)taosArrayGet(pRsp->blockDataLen, i);
void* data = taosArrayGetP(pRsp->blockData, i);
tlen += taosEncodeFixedI32(buf, bLen);
tlen += taosEncodeBinary(buf, data, bLen);
if (pRsp->withSchema) {
SSchemaWrapper* pSW = (SSchemaWrapper*)taosArrayGetP(pRsp->blockSchema, i);
tlen += taosEncodeSSchemaWrapper(buf, pSW);
}
if (pRsp->withTbName) {
char* tbName = (char*)taosArrayGetP(pRsp->blockTbName, i);
tlen += taosEncodeString(buf, tbName);
}
}
}
return tlen;
}
static FORCE_INLINE void* tDecodeSMqDataBlkRsp(const void* buf, SMqDataBlkRsp* pRsp) {
buf = taosDecodeFixedI64(buf, &pRsp->reqOffset);
buf = taosDecodeFixedI64(buf, &pRsp->rspOffset);
buf = taosDecodeFixedI32(buf, &pRsp->skipLogNum);
buf = taosDecodeFixedI32(buf, &pRsp->blockNum);
if (pRsp->blockNum != 0) {
pRsp->blockData = taosArrayInit(pRsp->blockNum, sizeof(void*));
pRsp->blockDataLen = taosArrayInit(pRsp->blockNum, sizeof(int32_t));
buf = taosDecodeFixedI8(buf, &pRsp->withTbName);
buf = taosDecodeFixedI8(buf, &pRsp->withSchema);
if (pRsp->withTbName) {
pRsp->blockTbName = taosArrayInit(pRsp->blockNum, sizeof(void*));
}
if (pRsp->withSchema) {
pRsp->blockSchema = taosArrayInit(pRsp->blockNum, sizeof(void*));
}
for (int32_t i = 0; i < pRsp->blockNum; i++) {
int32_t bLen = 0;
void* data = NULL;
buf = taosDecodeFixedI32(buf, &bLen);
buf = taosDecodeBinary(buf, &data, bLen);
taosArrayPush(pRsp->blockDataLen, &bLen);
taosArrayPush(pRsp->blockData, &data);
if (pRsp->withSchema) {
SSchemaWrapper* pSW = (SSchemaWrapper*)taosMemoryMalloc(sizeof(SSchemaWrapper));
buf = taosDecodeSSchemaWrapper(buf, pSW);
taosArrayPush(pRsp->blockSchema, &pSW);
}
if (pRsp->withTbName) {
char* name = NULL;
buf = taosDecodeString(buf, &name);
taosArrayPush(pRsp->blockTbName, &name);
}
}
}
return (void*)buf;
}
#endif
typedef struct {
SMqRspHead head;
char cgroup[TSDB_CGROUP_LEN];

2
include/common/tmsgdef.h
View File

@ -144,6 +144,7 @@ enum {
TD_DEF_MSG_TYPE(TDMT_MND_MQ_ASK_EP, "ask-ep", SMqAskEpReq, SMqAskEpRsp)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_CONSUMER_LOST, "consumer-lost", SMqConsumerLostMsg, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_CONSUMER_RECOVER, "consumer-recover", SMqConsumerRecoverMsg, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_HB, "consumer-hb", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_DO_REBALANCE, "do-rebalance", SMqDoRebalanceMsg, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_DROP_CGROUP, "drop-cgroup", SMqDropCGroupReq, SMqDropCGroupRsp)
TD_DEF_MSG_TYPE(TDMT_MND_MQ_COMMIT_OFFSET, "mnode-commit-offset", SMqCMCommitOffsetReq, SMqCMCommitOffsetRsp)
@ -151,6 +152,7 @@ enum {
TD_DEF_MSG_TYPE(TDMT_MND_TELEM_TIMER, "telem-tmr", SMTimerReq, SMTimerReq)
TD_DEF_MSG_TYPE(TDMT_MND_TRANS_TIMER, "trans-tmr", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_TTL_TIMER, "ttl-tmr", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_GRANT_HB_TIMER, "grant-hb-tmr", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_KILL_TRANS, "kill-trans", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_KILL_QUERY, "kill-query", NULL, NULL)
TD_DEF_MSG_TYPE(TDMT_MND_KILL_CONN, "kill-conn", NULL, NULL)

1
include/libs/nodes/nodes.h
View File

@ -170,6 +170,7 @@ typedef enum ENodeType {
QUERY_NODE_SHOW_STABLES_STMT,
QUERY_NODE_SHOW_STREAMS_STMT,
QUERY_NODE_SHOW_TABLES_STMT,
QUERY_NODE_SHOW_TAGS_STMT,
QUERY_NODE_SHOW_USERS_STMT,
QUERY_NODE_SHOW_LICENCE_STMT,
QUERY_NODE_SHOW_VGROUPS_STMT,

2
include/libs/transport/trpc.h
View File

@ -135,7 +135,7 @@ void rpcSendRequestWithCtx(void *thandle, const SEpSet *pEpSet, SRpcMsg *pMsg
int32_t rpcGetConnInfo(void *thandle, SRpcConnInfo *pInfo);
void rpcSendRecv(void *shandle, SEpSet *pEpSet, SRpcMsg *pReq, SRpcMsg *pRsp);
void rpcSetDefaultAddr(void *thandle, const char *ip, const char *fqdn);
int64_t rpcAllocHandle();
void* rpcAllocHandle();
#ifdef __cplusplus
}

1
include/util/taoserror.h
View File

@ -332,7 +332,6 @@ int32_t* taosGetErrno();
#define TSDB_CODE_VND_INVALID_TABLE_ACTION TAOS_DEF_ERROR_CODE(0, 0x0519)
#define TSDB_CODE_VND_COL_ALREADY_EXISTS TAOS_DEF_ERROR_CODE(0, 0x051a)
#define TSDB_CODE_VND_TABLE_COL_NOT_EXISTS TAOS_DEF_ERROR_CODE(0, 0x051b)
#define TSDB_CODE_VND_READ_END TAOS_DEF_ERROR_CODE(0, 0x051c)
// tsdb
#define TSDB_CODE_TDB_INVALID_TABLE_ID TAOS_DEF_ERROR_CODE(0, 0x0600)

10
source/client/src/clientHb.c
View File

@ -171,6 +171,7 @@ static int32_t hbQueryHbRspHandle(SAppHbMgr *pAppHbMgr, SClientHbRsp *pRsp) {
pTscObj->pAppInfo->totalDnodes = pRsp->query->totalDnodes;
pTscObj->pAppInfo->onlineDnodes = pRsp->query->onlineDnodes;
pTscObj->connId = pRsp->query->connId;
tscTrace("conn %p hb rsp, dnodes %d/%d", pTscObj->connId, pTscObj->pAppInfo->onlineDnodes, pTscObj->pAppInfo->totalDnodes);
if (pRsp->query->killRid) {
tscDebug("request rid %" PRIx64 " need to be killed now", pRsp->query->killRid);
@ -294,6 +295,7 @@ static int32_t hbAsyncCallBack(void *param, SDataBuf *pMsg, int32_t code) {
if (code != 0) {
(*pInst)->onlineDnodes = ((*pInst)->totalDnodes ? 0 : -1);
tscDebug("hb rsp error %s, update server status %d/%d", tstrerror(code), (*pInst)->onlineDnodes, (*pInst)->totalDnodes);
}
if (rspNum) {
@ -571,7 +573,8 @@ int32_t hbQueryHbReqHandle(SClientHbKey *connKey, void *param, SClientHbReq *req
return TSDB_CODE_SUCCESS;
}
void hbMgrInitMqHbHandle() {
static FORCE_INLINE void hbMgrInitHandle() {
// init all handle
clientHbMgr.reqHandle[CONN_TYPE__QUERY] = hbQueryHbReqHandle;
clientHbMgr.reqHandle[CONN_TYPE__TMQ] = hbMqHbReqHandle;
@ -579,11 +582,6 @@ void hbMgrInitMqHbHandle() {
clientHbMgr.rspHandle[CONN_TYPE__TMQ] = hbMqHbRspHandle;
}
static FORCE_INLINE void hbMgrInitHandle() {
// init all handle
hbMgrInitMqHbHandle();
}
SClientHbBatchReq *hbGatherAllInfo(SAppHbMgr *pAppHbMgr) {
SClientHbBatchReq *pBatchReq = taosMemoryCalloc(1, sizeof(SClientHbBatchReq));
if (pBatchReq == NULL) {

7
source/client/src/clientImpl.c
View File

@ -1276,7 +1276,12 @@ int32_t doProcessMsgFromServer(void* param) {
assert(pMsg->info.ahandle != NULL);
STscObj* pTscObj = NULL;
tscDebug("processMsgFromServer message: %s, code: %s", TMSG_INFO(pMsg->msgType), tstrerror(pMsg->code));
STraceId* trace = &pMsg->info.traceId;
char tbuf[40] = {0};
TRACE_TO_STR(trace, tbuf);
tscDebug("processMsgFromServer handle %p, message: %s, code: %s, gtid: %s", pMsg->info.handle, TMSG_INFO(pMsg->msgType), tstrerror(pMsg->code),
tbuf);
if (pSendInfo->requestObjRefId != 0) {
SRequestObj* pRequest = (SRequestObj*)taosAcquireRef(clientReqRefPool, pSendInfo->requestObjRefId);

563
source/client/src/tmq.c
View File

File diff suppressed because it is too large Load Diff

10
source/common/src/systable.c
View File

@ -153,6 +153,15 @@ static const SSysDbTableSchema userTblsSchema[] = {
{.name = "type", .bytes = 21 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
};
static const SSysDbTableSchema userTagsSchema[] = {
{.name = "table_name", .bytes = SYSTABLE_SCH_TABLE_NAME_LEN, .type = TSDB_DATA_TYPE_VARCHAR},
{.name = "db_name", .bytes = SYSTABLE_SCH_DB_NAME_LEN, .type = TSDB_DATA_TYPE_VARCHAR},
{.name = "stable_name", .bytes = SYSTABLE_SCH_TABLE_NAME_LEN, .type = TSDB_DATA_TYPE_VARCHAR},
{.name = "tag_name", .bytes = TSDB_COL_NAME_LEN - 1 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
{.name = "tag_type", .bytes = 1, .type = TSDB_DATA_TYPE_TINYINT},
{.name = "tag_value", .bytes = TSDB_MAX_TAGS_LEN + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
};
static const SSysDbTableSchema userTblDistSchema[] = {
{.name = "db_name", .bytes = 32 + VARSTR_HEADER_SIZE, .type = TSDB_DATA_TYPE_VARCHAR},
{.name = "table_name", .bytes = SYSTABLE_SCH_DB_NAME_LEN, .type = TSDB_DATA_TYPE_VARCHAR},
@ -255,6 +264,7 @@ static const SSysTableMeta infosMeta[] = {
{TSDB_INS_TABLE_USER_STABLES, userStbsSchema, tListLen(userStbsSchema)},
{TSDB_PERFS_TABLE_STREAMS, streamSchema, tListLen(streamSchema)},
{TSDB_INS_TABLE_USER_TABLES, userTblsSchema, tListLen(userTblsSchema)},
{TSDB_INS_TABLE_USER_TAGS, userTagsSchema, tListLen(userTagsSchema)},
// {TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED, userTblDistSchema, tListLen(userTblDistSchema)},
{TSDB_INS_TABLE_USER_USERS, userUsersSchema, tListLen(userUsersSchema)},
{TSDB_INS_TABLE_LICENCES, grantsSchema, tListLen(grantsSchema)},

2
source/common/src/tdatablock.c
View File

@ -1752,7 +1752,7 @@ char* dumpBlockData(SSDataBlock* pDataBlock, const char* flag, char** pDataBuf)
int32_t colNum = taosArrayGetSize(pDataBlock->pDataBlock);
int32_t rows = pDataBlock->info.rows;
int32_t len = 0;
len += snprintf(dumpBuf + len, size - len, "%s |block type %d |child id %d|group id:%" PRIu64 "| uid:%ld|======\n", "dumpBlockData",
len += snprintf(dumpBuf + len, size - len, "===stream===%s |block type %d |child id %d|group id:%" PRIu64 "| uid:%ld|\n", flag,
(int32_t)pDataBlock->info.type, pDataBlock->info.childId, pDataBlock->info.groupId,
pDataBlock->info.uid);
if (len >= size - 1) return dumpBuf;

1
source/common/src/tglobal.c
View File

@ -184,6 +184,7 @@ int32_t tsTransPullupInterval = 2;
int32_t tsMqRebalanceInterval = 2;
int32_t tsTtlUnit = 86400;
int32_t tsTtlPushInterval = 60;
int32_t tsGrantHBInterval = 60;
void taosAddDataDir(int32_t index, char *v1, int32_t level, int32_t primary) {
tstrncpy(tsDiskCfg[index].dir, v1, TSDB_FILENAME_LEN);

1
source/dnode/mgmt/mgmt_dnode/inc/dmInt.h
View File

@ -46,6 +46,7 @@ int32_t dmProcessAuthRsp(SDnodeMgmt *pMgmt, SRpcMsg *pMsg);
int32_t dmProcessGrantRsp(SDnodeMgmt *pMgmt, SRpcMsg *pMsg);
int32_t dmProcessServerRunStatus(SDnodeMgmt *pMgmt, SRpcMsg *pMsg);
int32_t dmProcessRetrieve(SDnodeMgmt *pMgmt, SRpcMsg *pMsg);
int32_t dmProcessGrantReq(SRpcMsg *pMsg);
// dmWorker.c
int32_t dmPutNodeMsgToMgmtQueue(SDnodeMgmt *pMgmt, SRpcMsg *pMsg);

3
source/dnode/mgmt/mgmt_dnode/src/dmHandle.c
View File

@ -331,7 +331,8 @@ SArray *dmGetMsgHandles() {
if (dmSetMgmtHandle(pArray, TDMT_DND_SYSTABLE_RETRIEVE, dmPutNodeMsgToMgmtQueue, 0) == NULL) goto _OVER;
// Requests handled by MNODE
if (dmSetMgmtHandle(pArray, TDMT_MND_GRANT_RSP, dmPutNodeMsgToMgmtQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_GRANT, dmPutNodeMsgToMgmtQueue, 0) == NULL) goto _OVER;
// if (dmSetMgmtHandle(pArray, TDMT_MND_GRANT_RSP, dmPutNodeMsgToMgmtQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_AUTH_RSP, dmPutNodeMsgToMgmtQueue, 0) == NULL) goto _OVER;
code = 0;

3
source/dnode/mgmt/mgmt_dnode/src/dmWorker.c
View File

@ -144,6 +144,9 @@ static void dmProcessMgmtQueue(SQueueInfo *pInfo, SRpcMsg *pMsg) {
case TDMT_DND_SYSTABLE_RETRIEVE:
code = dmProcessRetrieve(pMgmt, pMsg);
break;
case TDMT_MND_GRANT:
code = dmProcessGrantReq(pMsg);
break;
default:
terrno = TSDB_CODE_MSG_NOT_PROCESSED;
break;

3
source/dnode/mgmt/mgmt_mnode/src/mmHandle.c
View File

@ -196,6 +196,7 @@ SArray *mmGetMsgHandles() {
if (dmSetMgmtHandle(pArray, TDMT_MND_DROP_TOPIC, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_SUBSCRIBE, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_MQ_ASK_EP, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_MQ_HB, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_MQ_DROP_CGROUP, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_MQ_DROP_CGROUP_RSP, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_MQ_COMMIT_OFFSET, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
@ -205,7 +206,7 @@ SArray *mmGetMsgHandles() {
if (dmSetMgmtHandle(pArray, TDMT_MND_HEARTBEAT, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_STATUS, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_SYSTABLE_RETRIEVE, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_GRANT, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
// if (dmSetMgmtHandle(pArray, TDMT_MND_GRANT, mmPutMsgToWriteQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_AUTH, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_SHOW_VARIABLES, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;
if (dmSetMgmtHandle(pArray, TDMT_MND_SERVER_VERSION, mmPutMsgToReadQueue, 0) == NULL) goto _OVER;

1
source/dnode/mgmt/mgmt_qnode/src/qmWorker.c
View File

@ -81,6 +81,7 @@ int32_t qmPutRpcMsgToQueue(SQnodeMgmt *pMgmt, EQueueType qtype, SRpcMsg *pRpc) {
taosWriteQitem(pMgmt->queryWorker.queue, pMsg);
return 0;
case READ_QUEUE:
case FETCH_QUEUE:
dTrace("msg:%p, is created and will put into qnode-fetch queue", pMsg);
taosWriteQitem(pMgmt->fetchWorker.queue, pMsg);
return 0;

22
source/dnode/mgmt/mgmt_vnode/src/vmWorker.c
View File

@ -153,9 +153,15 @@ static int32_t vmPutMsgToQueue(SVnodeMgmt *pMgmt, SRpcMsg *pMsg, EQueueType qtyp
switch (qtype) {
case QUERY_QUEUE:
vnodePreprocessQueryMsg(pVnode->pImpl, pMsg);
dGTrace("vgId:%d, msg:%p put into vnode-query queue", pVnode->vgId, pMsg);
taosWriteQitem(pVnode->pQueryQ, pMsg);
if ((pMsg->msgType == TDMT_SCH_QUERY) && (grantCheck(TSDB_GRANT_TIME) != TSDB_CODE_SUCCESS)) {
terrno = TSDB_CODE_GRANT_EXPIRED;
code = terrno;
dDebug("vgId:%d, msg:%p put into vnode-query queue failed since %s", pVnode->vgId, pMsg, terrstr());
} else {
vnodePreprocessQueryMsg(pVnode->pImpl, pMsg);
dGTrace("vgId:%d, msg:%p put into vnode-query queue", pVnode->vgId, pMsg);
taosWriteQitem(pVnode->pQueryQ, pMsg);
}
break;
case STREAM_QUEUE:
dGTrace("vgId:%d, msg:%p put into vnode-stream queue", pVnode->vgId, pMsg);
@ -166,8 +172,14 @@ static int32_t vmPutMsgToQueue(SVnodeMgmt *pMgmt, SRpcMsg *pMsg, EQueueType qtyp
taosWriteQitem(pVnode->pFetchQ, pMsg);
break;
case WRITE_QUEUE:
dGTrace("vgId:%d, msg:%p put into vnode-write queue", pVnode->vgId, pMsg);
taosWriteQitem(pVnode->pWriteQ, pMsg);
if ((pMsg->msgType == TDMT_VND_SUBMIT) && (grantCheck(TSDB_GRANT_STORAGE) != TSDB_CODE_SUCCESS)) {
terrno = TSDB_CODE_VND_NO_WRITE_AUTH;
code = terrno;
dDebug("vgId:%d, msg:%p put into vnode-write queue failed since %s", pVnode->vgId, pMsg, terrstr());
} else {
dGTrace("vgId:%d, msg:%p put into vnode-write queue", pVnode->vgId, pMsg);
taosWriteQitem(pVnode->pWriteQ, pMsg);
}
break;
case SYNC_QUEUE:
dGTrace("vgId:%d, msg:%p put into vnode-sync queue", pVnode->vgId, pMsg);

1
source/dnode/mnode/impl/inc/mndCluster.h
View File

@ -26,6 +26,7 @@ int32_t mndInitCluster(SMnode *pMnode);
void mndCleanupCluster(SMnode *pMnode);
int32_t mndGetClusterName(SMnode *pMnode, char *clusterName, int32_t len);
int64_t mndGetClusterId(SMnode *pMnode);
int64_t mndGetClusterCreateTime(SMnode *pMnode);
#ifdef __cplusplus
}

1
source/dnode/mnode/impl/inc/mndDnode.h
View File

@ -29,6 +29,7 @@ void mndReleaseDnode(SMnode *pMnode, SDnodeObj *pDnode);
SEpSet mndGetDnodeEpset(SDnodeObj *pDnode);
int32_t mndGetDnodeSize(SMnode *pMnode);
bool mndIsDnodeOnline(SDnodeObj *pDnode, int64_t curMs);
void mndGetDnodeData(SMnode *pMnode, SArray *pDnodeEps);
#ifdef __cplusplus
}

21
source/dnode/mnode/impl/inc/mndGrant.h
View File

@ -22,27 +22,10 @@
#include "mndInt.h"
typedef enum {
TSDB_GRANT_ALL,
TSDB_GRANT_TIME,
TSDB_GRANT_USER,
TSDB_GRANT_DB,
TSDB_GRANT_TIMESERIES,
TSDB_GRANT_DNODE,
TSDB_GRANT_ACCT,
TSDB_GRANT_STORAGE,
TSDB_GRANT_SPEED,
TSDB_GRANT_QUERY_TIME,
TSDB_GRANT_CONNS,
TSDB_GRANT_STREAMS,
TSDB_GRANT_CPU_CORES,
} EGrantType;
int32_t mndInitGrant();
int32_t mndInitGrant(SMnode *pMnode);
void mndCleanupGrant();
void grantParseParameter();
int32_t grantCheck(EGrantType grant);
void grantReset(EGrantType grant, uint64_t value);
void grantReset(SMnode *pMnode, EGrantType grant, uint64_t value);
void grantAdd(EGrantType grant, uint64_t value);
void grantRestore(EGrantType grant, uint64_t value);

17
source/dnode/mnode/impl/src/mndCluster.c
View File

@ -79,6 +79,23 @@ int64_t mndGetClusterId(SMnode *pMnode) {
return clusterId;
}
int64_t mndGetClusterCreateTime(SMnode *pMnode) {
SSdb *pSdb = pMnode->pSdb;
void *pIter = NULL;
int64_t createTime = INT64_MAX;
while (1) {
SClusterObj *pCluster = NULL;
pIter = sdbFetch(pSdb, SDB_CLUSTER, pIter, (void **)&pCluster);
if (pIter == NULL) break;
createTime = pCluster->createdTime;
sdbRelease(pSdb, pCluster);
}
return createTime;
}
static SSdbRaw *mndClusterActionEncode(SClusterObj *pCluster) {
terrno = TSDB_CODE_OUT_OF_MEMORY;

61
source/dnode/mnode/impl/src/mndConsumer.c
View File

@ -48,6 +48,7 @@ static void mndCancelGetNextConsumer(SMnode *pMnode, void *pIter);
static int32_t mndProcessSubscribeReq(SRpcMsg *pMsg);
static int32_t mndProcessAskEpReq(SRpcMsg *pMsg);
static int32_t mndProcessMqHbReq(SRpcMsg *pMsg);
static int32_t mndProcessMqTimerMsg(SRpcMsg *pMsg);
static int32_t mndProcessConsumerLostMsg(SRpcMsg *pMsg);
static int32_t mndProcessConsumerRecoverMsg(SRpcMsg *pMsg);
@ -62,6 +63,7 @@ int32_t mndInitConsumer(SMnode *pMnode) {
.deleteFp = (SdbDeleteFp)mndConsumerActionDelete};
mndSetMsgHandle(pMnode, TDMT_MND_SUBSCRIBE, mndProcessSubscribeReq);
mndSetMsgHandle(pMnode, TDMT_MND_MQ_HB, mndProcessMqHbReq);
mndSetMsgHandle(pMnode, TDMT_MND_MQ_ASK_EP, mndProcessAskEpReq);
mndSetMsgHandle(pMnode, TDMT_MND_MQ_TIMER, mndProcessMqTimerMsg);
mndSetMsgHandle(pMnode, TDMT_MND_MQ_CONSUMER_LOST, mndProcessConsumerLostMsg);
@ -255,24 +257,15 @@ static int32_t mndProcessMqTimerMsg(SRpcMsg *pMsg) {
return 0;
}
static int32_t mndProcessAskEpReq(SRpcMsg *pMsg) {
SMnode *pMnode = pMsg->info.node;
SMqAskEpReq *pReq = (SMqAskEpReq *)pMsg->pCont;
SMqAskEpRsp rsp = {0};
int64_t consumerId = be64toh(pReq->consumerId);
int32_t epoch = ntohl(pReq->epoch);
static int32_t mndProcessMqHbReq(SRpcMsg *pMsg) {
SMnode *pMnode = pMsg->info.node;
SMqHbReq *pReq = (SMqHbReq *)pMsg->pCont;
int64_t consumerId = be64toh(pReq->consumerId);
SMqConsumerObj *pConsumer = mndAcquireConsumer(pMsg->info.node, consumerId);
if (pConsumer == NULL) {
terrno = TSDB_CODE_MND_CONSUMER_NOT_EXIST;
return -1;
}
SMqConsumerObj *pConsumer = mndAcquireConsumer(pMnode, consumerId);
ASSERT(strcmp(pReq->cgroup, pConsumer->cgroup) == 0);
/*int32_t hbStatus = atomic_load_32(&pConsumer->hbStatus);*/
atomic_store_32(&pConsumer->hbStatus, 0);
// 1. check consumer status
int32_t status = atomic_load_32(&pConsumer->status);
if (status == MQ_CONSUMER_STATUS__LOST_REBD) {
@ -286,6 +279,46 @@ static int32_t mndProcessAskEpReq(SRpcMsg *pMsg) {
tmsgPutToQueue(&pMnode->msgCb, WRITE_QUEUE, pRpcMsg);
}
mndReleaseConsumer(pMnode, pConsumer);
return 0;
}
static int32_t mndProcessAskEpReq(SRpcMsg *pMsg) {
SMnode *pMnode = pMsg->info.node;
SMqAskEpReq *pReq = (SMqAskEpReq *)pMsg->pCont;
SMqAskEpRsp rsp = {0};
int64_t consumerId = be64toh(pReq->consumerId);
int32_t epoch = ntohl(pReq->epoch);
SMqConsumerObj *pConsumer = mndAcquireConsumer(pMnode, consumerId);
if (pConsumer == NULL) {
terrno = TSDB_CODE_MND_CONSUMER_NOT_EXIST;
return -1;
}
ASSERT(strcmp(pReq->cgroup, pConsumer->cgroup) == 0);
#if 1
atomic_store_32(&pConsumer->hbStatus, 0);
#endif
// 1. check consumer status
int32_t status = atomic_load_32(&pConsumer->status);
#if 1
if (status == MQ_CONSUMER_STATUS__LOST_REBD) {
SMqConsumerRecoverMsg *pRecoverMsg = rpcMallocCont(sizeof(SMqConsumerRecoverMsg));
pRecoverMsg->consumerId = consumerId;
SRpcMsg *pRpcMsg = taosMemoryCalloc(1, sizeof(SRpcMsg));
pRpcMsg->msgType = TDMT_MND_MQ_CONSUMER_RECOVER;
pRpcMsg->pCont = pRecoverMsg;
pRpcMsg->contLen = sizeof(SMqConsumerRecoverMsg);
tmsgPutToQueue(&pMnode->msgCb, WRITE_QUEUE, pRpcMsg);
}
#endif
if (status != MQ_CONSUMER_STATUS__READY) {
terrno = TSDB_CODE_MND_CONSUMER_NOT_READY;
return -1;

6
source/dnode/mnode/impl/src/mndDb.c
View File

@ -509,6 +509,12 @@ static int32_t mndProcessCreateDbReq(SRpcMsg *pReq) {
SUserObj *pUser = NULL;
SCreateDbReq createReq = {0};
code = grantCheck(TSDB_GRANT_DB);
if (code != 0) {
terrno = code;
goto _OVER;
}
if (tDeserializeSCreateDbReq(pReq->pCont, pReq->contLen, &createReq) != 0) {
terrno = TSDB_CODE_INVALID_MSG;
goto _OVER;

8
source/dnode/mnode/impl/src/mndDnode.c
View File

@ -262,7 +262,7 @@ bool mndIsDnodeOnline(SDnodeObj *pDnode, int64_t curMs) {
return true;
}
static void mndGetDnodeData(SMnode *pMnode, SArray *pDnodeEps) {
void mndGetDnodeData(SMnode *pMnode, SArray *pDnodeEps) {
SSdb *pSdb = pMnode->pSdb;
int32_t numOfEps = 0;
@ -621,6 +621,12 @@ static int32_t mndProcessCreateDnodeReq(SRpcMsg *pReq) {
SDnodeObj *pDnode = NULL;
SCreateDnodeReq createReq = {0};
code = grantCheck(TSDB_GRANT_DNODE);
if (code != TSDB_CODE_SUCCESS) {
terrno = code;
goto _OVER;
}
if (tDeserializeSCreateDnodeReq(pReq->pCont, pReq->contLen, &createReq) != 0) {
terrno = TSDB_CODE_INVALID_MSG;
goto _OVER;

6
source/dnode/mnode/impl/src/mndGrant.c
View File

@ -118,17 +118,21 @@ static int32_t mndRetrieveGrant(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *pBl
return numOfRows;
}
static int32_t mndProcessGrantHB(SRpcMsg *pReq) { return TSDB_CODE_SUCCESS; }
int32_t mndInitGrant(SMnode *pMnode) {
mndAddShowRetrieveHandle(pMnode, TSDB_MGMT_TABLE_GRANTS, mndRetrieveGrant);
mndSetMsgHandle(pMnode, TDMT_MND_GRANT_HB_TIMER, mndProcessGrantHB);
return 0;
}
void mndCleanupGrant() {}
void grantParseParameter() { mError("can't parsed parameter k"); }
int32_t grantCheck(EGrantType grant) { return TSDB_CODE_SUCCESS; }
void grantReset(EGrantType grant, uint64_t value) {}
void grantReset(SMnode *pMnode, EGrantType grant, uint64_t value) {}
void grantAdd(EGrantType grant, uint64_t value) {}
void grantRestore(EGrantType grant, uint64_t value) {}
int32_t dmProcessGrantReq(SRpcMsg *pMsg) { return TSDB_CODE_SUCCESS; }
#endif

17
source/dnode/mnode/impl/src/mndMain.c
View File

@ -90,6 +90,16 @@ static void mndPullupTelem(SMnode *pMnode) {
}
}
static void mndGrantHeartBeat(SMnode *pMnode) {
int32_t contLen = 0;
void *pReq = mndBuildTimerMsg(&contLen);
if (pReq != NULL) {
SRpcMsg rpcMsg = {
.msgType = TDMT_MND_GRANT_HB_TIMER, .pCont = pReq, .contLen = contLen, .info.ahandle = (void *)0x9527};
tmsgPutToQueue(&pMnode->msgCb, READ_QUEUE, &rpcMsg);
}
}
static void *mndThreadFp(void *param) {
SMnode *pMnode = param;
int64_t lastTime = 0;
@ -115,6 +125,10 @@ static void *mndThreadFp(void *param) {
if (lastTime % (tsTelemInterval * 10) == 0) {
mndPullupTelem(pMnode);
}
if (lastTime % (tsGrantHBInterval * 10) == 0) {
mndGrantHeartBeat(pMnode);
}
}
return NULL;
@ -402,6 +416,9 @@ int32_t mndStart(SMnode *pMnode) {
}
mndSetRestore(pMnode, true);
}
grantReset(pMnode, TSDB_GRANT_ALL, 0);
return mndInitTimer(pMnode);
}

62
source/dnode/mnode/impl/src/mndProfile.c
View File

@ -388,67 +388,7 @@ static void mndCancelGetNextApp(SMnode *pMnode, void *pIter) {
}
static SClientHbRsp *mndMqHbBuildRsp(SMnode *pMnode, SClientHbReq *pReq) {
#if 0
SClientHbRsp* pRsp = taosMemoryMalloc(sizeof(SClientHbRsp));
if (pRsp == NULL) {
terrno = TSDB_CODE_OUT_OF_MEMORY;
return NULL;
}
pRsp->connKey = pReq->connKey;
SMqHbBatchRsp batchRsp;
batchRsp.batchRsps = taosArrayInit(0, sizeof(SMqHbRsp));
if (batchRsp.batchRsps == NULL) {
terrno = TSDB_CODE_OUT_OF_MEMORY;
return NULL;
}
SClientHbKey connKey = pReq->connKey;
SHashObj* pObj = pReq->info;
SKv* pKv = taosHashGet(pObj, "mq-tmp", strlen("mq-tmp") + 1);
if (pKv == NULL) {
taosMemoryFree(pRsp);
return NULL;
}
SMqHbMsg mqHb;
taosDecodeSMqMsg(pKv->value, &mqHb);
/*int64_t clientUid = htonl(pKv->value);*/
/*if (mqHb.epoch )*/
int sz = taosArrayGetSize(mqHb.pTopics);
SMqConsumerObj* pConsumer = mndAcquireConsumer(pMnode, mqHb.consumerId);
for (int i = 0; i < sz; i++) {
SMqHbOneTopicBatchRsp innerBatchRsp;
innerBatchRsp.rsps = taosArrayInit(sz, sizeof(SMqHbRsp));
if (innerBatchRsp.rsps == NULL) {
//TODO
terrno = TSDB_CODE_OUT_OF_MEMORY;
return NULL;
}
SMqHbTopicInfo* topicInfo = taosArrayGet(mqHb.pTopics, i);
SMqConsumerTopic* pConsumerTopic = taosHashGet(pConsumer->topicHash, topicInfo->name, strlen(topicInfo->name)+1);
if (pConsumerTopic->epoch != topicInfo->epoch) {
//add new vgids into rsp
int vgSz = taosArrayGetSize(topicInfo->pVgInfo);
for (int j = 0; j < vgSz; j++) {
SMqHbRsp innerRsp;
SMqHbVgInfo* pVgInfo = taosArrayGet(topicInfo->pVgInfo, i);
SVgObj* pVgObj = mndAcquireVgroup(pMnode, pVgInfo->vgId);
innerRsp.epSet = mndGetVgroupEpset(pMnode, pVgObj);
taosArrayPush(innerBatchRsp.rsps, &innerRsp);
}
}
taosArrayPush(batchRsp.batchRsps, &innerBatchRsp);
}
int32_t tlen = taosEncodeSMqHbBatchRsp(NULL, &batchRsp);
void* buf = taosMemoryMalloc(tlen);
if (buf == NULL) {
//TODO
return NULL;
}
void* abuf = buf;
taosEncodeSMqHbBatchRsp(&abuf, &batchRsp);
pRsp->body = buf;
pRsp->bodyLen = tlen;
return pRsp;
#endif
//
return NULL;
}

2
source/dnode/mnode/impl/src/mndShow.c
View File

@ -76,6 +76,8 @@ static int32_t convertToRetrieveType(char *name, int32_t len) {
type = TSDB_MGMT_TABLE_STB;
} else if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, len) == 0) {
type = TSDB_MGMT_TABLE_TABLE;
} else if (strncasecmp(name, TSDB_INS_TABLE_USER_TAGS, len) == 0) {
type = TSDB_MGMT_TABLE_TAG;
} else if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED, len) == 0) {
// type = TSDB_MGMT_TABLE_DIST;
} else if (strncasecmp(name, TSDB_INS_TABLE_USER_USERS, len) == 0) {

2
source/dnode/mnode/impl/src/mndSma.c
View File

@ -709,7 +709,7 @@ static int32_t mndProcessCreateSmaReq(SRpcMsg *pReq) {
_OVER:
if (code != 0 && code != TSDB_CODE_ACTION_IN_PROGRESS) {
mError("sma:%s, failed to create since %s", createReq.name, terrstr(terrno));
mError("sma:%s, failed to create since %s", createReq.name, terrstr());
}
mndReleaseStb(pMnode, pStb);

5
source/dnode/mnode/impl/src/mndStb.c
View File

@ -1689,6 +1689,9 @@ static int32_t mndAlterStb(SMnode *pMnode, SRpcMsg *pReq, const SMAlterStbReq *p
_OVER:
taosMemoryFreeClear(stbObj.pTags);
taosMemoryFreeClear(stbObj.pColumns);
if (pAlter->commentLen > 0) {
taosMemoryFreeClear(stbObj.comment);
}
return code;
}
@ -1733,7 +1736,7 @@ _OVER:
mndReleaseStb(pMnode, pStb);
mndReleaseDb(pMnode, pDb);
taosArrayDestroy(alterReq.pFields);
tFreeSMAltertbReq(&alterReq);
return code;
}

6
source/dnode/mnode/impl/src/mndUser.c
View File

@ -363,6 +363,12 @@ static int32_t mndProcessCreateUserReq(SRpcMsg *pReq) {
goto _OVER;
}
code = grantCheck(TSDB_GRANT_USER);
if (code != TSDB_CODE_SUCCESS) {
terrno = code;
goto _OVER;
}
code = mndCreateUser(pMnode, pOperUser->acct, &createReq, pReq);
if (code == 0) code = TSDB_CODE_ACTION_IN_PROGRESS;

1
source/dnode/mnode/impl/src/mndVgroup.c
View File

@ -639,6 +639,7 @@ static int32_t mndRetrieveVgroups(SRpcMsg *pReq, SShowObj *pShow, SSDataBlock *p
if (pShow->pIter == NULL) break;
if (pDb != NULL && pVgroup->dbUid != pDb->uid) {
sdbRelease(pSdb, pVgroup);
continue;
}

2
source/dnode/vnode/inc/vnode.h
View File

@ -138,7 +138,7 @@ void *tsdbGetIdx(SMeta *pMeta);
void *tsdbGetIvtIdx(SMeta *pMeta);
int32_t tsdbLastRowReaderOpen(void *pVnode, int32_t type, SArray *pTableIdList, int32_t numOfCols, void **pReader);
int32_t tsdbRetrieveLastRow(void *pReader, SSDataBlock *pResBlock, const int32_t *slotIds, SArray* pTableUids);
int32_t tsdbRetrieveLastRow(void *pReader, SSDataBlock *pResBlock, const int32_t *slotIds, SArray *pTableUids);
int32_t tsdbLastrowReaderClose(void *pReader);
int32_t tsdbGetTableSchema(SVnode *pVnode, int64_t uid, STSchema **pSchema, int64_t *suid);

88
source/dnode/vnode/src/inc/sma.h
View File

@ -32,6 +32,8 @@ extern "C" {
#define smaTrace(...) do { if (smaDebugFlag & DEBUG_TRACE) { taosPrintLog("SMA ", DEBUG_TRACE, tsdbDebugFlag, __VA_ARGS__); }} while(0)
// clang-format on
#define RSMA_TASK_INFO_HASH_SLOT 8
typedef struct SSmaEnv SSmaEnv;
typedef struct SSmaStat SSmaStat;
typedef struct STSmaStat STSmaStat;
@ -41,7 +43,7 @@ typedef struct SRSmaInfo SRSmaInfo;
typedef struct SRSmaInfoItem SRSmaInfoItem;
struct SSmaEnv {
TdThreadRwlock lock;
SRWLatch lock;
int8_t type;
SSmaStat *pStat;
};
@ -52,7 +54,7 @@ typedef struct {
void *tmrHandle; // shared by all fetch tasks
} SSmaMgmt;
#define SMA_ENV_LOCK(env) ((env)->lock)
#define SMA_ENV_LOCK(env) (&(env)->lock)
#define SMA_ENV_TYPE(env) ((env)->type)
#define SMA_ENV_STAT(env) ((env)->pStat)
@ -64,10 +66,14 @@ struct STSmaStat {
struct SRSmaStat {
SSma *pSma;
int64_t submitVer;
int64_t refId; // shared by fetch tasks
int8_t triggerStat; // shared by fetch tasks
SHashObj *rsmaInfoHash; // key: stbUid, value: SRSmaInfo;
int64_t commitAppliedVer; // vnode applied version for async commit
int64_t commitSubmitVer; // rsma submit version for async commit
int64_t submitVer; // latest submit version
int64_t refId; // shared by fetch tasks
int8_t triggerStat; // shared by fetch tasks
int8_t commitStat; // 0 not in committing, 1 in committing
SHashObj *rsmaInfoHash; // key: stbUid, value: SRSmaInfo;
SHashObj *iRsmaInfoHash; // key: stbUid, value: SRSmaInfo; immutable rsmaInfoHash
};
struct SSmaStat {
@ -78,12 +84,29 @@ struct SSmaStat {
T_REF_DECLARE()
};
#define SMA_TSMA_STAT(s) (&(s)->tsmaStat)
#define SMA_RSMA_STAT(s) (&(s)->rsmaStat)
#define RSMA_INFO_HASH(r) ((r)->rsmaInfoHash)
#define RSMA_TRIGGER_STAT(r) (&(r)->triggerStat)
#define RSMA_REF_ID(r) ((r)->refId)
#define RSMA_SUBMIT_VER(r) ((r)->submitVer)
#define SMA_TSMA_STAT(s) (&(s)->tsmaStat)
#define SMA_RSMA_STAT(s) (&(s)->rsmaStat)
#define RSMA_INFO_HASH(r) ((r)->rsmaInfoHash)
#define RSMA_IMU_INFO_HASH(r) ((r)->iRsmaInfoHash)
#define RSMA_TRIGGER_STAT(r) (&(r)->triggerStat)
#define RSMA_COMMIT_STAT(r) (&(r)->commitStat)
#define RSMA_REF_ID(r) ((r)->refId)
#define RSMA_SUBMIT_VER(r) ((r)->submitVer)
struct SRSmaInfoItem {
void *taskInfo; // qTaskInfo_t
int64_t refId;
tmr_h tmrId;
int32_t maxDelay;
int8_t level;
int8_t triggerStat;
};
struct SRSmaInfo {
STSchema *pTSchema;
int64_t suid;
SRSmaInfoItem items[TSDB_RETENTION_L2];
};
enum {
TASK_TRIGGER_STAT_INIT = 0,
@ -94,6 +117,14 @@ enum {
TASK_TRIGGER_STAT_DROPPED = 5,
};
enum {
RSMA_ROLE_CREATE = 0,
RSMA_ROLE_DROP = 1,
RSMA_ROLE_FETCH = 2,
RSMA_ROLE_SUBMIT = 3,
RSMA_ROLE_ITERATE = 4,
};
void tdDestroySmaEnv(SSmaEnv *pSmaEnv);
void *tdFreeSmaEnv(SSmaEnv *pSmaEnv);
@ -112,33 +143,6 @@ int32_t tdCheckAndInitSmaEnv(SSma *pSma, int8_t smaType);
int32_t tdLockSma(SSma *pSma);
int32_t tdUnLockSma(SSma *pSma);
static FORCE_INLINE int32_t tdRLockSmaEnv(SSmaEnv *pEnv) {
int code = taosThreadRwlockRdlock(&(pEnv->lock));
if (code != 0) {
terrno = TAOS_SYSTEM_ERROR(code);
return -1;
}
return 0;
}
static FORCE_INLINE int32_t tdWLockSmaEnv(SSmaEnv *pEnv) {
int code = taosThreadRwlockWrlock(&(pEnv->lock));
if (code != 0) {
terrno = TAOS_SYSTEM_ERROR(code);
return -1;
}
return 0;
}
static FORCE_INLINE int32_t tdUnLockSmaEnv(SSmaEnv *pEnv) {
int code = taosThreadRwlockUnlock(&(pEnv->lock));
if (code != 0) {
terrno = TAOS_SYSTEM_ERROR(code);
return -1;
}
return 0;
}
static FORCE_INLINE int8_t tdSmaStat(STSmaStat *pTStat) {
if (pTStat) {
return atomic_load_8(&pTStat->state);
@ -184,10 +188,12 @@ static FORCE_INLINE void tdSmaStatSetDropped(STSmaStat *pTStat) {
}
}
int32_t tdCloneRSmaInfo(SSma *pSma, SRSmaInfo *pDest, SRSmaInfo *pSrc);
void tdFreeQTaskInfo(qTaskInfo_t *taskHandle, int32_t vgId, int32_t level);
static int32_t tdDestroySmaState(SSmaStat *pSmaStat, int8_t smaType);
void *tdFreeSmaState(SSmaStat *pSmaStat, int8_t smaType);
void *tdFreeRSmaInfo(SSma *pSma, SRSmaInfo *pInfo);
int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat);
void *tdFreeRSmaInfo(SSma *pSma, SRSmaInfo *pInfo, bool isDeepFree);
int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat, SHashObj *pInfoHash);
int32_t tdProcessRSmaCreateImpl(SSma *pSma, SRSmaParam *param, int64_t suid, const char *tbName);
int32_t tdProcessRSmaRestoreImpl(SSma *pSma);

26
source/dnode/vnode/src/inc/tsdb.h
View File

@ -24,12 +24,12 @@ extern "C" {
// tsdbDebug ================
// clang-format off
#define tsdbFatal(...) do { if (tsdbDebugFlag & DEBUG_FATAL) { taosPrintLog("TSDB FATAL ", DEBUG_FATAL, 255, __VA_ARGS__); }} while(0)
#define tsdbError(...) do { if (tsdbDebugFlag & DEBUG_ERROR) { taosPrintLog("TSDB ERROR ", DEBUG_ERROR, 255, __VA_ARGS__); }} while(0)
#define tsdbWarn(...) do { if (tsdbDebugFlag & DEBUG_WARN) { taosPrintLog("TSDB WARN ", DEBUG_WARN, 255, __VA_ARGS__); }} while(0)
#define tsdbInfo(...) do { if (tsdbDebugFlag & DEBUG_INFO) { taosPrintLog("TSDB ", DEBUG_INFO, 255, __VA_ARGS__); }} while(0)
#define tsdbDebug(...) do { if (tsdbDebugFlag & DEBUG_DEBUG) { taosPrintLog("TSDB ", DEBUG_DEBUG, tsdbDebugFlag, __VA_ARGS__); }} while(0)
#define tsdbTrace(...) do { if (tsdbDebugFlag & DEBUG_TRACE) { taosPrintLog("TSDB ", DEBUG_TRACE, tsdbDebugFlag, __VA_ARGS__); }} while(0)
#define tsdbFatal(...) do { if (tsdbDebugFlag & DEBUG_FATAL) { taosPrintLog("TSD FATAL ", DEBUG_FATAL, 255, __VA_ARGS__); }} while(0)
#define tsdbError(...) do { if (tsdbDebugFlag & DEBUG_ERROR) { taosPrintLog("TSD ERROR ", DEBUG_ERROR, 255, __VA_ARGS__); }} while(0)
#define tsdbWarn(...) do { if (tsdbDebugFlag & DEBUG_WARN) { taosPrintLog("TSD WARN ", DEBUG_WARN, 255, __VA_ARGS__); }} while(0)
#define tsdbInfo(...) do { if (tsdbDebugFlag & DEBUG_INFO) { taosPrintLog("TSD ", DEBUG_INFO, 255, __VA_ARGS__); }} while(0)
#define tsdbDebug(...) do { if (tsdbDebugFlag & DEBUG_DEBUG) { taosPrintLog("TSD ", DEBUG_DEBUG, tsdbDebugFlag, __VA_ARGS__); }} while(0)
#define tsdbTrace(...) do { if (tsdbDebugFlag & DEBUG_TRACE) { taosPrintLog("TSD ", DEBUG_TRACE, tsdbDebugFlag, __VA_ARGS__); }} while(0)
// clang-format on
typedef struct TSDBROW TSDBROW;
@ -115,7 +115,6 @@ int32_t tGetBlock(uint8_t *p, void *ph);
int32_t tBlockCmprFn(const void *p1, const void *p2);
bool tBlockHasSma(SBlock *pBlock);
// SBlockIdx
void tBlockIdxReset(SBlockIdx *pBlockIdx);
int32_t tPutBlockIdx(uint8_t *p, void *ph);
int32_t tGetBlockIdx(uint8_t *p, void *ph);
int32_t tCmprBlockIdx(void const *lhs, void const *rhs);
@ -126,6 +125,8 @@ void tColDataClear(void *ph);
int32_t tColDataAppendValue(SColData *pColData, SColVal *pColVal);
int32_t tColDataGetValue(SColData *pColData, int32_t iRow, SColVal *pColVal);
int32_t tColDataCopy(SColData *pColDataSrc, SColData *pColDataDest);
int32_t tPutColData(uint8_t *p, SColData *pColData);
int32_t tGetColData(uint8_t *p, SColData *pColData);
// SBlockData
#define tBlockDataFirstRow(PBLOCKDATA) tsdbRowFromBlockData(PBLOCKDATA, 0)
#define tBlockDataLastRow(PBLOCKDATA) tsdbRowFromBlockData(PBLOCKDATA, (PBLOCKDATA)->nRow - 1)
@ -134,14 +135,17 @@ int32_t tColDataCopy(SColData *pColDataSrc, SColData *pColDataDest);
int32_t tBlockDataInit(SBlockData *pBlockData);
void tBlockDataReset(SBlockData *pBlockData);
int32_t tBlockDataSetSchema(SBlockData *pBlockData, STSchema *pTSchema);
int32_t tBlockDataCorrectSchema(SBlockData *pBlockData, SBlockData *pBlockDataFrom);
void tBlockDataClearData(SBlockData *pBlockData);
void tBlockDataClear(SBlockData *pBlockData);
void tBlockDataClear(SBlockData *pBlockData, int8_t deepClear);
int32_t tBlockDataAddColData(SBlockData *pBlockData, int32_t iColData, SColData **ppColData);
int32_t tBlockDataAppendRow(SBlockData *pBlockData, TSDBROW *pRow, STSchema *pTSchema);
int32_t tBlockDataMerge(SBlockData *pBlockData1, SBlockData *pBlockData2, SBlockData *pBlockData);
int32_t tBlockDataCopy(SBlockData *pBlockDataSrc, SBlockData *pBlockDataDest);
SColData *tBlockDataGetColDataByIdx(SBlockData *pBlockData, int32_t idx);
void tBlockDataGetColData(SBlockData *pBlockData, int16_t cid, SColData **ppColData);
int32_t tPutBlockData(uint8_t *p, SBlockData *pBlockData);
int32_t tGetBlockData(uint8_t *p, SBlockData *pBlockData);
// SDelIdx
int32_t tPutDelIdx(uint8_t *p, void *ph);
int32_t tGetDelIdx(uint8_t *p, void *ph);
@ -202,7 +206,7 @@ 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);
SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid, int32_t flag);
// tsdbReaderWriter.c ==============================================================================================
// SDataFWriter
int32_t tsdbDataFWriterOpen(SDataFWriter **ppWriter, STsdb *pTsdb, SDFileSet *pSet);
@ -357,10 +361,6 @@ struct TSDBROW {
struct SBlockIdx {
int64_t suid;
int64_t uid;
TSKEY minKey;
TSKEY maxKey;
int64_t minVersion;
int64_t maxVersion;
int64_t offset;
int64_t size;
};

13
source/dnode/vnode/src/inc/vnodeInt.h
View File

@ -99,7 +99,8 @@ STSchema* metaGetTbTSchema(SMeta* pMeta, tb_uid_t uid, int32_t sver);
int32_t metaGetTbTSchemaEx(SMeta* pMeta, tb_uid_t suid, tb_uid_t uid, int32_t sver, STSchema** ppTSchema);
int metaGetTableEntryByName(SMetaReader* pReader, const char* name);
tb_uid_t metaGetTableEntryUidByName(SMeta* pMeta, const char* name);
int metaGetTbNum(SMeta* pMeta);
int64_t metaGetTbNum(SMeta* pMeta);
int64_t metaGetTimeSeriesNum(SMeta* pMeta);
SMCtbCursor* metaOpenCtbCursor(SMeta* pMeta, tb_uid_t uid);
void metaCloseCtbCursor(SMCtbCursor* pCtbCur);
tb_uid_t metaCtbCursorNext(SMCtbCursor* pCtbCur);
@ -164,9 +165,12 @@ void smaCleanUp();
int32_t smaOpen(SVnode* pVnode);
int32_t smaClose(SSma* pSma);
int32_t smaBegin(SSma* pSma);
int32_t smaPreCommit(SSma* pSma);
int32_t smaCommit(SSma* pSma);
int32_t smaPostCommit(SSma* pSma);
int32_t smaSyncPreCommit(SSma* pSma);
int32_t smaSyncCommit(SSma* pSma);
int32_t smaSyncPostCommit(SSma* pSma);
int32_t smaAsyncPreCommit(SSma* pSma);
int32_t smaAsyncCommit(SSma* pSma);
int32_t smaAsyncPostCommit(SSma* pSma);
int32_t tdProcessTSmaCreate(SSma* pSma, int64_t version, const char* msg);
int32_t tdProcessTSmaInsert(SSma* pSma, int64_t indexUid, const char* msg);
@ -309,6 +313,7 @@ void smaHandleRes(void* pVnode, int64_t smaId, const SArray* data);
struct SSnapDataHdr {
int8_t type;
int64_t index;
int64_t size;
uint8_t data[];
};

12
source/dnode/vnode/src/meta/metaQuery.c
View File

@ -463,10 +463,16 @@ _err:
return code;
}
int metaGetTbNum(SMeta *pMeta) {
// N.B. Called by statusReq per second
int64_t metaGetTbNum(SMeta *pMeta) {
// TODO
// ASSERT(0);
return 0;
return 100;
}
// N.B. Called by statusReq per second
int64_t metaGetTimeSeriesNum(SMeta *pMeta) {
// TODO
return 400;
}
typedef struct {

89
source/dnode/vnode/src/meta/metaSnapshot.c
View File

@ -26,60 +26,72 @@ struct SMetaSnapReader {
int32_t metaSnapReaderOpen(SMeta* pMeta, int64_t sver, int64_t ever, SMetaSnapReader** ppReader) {
int32_t code = 0;
int32_t c = 0;
SMetaSnapReader* pMetaSnapReader = NULL;
SMetaSnapReader* pReader = NULL;
// alloc
pMetaSnapReader = (SMetaSnapReader*)taosMemoryCalloc(1, sizeof(*pMetaSnapReader));
if (pMetaSnapReader == NULL) {
pReader = (SMetaSnapReader*)taosMemoryCalloc(1, sizeof(*pReader));
if (pReader == NULL) {
code = TSDB_CODE_OUT_OF_MEMORY;
goto _err;
}
pMetaSnapReader->pMeta = pMeta;
pMetaSnapReader->sver = sver;
pMetaSnapReader->ever = ever;
pReader->pMeta = pMeta;
pReader->sver = sver;
pReader->ever = ever;
// impl
code = tdbTbcOpen(pMeta->pTbDb, &pMetaSnapReader->pTbc, NULL);
code = tdbTbcOpen(pMeta->pTbDb, &pReader->pTbc, NULL);
if (code) {
taosMemoryFree(pReader);
goto _err;
}
code = tdbTbcMoveTo(pMetaSnapReader->pTbc, &(STbDbKey){.version = sver, .uid = INT64_MIN}, sizeof(STbDbKey), &c);
code = tdbTbcMoveTo(pReader->pTbc, &(STbDbKey){.version = sver, .uid = INT64_MIN}, sizeof(STbDbKey), &c);
if (code) {
taosMemoryFree(pReader);
goto _err;
}
*ppReader = pMetaSnapReader;
metaInfo("vgId:%d vnode snapshot meta reader opened", TD_VID(pMeta->pVnode));
*ppReader = pReader;
return code;
_err:
metaError("vgId:%d meta snap reader open failed since %s", TD_VID(pMeta->pVnode), tstrerror(code));
metaError("vgId:%d vnode snapshot meta reader open failed since %s", TD_VID(pMeta->pVnode), tstrerror(code));
*ppReader = NULL;
return code;
}
int32_t metaSnapReaderClose(SMetaSnapReader** ppReader) {
int32_t code = 0;
tdbTbcClose((*ppReader)->pTbc);
taosMemoryFree(*ppReader);
*ppReader = NULL;
return 0;
return code;
}
int32_t metaSnapRead(SMetaSnapReader* pReader, uint8_t** ppData) {
int32_t code = 0;
const void* pKey = NULL;
const void* pData = NULL;
int32_t nKey = 0;
int32_t nData = 0;
int32_t code = 0;
STbDbKey key;
*ppData = NULL;
for (;;) {
code = tdbTbcGet(pReader->pTbc, &pKey, &nKey, &pData, &nData);
if (code || ((STbDbKey*)pData)->version > pReader->ever) {
code = TSDB_CODE_VND_READ_END;
if (tdbTbcGet(pReader->pTbc, &pKey, &nKey, &pData, &nData)) {
goto _exit;
}
if (((STbDbKey*)pData)->version < pReader->sver) {
key = ((STbDbKey*)pKey)[0];
if (key.version > pReader->ever) {
goto _exit;
}
if (key.version < pReader->sver) {
tdbTbcMoveToNext(pReader->pTbc);
continue;
}
@ -88,17 +100,28 @@ int32_t metaSnapRead(SMetaSnapReader* pReader, uint8_t** ppData) {
break;
}
// copy the data
if (tRealloc(ppData, sizeof(SSnapDataHdr) + nData) < 0) {
ASSERT(pData && nData);
*ppData = taosMemoryMalloc(sizeof(SSnapDataHdr) + nData);
if (*ppData == NULL) {
code = TSDB_CODE_OUT_OF_MEMORY;
return code;
goto _err;
}
((SSnapDataHdr*)(*ppData))->type = 0; // TODO: use macro
((SSnapDataHdr*)(*ppData))->size = nData;
memcpy(((SSnapDataHdr*)(*ppData))->data, pData, nData);
SSnapDataHdr* pHdr = (SSnapDataHdr*)(*ppData);
pHdr->type = 0; // TODO: use macro
pHdr->size = nData;
memcpy(pHdr->data, pData, nData);
metaInfo("vgId:%d vnode snapshot meta read data, version:%" PRId64 " uid:%" PRId64 " nData:%d",
TD_VID(pReader->pMeta->pVnode), key.version, key.uid, nData);
_exit:
return code;
_err:
metaError("vgId:%d vnode snapshot meta read data failed since %s", TD_VID(pReader->pMeta->pVnode), tstrerror(code));
return code;
}
// SMetaSnapWriter ========================================
@ -108,18 +131,6 @@ struct SMetaSnapWriter {
int64_t ever;
};
static int32_t metaSnapRollback(SMetaSnapWriter* pWriter) {
int32_t code = 0;
// TODO
return code;
}
static int32_t metaSnapCommit(SMetaSnapWriter* pWriter) {
int32_t code = 0;
// TODO
return code;
}
int32_t metaSnapWriterOpen(SMeta* pMeta, int64_t sver, int64_t ever, SMetaSnapWriter** ppWriter) {
int32_t code = 0;
SMetaSnapWriter* pWriter;
@ -148,10 +159,9 @@ int32_t metaSnapWriterClose(SMetaSnapWriter** ppWriter, int8_t rollback) {
SMetaSnapWriter* pWriter = *ppWriter;
if (rollback) {
code = metaSnapRollback(pWriter);
if (code) goto _err;
ASSERT(0);
} else {
code = metaSnapCommit(pWriter);
code = metaCommit(pWriter->pMeta);
if (code) goto _err;
}
taosMemoryFree(pWriter);
@ -170,15 +180,16 @@ int32_t metaSnapWrite(SMetaSnapWriter* pWriter, uint8_t* pData, uint32_t nData)
SMetaEntry metaEntry = {0};
SDecoder* pDecoder = &(SDecoder){0};
tDecoderInit(pDecoder, pData, nData);
tDecoderInit(pDecoder, pData + sizeof(SSnapDataHdr), nData - sizeof(SSnapDataHdr));
metaDecodeEntry(pDecoder, &metaEntry);
code = metaHandleEntry(pMeta, &metaEntry);
if (code) goto _err;
tDecoderClear(pDecoder);
return code;
_err:
metaError("vgId:%d meta snapshot write failed since %s", TD_VID(pMeta->pVnode), tstrerror(code));
metaError("vgId:%d vnode snapshot meta write failed since %s", TD_VID(pMeta->pVnode), tstrerror(code));
return code;
}

232
source/dnode/vnode/src/sma/smaCommit.c
View File

@ -15,9 +15,13 @@
#include "sma.h"
static int32_t tdProcessRSmaPreCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaPostCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaSyncPreCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaSyncCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaSyncPostCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaAsyncPreCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaAsyncCommitImpl(SSma *pSma);
static int32_t tdProcessRSmaAsyncPostCommitImpl(SSma *pSma);
static int32_t tdCleanupQTaskInfoFiles(SSma *pSma, SRSmaStat *pRSmaStat);
/**
* @brief Only applicable to Rollup SMA
@ -25,7 +29,7 @@ static int32_t tdProcessRSmaPostCommitImpl(SSma *pSma);
* @param pSma
* @return int32_t
*/
int32_t smaPreCommit(SSma *pSma) { return tdProcessRSmaPreCommitImpl(pSma); }
int32_t smaSyncPreCommit(SSma *pSma) { return tdProcessRSmaSyncPreCommitImpl(pSma); }
/**
* @brief Only applicable to Rollup SMA
@ -33,7 +37,7 @@ int32_t smaPreCommit(SSma *pSma) { return tdProcessRSmaPreCommitImpl(pSma); }
* @param pSma
* @return int32_t
*/
int32_t smaCommit(SSma *pSma) { return tdProcessRSmaCommitImpl(pSma); }
int32_t smaSyncCommit(SSma *pSma) { return tdProcessRSmaSyncCommitImpl(pSma); }
/**
* @brief Only applicable to Rollup SMA
@ -41,7 +45,31 @@ int32_t smaCommit(SSma *pSma) { return tdProcessRSmaCommitImpl(pSma); }
* @param pSma
* @return int32_t
*/
int32_t smaPostCommit(SSma *pSma) { return tdProcessRSmaPostCommitImpl(pSma); }
int32_t smaSyncPostCommit(SSma *pSma) { return tdProcessRSmaSyncPostCommitImpl(pSma); }
/**
* @brief Only applicable to Rollup SMA
*
* @param pSma
* @return int32_t
*/
int32_t smaAsyncPreCommit(SSma *pSma) { return tdProcessRSmaAsyncPreCommitImpl(pSma); }
/**
* @brief Only applicable to Rollup SMA
*
* @param pSma
* @return int32_t
*/
int32_t smaAsyncCommit(SSma *pSma) { return tdProcessRSmaAsyncCommitImpl(pSma); }
/**
* @brief Only applicable to Rollup SMA
*
* @param pSma
* @return int32_t
*/
int32_t smaAsyncPostCommit(SSma *pSma) { return tdProcessRSmaAsyncPostCommitImpl(pSma); }
/**
* @brief set rsma trigger stat active
@ -62,18 +90,17 @@ int32_t smaBegin(SSma *pSma) {
atomic_val_compare_exchange_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_PAUSED, TASK_TRIGGER_STAT_ACTIVE);
switch (rsmaTriggerStat) {
case TASK_TRIGGER_STAT_PAUSED: {
smaDebug("vgId:%d rsma trigger stat from paused to active", SMA_VID(pSma));
smaDebug("vgId:%d, rsma trigger stat from paused to active", SMA_VID(pSma));
break;
}
case TASK_TRIGGER_STAT_INIT: {
atomic_store_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_ACTIVE);
smaDebug("vgId:%d rsma trigger stat from init to active", SMA_VID(pSma));
smaDebug("vgId:%d, rsma trigger stat from init to active", SMA_VID(pSma));
break;
}
default: {
atomic_store_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_ACTIVE);
smaWarn("vgId:%d rsma trigger stat %" PRIi8 " is unexpected", SMA_VID(pSma), rsmaTriggerStat);
ASSERT(0);
smaError("vgId:%d, rsma trigger stat %" PRIi8 " is unexpected", SMA_VID(pSma), rsmaTriggerStat);
break;
}
}
@ -81,7 +108,7 @@ int32_t smaBegin(SSma *pSma) {
}
/**
* @brief pre-commit for rollup sma.
* @brief pre-commit for rollup sma(sync commit).
* 1) set trigger stat of rsma timer TASK_TRIGGER_STAT_PAUSED.
* 2) wait all triggered fetch tasks finished
* 3) perform persist task for qTaskInfo
@ -89,7 +116,7 @@ int32_t smaBegin(SSma *pSma) {
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaPreCommitImpl(SSma *pSma) {
static int32_t tdProcessRSmaSyncPreCommitImpl(SSma *pSma) {
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
if (!pSmaEnv) {
return TSDB_CODE_SUCCESS;
@ -98,8 +125,7 @@ static int32_t tdProcessRSmaPreCommitImpl(SSma *pSma) {
SSmaStat *pStat = SMA_ENV_STAT(pSmaEnv);
SRSmaStat *pRSmaStat = SMA_RSMA_STAT(pStat);
// step 1: set persistence task paused
// step 1: set rsma stat paused
atomic_store_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_PAUSED);
// step 2: wait all triggered fetch tasks finished
@ -119,7 +145,9 @@ static int32_t tdProcessRSmaPreCommitImpl(SSma *pSma) {
}
// step 3: perform persist task for qTaskInfo
tdRSmaPersistExecImpl(pRSmaStat);
pRSmaStat->commitAppliedVer = pSma->pVnode->state.applied;
pRSmaStat->commitSubmitVer = pRSmaStat->submitVer;
tdRSmaPersistExecImpl(pRSmaStat, RSMA_INFO_HASH(pRSmaStat));
smaDebug("vgId:%d, rsma pre commit success", SMA_VID(pSma));
@ -132,7 +160,7 @@ static int32_t tdProcessRSmaPreCommitImpl(SSma *pSma) {
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaCommitImpl(SSma *pSma) {
static int32_t tdProcessRSmaSyncCommitImpl(SSma *pSma) {
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
if (!pSmaEnv) {
return TSDB_CODE_SUCCESS;
@ -140,21 +168,9 @@ static int32_t tdProcessRSmaCommitImpl(SSma *pSma) {
return TSDB_CODE_SUCCESS;
}
/**
* @brief post-commit for rollup sma
* 1) clean up the outdated qtaskinfo files
*
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaPostCommitImpl(SSma *pSma) {
SVnode *pVnode = pSma->pVnode;
if (!VND_IS_RSMA(pVnode)) {
return TSDB_CODE_SUCCESS;
}
int64_t committed = pVnode->state.committed;
static int32_t tdCleanupQTaskInfoFiles(SSma *pSma, SRSmaStat *pRSmaStat) {
SVnode *pVnode = pSma->pVnode;
int64_t committed = pRSmaStat->commitAppliedVer;
TdDirPtr pDir = NULL;
TdDirEntryPtr pDirEntry = NULL;
char dir[TSDB_FILENAME_LEN];
@ -222,5 +238,159 @@ static int32_t tdProcessRSmaPostCommitImpl(SSma *pSma) {
taosCloseDir(&pDir);
regfree(&regex);
return TSDB_CODE_SUCCESS;
}
/**
* @brief post-commit for rollup sma
* 1) clean up the outdated qtaskinfo files
*
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaSyncPostCommitImpl(SSma *pSma) {
SVnode *pVnode = pSma->pVnode;
if (!VND_IS_RSMA(pVnode)) {
return TSDB_CODE_SUCCESS;
}
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
SRSmaStat *pRSmaStat = SMA_RSMA_STAT(SMA_ENV_STAT(pSmaEnv));
// cleanup outdated qtaskinfo files
tdCleanupQTaskInfoFiles(pSma, pRSmaStat);
return TSDB_CODE_SUCCESS;
}
/**
* @brief Rsma async commit implementation
* 1) set rsma stat TASK_TRIGGER_STAT_PAUSED
* 2) Wait all running fetch task finish to fetch and put submitMsg into level 2/3 wQueue(blocking level 1 write)
* 3)
*
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaAsyncPreCommitImpl(SSma *pSma) {
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
if (!pSmaEnv) {
return TSDB_CODE_SUCCESS;
}
SSmaStat *pStat = SMA_ENV_STAT(pSmaEnv);
SRSmaStat *pRSmaStat = SMA_RSMA_STAT(pStat);
// step 1: set rsma stat
atomic_store_8(RSMA_TRIGGER_STAT(pRSmaStat), TASK_TRIGGER_STAT_PAUSED);
atomic_store_8(RSMA_COMMIT_STAT(pRSmaStat), 1);
// step 2: wait all triggered fetch tasks finished
int32_t nLoops = 0;
while (1) {
if (T_REF_VAL_GET(pStat) == 0) {
smaDebug("vgId:%d, rsma fetch tasks all finished", SMA_VID(pSma));
break;
} else {
smaDebug("vgId:%d, rsma fetch tasks not all finished yet", SMA_VID(pSma));
}
++nLoops;
if (nLoops > 1000) {
sched_yield();
nLoops = 0;
}
}
// step 3: swap rsmaInfoHash and iRsmaInfoHash
ASSERT(!RSMA_IMU_INFO_HASH(pRSmaStat));
ASSERT(RSMA_INFO_HASH(pRSmaStat));
RSMA_IMU_INFO_HASH(pRSmaStat) = RSMA_INFO_HASH(pRSmaStat);
RSMA_INFO_HASH(pRSmaStat) =
taosHashInit(RSMA_TASK_INFO_HASH_SLOT, taosGetDefaultHashFunction(TSDB_DATA_TYPE_BIGINT), true, HASH_ENTRY_LOCK);
if (!RSMA_INFO_HASH(pRSmaStat)) {
smaError("vgId:%d, rsma async commit failed since %s", SMA_VID(pSma), terrstr());
return TSDB_CODE_FAILED;
}
// step 4: others
pRSmaStat->commitAppliedVer = pSma->pVnode->state.applied;
pRSmaStat->commitSubmitVer = pRSmaStat->submitVer;
return TSDB_CODE_SUCCESS;
}
/**
* @brief commit for rollup sma
*
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaAsyncCommitImpl(SSma *pSma) {
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
if (!pSmaEnv) {
return TSDB_CODE_SUCCESS;
}
SSmaStat *pStat = SMA_ENV_STAT(pSmaEnv);
SRSmaStat *pRSmaStat = SMA_RSMA_STAT(pStat);
// perform persist task for qTaskInfo
tdRSmaPersistExecImpl(pRSmaStat, RSMA_IMU_INFO_HASH(pRSmaStat));
return TSDB_CODE_SUCCESS;
}
/**
* @brief Migrate rsmaInfo from iRsmaInfo to rsmaInfo if rsmaInfoHash not empty.
*
* @param pSma
* @return int32_t
*/
static int32_t tdProcessRSmaAsyncPostCommitImpl(SSma *pSma) {
SSmaEnv *pSmaEnv = SMA_RSMA_ENV(pSma);
if (!pSmaEnv) {
return TSDB_CODE_SUCCESS;
}
SSmaStat *pStat = SMA_ENV_STAT(pSmaEnv);
SRSmaStat *pRSmaStat = SMA_RSMA_STAT(pStat);
// step 1: merge rsmaInfoHash and iRsmaInfoHash
taosWLockLatch(SMA_ENV_LOCK(pSmaEnv));
if (taosHashGetSize(RSMA_INFO_HASH(pRSmaStat)) <= 0) {
// TODO: optimization - just switch the hash pointer if rsmaInfoHash is empty
}
void *pIter = taosHashIterate(RSMA_IMU_INFO_HASH(pRSmaStat), NULL);
while (pIter) {
tb_uid_t *pSuid = (tb_uid_t *)taosHashGetKey(pIter, NULL);
if (!taosHashGet(RSMA_INFO_HASH(pRSmaStat), pSuid, sizeof(tb_uid_t))) {
taosHashPut(RSMA_INFO_HASH(pRSmaStat), pSuid, sizeof(tb_uid_t), pIter, sizeof(pIter));
smaDebug("vgId:%d, rsma async post commit, migrated from iRsmaInfoHash for table:%" PRIi64, SMA_VID(pSma),
*pSuid);
} else {
// free the resources
SRSmaInfo *pRSmaInfo = *(SRSmaInfo **)pIter;
tdFreeRSmaInfo(pSma, pRSmaInfo, false);
smaDebug("vgId:%d, rsma async post commit, free rsma info since already COW for table:%" PRIi64, SMA_VID(pSma),
*pSuid);
}
pIter = taosHashIterate(RSMA_IMU_INFO_HASH(pRSmaStat), pIter);
}
taosHashCleanup(RSMA_IMU_INFO_HASH(pRSmaStat));
RSMA_IMU_INFO_HASH(pRSmaStat) = NULL;
taosWUnLockLatch(SMA_ENV_LOCK(pSmaEnv));
// step 2: cleanup outdated qtaskinfo files
tdCleanupQTaskInfoFiles(pSma, pRSmaStat);
return TSDB_CODE_SUCCESS;
}

12
source/dnode/vnode/src/sma/smaEnv.c
View File

@ -17,7 +17,6 @@
typedef struct SSmaStat SSmaStat;
#define RSMA_TASK_INFO_HASH_SLOT 8
#define SMA_MGMT_REF_NUM 10240
extern SSmaMgmt smaMgmt;
@ -109,12 +108,7 @@ static SSmaEnv *tdNewSmaEnv(const SSma *pSma, int8_t smaType, const char *path)
SMA_ENV_TYPE(pEnv) = smaType;
int code = taosThreadRwlockInit(&(pEnv->lock), NULL);
if (code) {
terrno = TAOS_SYSTEM_ERROR(code);
taosMemoryFree(pEnv);
return NULL;
}
taosInitRWLatch(&(pEnv->lock));
if (tdInitSmaStat(&SMA_ENV_STAT(pEnv), smaType, pSma) != TSDB_CODE_SUCCESS) {
tdFreeSmaEnv(pEnv);
@ -148,7 +142,6 @@ static int32_t tdInitSmaEnv(SSma *pSma, int8_t smaType, const char *path, SSmaEn
void tdDestroySmaEnv(SSmaEnv *pSmaEnv) {
if (pSmaEnv) {
pSmaEnv->pStat = tdFreeSmaState(pSmaEnv->pStat, SMA_ENV_TYPE(pSmaEnv));
taosThreadRwlockDestroy(&(pSmaEnv->lock));
}
}
@ -260,7 +253,7 @@ static void tdDestroyRSmaStat(void *pRSmaStat) {
void *infoHash = taosHashIterate(RSMA_INFO_HASH(pStat), NULL);
while (infoHash) {
SRSmaInfo *pSmaInfo = *(SRSmaInfo **)infoHash;
tdFreeRSmaInfo(pSma, pSmaInfo);
tdFreeRSmaInfo(pSma, pSmaInfo, true);
infoHash = taosHashIterate(RSMA_INFO_HASH(pStat), infoHash);
}
}
@ -311,7 +304,6 @@ int32_t tdDestroySmaState(SSmaStat *pSmaStat, int8_t smaType) {
if (taosRemoveRef(smaMgmt.rsetId, RSMA_REF_ID(pRSmaStat)) < 0) {
smaError("vgId:%d, remove refId:%" PRIi64 " from rsmaRef:%" PRIi32 " failed since %s", SMA_VID(pRSmaStat->pSma),
RSMA_REF_ID(pRSmaStat), smaMgmt.rsetId, terrstr());
ASSERT(0);
} else {
smaDebug("vgId:%d, remove refId:%" PRIi64 " from rsmaRef:%" PRIi32 " succeed", SMA_VID(pRSmaStat->pSma),
RSMA_REF_ID(pRSmaStat), smaMgmt.rsetId);

151
source/dnode/vnode/src/sma/smaRollup.c
View File

@ -48,20 +48,7 @@ static int32_t tdRSmaRestoreQTaskInfoInit(SSma *pSma, int64_t *nTables);
static int32_t tdRSmaRestoreQTaskInfoReload(SSma *pSma, int64_t *committed);
static int32_t tdRSmaRestoreTSDataReload(SSma *pSma, int64_t committed);
struct SRSmaInfoItem {
void *taskInfo; // qTaskInfo_t
int64_t refId;
tmr_h tmrId;
int32_t maxDelay;
int8_t level;
int8_t triggerStat;
};
struct SRSmaInfo {
STSchema *pTSchema;
int64_t suid;
SRSmaInfoItem items[TSDB_RETENTION_L2];
};
static SRSmaInfo *tdGetRSmaInfoByItem(SRSmaInfoItem *pItem) {
// adapt accordingly if definition of SRSmaInfo update
@ -102,8 +89,9 @@ static FORCE_INLINE int32_t tdRSmaQTaskInfoContLen(int32_t lenWithHead) {
static FORCE_INLINE void tdRSmaQTaskInfoIterDestroy(SRSmaQTaskInfoIter *pIter) { taosMemoryFreeClear(pIter->pBuf); }
static FORCE_INLINE void tdFreeTaskHandle(qTaskInfo_t *taskHandle, int32_t vgId, int32_t level) {
void tdFreeQTaskInfo(qTaskInfo_t *taskHandle, int32_t vgId, int32_t level) {
// Note: free/kill may in RC
if (!taskHandle) return;
qTaskInfo_t otaskHandle = atomic_load_ptr(taskHandle);
if (otaskHandle && atomic_val_compare_exchange_ptr(taskHandle, otaskHandle, NULL)) {
smaDebug("vgId:%d, free qTaskInfo_t %p of level %d", vgId, otaskHandle, level);
@ -111,25 +99,36 @@ static FORCE_INLINE void tdFreeTaskHandle(qTaskInfo_t *taskHandle, int32_t vgId,
} else {
smaDebug("vgId:%d, not free qTaskInfo_t %p of level %d", vgId, otaskHandle, level);
}
// TODO: clear files related to qTaskInfo?
}
void *tdFreeRSmaInfo(SSma *pSma, SRSmaInfo *pInfo) {
/**
* @brief general function to free rsmaInfo
*
* @param pSma
* @param pInfo
* @param isDeepFree Only stop tmrId and free pTSchema for deep free
* @return void*
*/
void *tdFreeRSmaInfo(SSma *pSma, SRSmaInfo *pInfo, bool isDeepFree) {
if (pInfo) {
for (int32_t i = 0; i < TSDB_RETENTION_L2; ++i) {
SRSmaInfoItem *pItem = &pInfo->items[i];
if (pItem->taskInfo) {
if (pItem->tmrId) {
if (isDeepFree && pItem->tmrId) {
smaDebug("vgId:%d, table %" PRIi64 " stop fetch timer %p level %d", SMA_VID(pSma), pInfo->suid, pItem->tmrId,
i + 1);
taosTmrStopA(&pItem->tmrId);
}
tdFreeTaskHandle(&pItem->taskInfo, SMA_VID(pSma), i + 1);
tdFreeQTaskInfo(&pItem->taskInfo, SMA_VID(pSma), i + 1);
} else {
smaDebug("vgId:%d, table %" PRIi64 " no need to destroy rsma info level %d since empty taskInfo", SMA_VID(pSma),
pInfo->suid, i + 1);
}
}
taosMemoryFree(pInfo->pTSchema);
if (isDeepFree) {
taosMemoryFree(pInfo->pTSchema);
}
taosMemoryFree(pInfo);
}
@ -151,7 +150,7 @@ static int32_t tdUpdateTbUidListImpl(SSma *pSma, tb_uid_t *suid, SArray *tbUids)
if (!suid || !tbUids) {
terrno = TSDB_CODE_INVALID_PTR;
smaError("vgId:%d, failed to get rsma info for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr(terrno));
smaError("vgId:%d, failed to get rsma info for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr());
return TSDB_CODE_FAILED;
}
@ -165,7 +164,7 @@ static int32_t tdUpdateTbUidListImpl(SSma *pSma, tb_uid_t *suid, SArray *tbUids)
if (pRSmaInfo->items[0].taskInfo) {
if ((qUpdateQualifiedTableId(pRSmaInfo->items[0].taskInfo, tbUids, true) < 0)) {
smaError("vgId:%d, update tbUidList failed for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr(terrno));
smaError("vgId:%d, update tbUidList failed for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr());
return TSDB_CODE_FAILED;
} else {
smaDebug("vgId:%d, update tbUidList succeed for qTaskInfo:%p with suid:%" PRIi64 ", uid:%" PRIi64, SMA_VID(pSma),
@ -175,7 +174,7 @@ static int32_t tdUpdateTbUidListImpl(SSma *pSma, tb_uid_t *suid, SArray *tbUids)
if (pRSmaInfo->items[1].taskInfo) {
if ((qUpdateQualifiedTableId(pRSmaInfo->items[1].taskInfo, tbUids, true) < 0)) {
smaError("vgId:%d, update tbUidList failed for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr(terrno));
smaError("vgId:%d, update tbUidList failed for uid:%" PRIi64 " since %s", SMA_VID(pSma), *suid, terrstr());
return TSDB_CODE_FAILED;
} else {
smaDebug("vgId:%d, update tbUidList succeed for qTaskInfo:%p with suid:%" PRIi64 ", uid:%" PRIi64, SMA_VID(pSma),
@ -257,22 +256,22 @@ int32_t tdFetchTbUidList(SSma *pSma, STbUidStore **ppStore, tb_uid_t suid, tb_ui
static int32_t tdSetRSmaInfoItemParams(SSma *pSma, SRSmaParam *param, SRSmaStat *pStat, SRSmaInfo *pRSmaInfo,
int8_t idx) {
SRetention *pRetention = SMA_RETENTION(pSma);
STsdbCfg *pTsdbCfg = SMA_TSDB_CFG(pSma);
if ((param->qmsgLen > 0) && param->qmsg[idx]) {
SRetention *pRetention = SMA_RETENTION(pSma);
STsdbCfg *pTsdbCfg = SMA_TSDB_CFG(pSma);
SVnode *pVnode = pSma->pVnode;
SReadHandle handle = {
.meta = pVnode->pMeta,
.vnode = pVnode,
.initTqReader = 1,
};
SReadHandle handle = {
.meta = pSma->pVnode->pMeta,
.vnode = pSma->pVnode,
.initTqReader = 1,
};
if (param->qmsg[idx]) {
SRSmaInfoItem *pItem = &(pRSmaInfo->items[idx]);
pItem->refId = RSMA_REF_ID(pStat);
pItem->taskInfo = qCreateStreamExecTaskInfo(param->qmsg[idx], &handle);
if (!pItem->taskInfo) {
terrno = TSDB_CODE_RSMA_QTASKINFO_CREATE;
goto _err;
return TSDB_CODE_FAILED;
}
pItem->triggerStat = TASK_TRIGGER_STAT_INACTIVE;
if (param->maxdelay[idx] < TSDB_MIN_ROLLUP_MAX_DELAY) {
@ -286,13 +285,11 @@ static int32_t tdSetRSmaInfoItemParams(SSma *pSma, SRSmaParam *param, SRSmaStat
pItem->maxDelay = TSDB_MAX_ROLLUP_MAX_DELAY;
}
pItem->level = idx == 0 ? TSDB_RETENTION_L1 : TSDB_RETENTION_L2;
smaInfo("vgId:%d table:%" PRIi64 " level:%" PRIi8 " maxdelay:%" PRIi64 " watermark:%" PRIi64
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);
TD_VID(pVnode), pRSmaInfo->suid, idx + 1, param->maxdelay[idx], param->watermark[idx], pItem->maxDelay);
}
return TSDB_CODE_SUCCESS;
_err:
return TSDB_CODE_FAILED;
}
/**
@ -357,7 +354,7 @@ int32_t tdProcessRSmaCreateImpl(SSma *pSma, SRSmaParam *param, int64_t suid, con
return TSDB_CODE_SUCCESS;
_err:
tdFreeRSmaInfo(pSma, pRSmaInfo);
tdFreeRSmaInfo(pSma, pRSmaInfo, true);
return TSDB_CODE_FAILED;
}
@ -562,7 +559,9 @@ static int32_t tdRSmaFetchAndSubmitResult(SRSmaInfoItem *pItem, STSchema *pTSche
SSDataBlock *output = NULL;
uint64_t ts;
if (qExecTask(pItem->taskInfo, &output, &ts) < 0) {
ASSERT(false);
smaError("vgId:%d, qExecTask for rsma table %" PRIi64 "l evel %" PRIi8 " failed since %s", SMA_VID(pSma), suid,
pItem->level, terrstr());
goto _err;
}
if (!output) {
break;
@ -572,7 +571,7 @@ static int32_t tdRSmaFetchAndSubmitResult(SRSmaInfoItem *pItem, STSchema *pTSche
pResult = taosArrayInit(1, sizeof(SSDataBlock));
if (!pResult) {
terrno = TSDB_CODE_OUT_OF_MEMORY;
return TSDB_CODE_FAILED;
goto _err;
}
}
@ -649,9 +648,18 @@ static int32_t tdExecuteRSmaImpl(SSma *pSma, const void *pMsg, int32_t inputType
return TSDB_CODE_SUCCESS;
}
/**
* @brief During async commit, the SRSmaInfo object would be COW from iRSmaInfoHash and write lock should be applied.
*
* @param pSma
* @param suid
* @return SRSmaInfo*
*/
static SRSmaInfo *tdGetRSmaInfoBySuid(SSma *pSma, int64_t suid) {
SSmaEnv *pEnv = SMA_RSMA_ENV(pSma);
SRSmaStat *pStat = NULL;
SRSmaInfo *pRSmaInfo = NULL;
if (!pEnv) {
// only applicable when rsma env exists
return NULL;
@ -662,11 +670,37 @@ static SRSmaInfo *tdGetRSmaInfoBySuid(SSma *pSma, int64_t suid) {
return NULL;
}
SRSmaInfo *pRSmaInfo = taosHashGet(RSMA_INFO_HASH(pStat), &suid, sizeof(tb_uid_t));
if (!pRSmaInfo || !(pRSmaInfo = *(SRSmaInfo **)pRSmaInfo)) {
pRSmaInfo = taosHashGet(RSMA_INFO_HASH(pStat), &suid, sizeof(tb_uid_t));
if (pRSmaInfo && (pRSmaInfo = *(SRSmaInfo **)pRSmaInfo)) {
return pRSmaInfo;
}
if (RSMA_COMMIT_STAT(pStat) == 0) {
return NULL;
}
return pRSmaInfo;
// clone the SRSmaInfo from iRsmaInfoHash to rsmaInfoHash if in committing stat
SRSmaInfo *pCowRSmaInfo = NULL;
// lock
taosWLockLatch(SMA_ENV_LOCK(pEnv));
void *iRSmaInfo = taosHashGet(RSMA_IMU_INFO_HASH(pStat), &suid, sizeof(tb_uid_t));
if (iRSmaInfo) {
SRSmaInfo *pIRSmaInfo = *(SRSmaInfo **)iRSmaInfo;
if (pIRSmaInfo) {
if (tdCloneRSmaInfo(pSma, pCowRSmaInfo, pIRSmaInfo) < 0) {
taosWUnLockLatch(SMA_ENV_LOCK(pEnv));
smaError("vgId:%d, clone rsma info failed for suid:%" PRIu64 " since %s", SMA_VID(pSma), suid, terrstr());
return NULL;
}
if (taosHashPut(RSMA_INFO_HASH(pStat), &suid, sizeof(tb_uid_t), &pCowRSmaInfo, sizeof(pCowRSmaInfo)) < 0) {
taosWUnLockLatch(SMA_ENV_LOCK(pEnv));
return NULL;
}
}
}
// unlock
taosWUnLockLatch(SMA_ENV_LOCK(pEnv));
return pCowRSmaInfo;
}
static int32_t tdExecuteRSma(SSma *pSma, const void *pMsg, int32_t inputType, tb_uid_t suid) {
@ -891,10 +925,17 @@ int32_t tdProcessRSmaRestoreImpl(SSma *pSma) {
return TSDB_CODE_SUCCESS;
_err:
smaError("vgId:%d failed to restore rsma task since %s", SMA_VID(pSma), terrstr());
smaError("vgId:%d, failed to restore rsma task since %s", SMA_VID(pSma), terrstr());
return TSDB_CODE_FAILED;
}
/**
* @brief Restore from SRSmaQTaskInfoItem
*
* @param pSma
* @param pItem
* @return int32_t
*/
static int32_t tdRSmaQTaskInfoItemRestore(SSma *pSma, const SRSmaQTaskInfoItem *pItem) {
SRSmaInfo *pRSmaInfo = NULL;
void *qTaskInfo = NULL;
@ -920,7 +961,7 @@ static int32_t tdRSmaQTaskInfoItemRestore(SSma *pSma, const SRSmaQTaskInfoItem *
if (qDeserializeTaskStatus(qTaskInfo, pItem->qTaskInfo, pItem->len) < 0) {
smaError("vgId:%d, restore rsma task failed for table:%" PRIi64 " level %d since %s", SMA_VID(pSma), pItem->suid,
pItem->type, terrstr(terrno));
pItem->type, terrstr());
return TSDB_CODE_FAILED;
}
smaDebug("vgId:%d, restore rsma task success for table:%" PRIi64 " level %d", SMA_VID(pSma), pItem->suid,
@ -1067,26 +1108,27 @@ static int32_t tdRSmaQTaskInfoRestore(SSma *pSma, SRSmaQTaskInfoIter *pIter) {
return TSDB_CODE_SUCCESS;
}
int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat) {
int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat, SHashObj *pInfoHash) {
SSma *pSma = pRSmaStat->pSma;
SVnode *pVnode = pSma->pVnode;
int32_t vid = SMA_VID(pSma);
int64_t toffset = 0;
bool isFileCreated = false;
if (taosHashGetSize(RSMA_INFO_HASH(pRSmaStat)) <= 0) {
if (taosHashGetSize(pInfoHash) <= 0) {
return TSDB_CODE_SUCCESS;
}
void *infoHash = taosHashIterate(RSMA_INFO_HASH(pRSmaStat), NULL);
void *infoHash = taosHashIterate(pInfoHash, NULL);
if (!infoHash) {
return TSDB_CODE_SUCCESS;
}
STFile tFile = {0};
if (RSMA_SUBMIT_VER(pRSmaStat) > 0) {
#if 0
if (pRSmaStat->commitAppliedVer > 0) {
char qTaskInfoFName[TSDB_FILENAME_LEN];
tdRSmaQTaskInfoGetFName(vid, pSma->pVnode->state.applied, qTaskInfoFName);
tdRSmaQTaskInfoGetFName(vid, pRSmaStat->commitAppliedVer, qTaskInfoFName);
if (tdInitTFile(&tFile, tfsGetPrimaryPath(pVnode->pTfs), qTaskInfoFName) < 0) {
smaError("vgId:%d, rsma persit, init %s failed since %s", vid, qTaskInfoFName, terrstr());
goto _err;
@ -1099,6 +1141,7 @@ int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat) {
isFileCreated = true;
}
#endif
while (infoHash) {
SRSmaInfo *pRSmaInfo = *(SRSmaInfo **)infoHash;
@ -1114,7 +1157,7 @@ int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat) {
int8_t type = (int8_t)(i + 1);
if (qSerializeTaskStatus(taskInfo, &pOutput, &len) < 0) {
smaError("vgId:%d, rsma, table %" PRIi64 " level %d serialize qTaskInfo failed since %s", vid, pRSmaInfo->suid,
i + 1, terrstr(terrno));
i + 1, terrstr());
goto _err;
}
if (!pOutput || len <= 0) {
@ -1130,7 +1173,7 @@ int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat) {
if (!isFileCreated) {
char qTaskInfoFName[TSDB_FILENAME_LEN];
tdRSmaQTaskInfoGetFName(vid, pSma->pVnode->state.applied, qTaskInfoFName);
tdRSmaQTaskInfoGetFName(vid, pRSmaStat->commitAppliedVer, qTaskInfoFName);
if (tdInitTFile(&tFile, tfsGetPrimaryPath(pVnode->pTfs), qTaskInfoFName) < 0) {
smaError("vgId:%d, rsma persit, init %s failed since %s", vid, qTaskInfoFName, terrstr());
goto _err;
@ -1163,11 +1206,11 @@ int32_t tdRSmaPersistExecImpl(SRSmaStat *pRSmaStat) {
taosMemoryFree(pOutput);
}
infoHash = taosHashIterate(RSMA_INFO_HASH(pRSmaStat), infoHash);
infoHash = taosHashIterate(pInfoHash, infoHash);
}
if (isFileCreated) {
tFile.info.qTaskInfo.submitVer = atomic_load_64(&pRSmaStat->submitVer);
tFile.info.qTaskInfo.submitVer = atomic_load_64(&pRSmaStat->commitSubmitVer);
if (tdUpdateTFileHeader(&tFile) < 0) {
smaError("vgId:%d, rsma, failed to update tfile %s header since %s", vid, TD_TFILE_FULL_NAME(&tFile),
tstrerror(terrno));
@ -1217,6 +1260,10 @@ static void tdRSmaFetchTrigger(void *param, void *tmrId) {
smaDebug("vgId:%d, not fetch rsma level %" PRIi8 " data since stat is %" PRIi8 ", rsetId rsetId:%" PRIi64
" refId:%d",
SMA_VID(pSma), pItem->level, rsmaTriggerStat, smaMgmt.rsetId, pItem->refId);
if (rsmaTriggerStat == TASK_TRIGGER_STAT_PAUSED) {
taosTmrReset(tdRSmaFetchTrigger, pItem->maxDelay > 5000 ? 5000 : pItem->maxDelay, pItem, smaMgmt.tmrHandle,
&pItem->tmrId);
}
return;
}
default:

95
source/dnode/vnode/src/sma/smaUtil.c
View File

@ -313,4 +313,99 @@ int32_t tdReleaseSmaRef(int32_t rsetId, int64_t refId, const char *tags, int32_t
return TSDB_CODE_SUCCESS;
}
static int32_t tdCloneQTaskInfo(SSma *pSma, qTaskInfo_t dstTaskInfo, qTaskInfo_t srcTaskInfo, SRSmaParam *param,
tb_uid_t suid, int8_t idx) {
SVnode *pVnode = pSma->pVnode;
char *pOutput = NULL;
int32_t len = 0;
if (qSerializeTaskStatus(srcTaskInfo, &pOutput, &len) < 0) {
smaError("vgId:%d, rsma clone, table %" PRIi64 " serialize qTaskInfo failed since %s", TD_VID(pVnode), suid,
terrstr());
goto _err;
}
SReadHandle handle = {
.meta = pVnode->pMeta,
.vnode = pVnode,
.initTqReader = 1,
};
ASSERT(!dstTaskInfo);
dstTaskInfo = qCreateStreamExecTaskInfo(param->qmsg[idx], &handle);
if (!dstTaskInfo) {
terrno = TSDB_CODE_RSMA_QTASKINFO_CREATE;
goto _err;
}
if (qDeserializeTaskStatus(dstTaskInfo, pOutput, len) < 0) {
smaError("vgId:%d, rsma clone, restore rsma task for table:%" PRIi64 " failed since %s", TD_VID(pVnode), suid,
terrstr());
goto _err;
}
smaError("vgId:%d, rsma clone, restore rsma task for table:%" PRIi64 " succeed", TD_VID(pVnode), suid);
taosMemoryFreeClear(pOutput);
return TSDB_CODE_SUCCESS;
_err:
taosMemoryFreeClear(pOutput);
tdFreeQTaskInfo(dstTaskInfo, TD_VID(pVnode), idx + 1);
return TSDB_CODE_FAILED;
}
/**
* @brief pTSchema is shared
*
* @param pSma
* @param pDest
* @param pSrc
* @return int32_t
*/
int32_t tdCloneRSmaInfo(SSma *pSma, SRSmaInfo *pDest, SRSmaInfo *pSrc) {
SVnode *pVnode = pSma->pVnode;
SRSmaParam *param = NULL;
if (!pSrc) {
return TSDB_CODE_SUCCESS;
}
if (!pDest) {
pDest = taosMemoryCalloc(1, sizeof(SRSmaInfo));
if (!pDest) {
terrno = TSDB_CODE_OUT_OF_MEMORY;
return TSDB_CODE_FAILED;
}
}
memcpy(pDest, pSrc, sizeof(SRSmaInfo));
SMetaReader mr = {0};
metaReaderInit(&mr, SMA_META(pSma), 0);
smaDebug("vgId:%d, rsma clone, suid is %" PRIi64, TD_VID(pVnode), pSrc->suid);
if (metaGetTableEntryByUid(&mr, pSrc->suid) < 0) {
smaError("vgId:%d, rsma clone, failed to get table meta for %" PRIi64 " since %s", TD_VID(pVnode), pSrc->suid,
terrstr());
goto _err;
}
ASSERT(mr.me.type == TSDB_SUPER_TABLE);
ASSERT(mr.me.uid == pSrc->suid);
if (TABLE_IS_ROLLUP(mr.me.flags)) {
param = &mr.me.stbEntry.rsmaParam;
for (int i = 0; i < TSDB_RETENTION_L2; ++i) {
SRSmaInfoItem *pItem = &pSrc->items[i];
if (pItem->taskInfo) {
tdCloneQTaskInfo(pSma, pDest->items[i].taskInfo, pItem->taskInfo, param, pSrc->suid, i);
}
}
smaDebug("vgId:%d, rsma clone env success for %" PRIi64, TD_VID(pVnode), pSrc->suid);
}
metaReaderClear(&mr);
return TSDB_CODE_SUCCESS;
_err:
metaReaderClear(&mr);
tdFreeRSmaInfo(pSma, pDest, false);
return TSDB_CODE_FAILED;
}
// ...

14
source/dnode/vnode/src/tsdb/tsdbCache.c
View File

@ -476,9 +476,9 @@ static int32_t getNextRowFromFS(void *iter, TSDBROW **ppRow) {
if (--state->iFileSet >= 0) {
pFileSet = (SDFileSet *)taosArrayGet(state->aDFileSet, state->iFileSet);
} else {
// tBlockDataClear(&state->blockData);
// tBlockDataClear(&state->blockData, 1);
if (state->pBlockData) {
tBlockDataClear(state->pBlockData);
tBlockDataClear(state->pBlockData, 1);
state->pBlockData = NULL;
}
@ -500,9 +500,7 @@ static int32_t getNextRowFromFS(void *iter, TSDBROW **ppRow) {
if (code) goto _err;
/* if (state->pBlockIdx) { */
/* tBlockIdxReset(state->blockIdx); */
/* } */
/* tBlockIdxReset(state->blockIdx); */
/* code = tMapDataSearch(&state->blockIdxMap, state->pBlockIdxExp, tGetBlockIdx, tCmprBlockIdx,
* &state->blockIdx);
*/
@ -582,8 +580,8 @@ _err:
state->aBlockIdx = NULL;
}
if (state->pBlockData) {
// tBlockDataClear(&state->blockData);
tBlockDataClear(state->pBlockData);
// tBlockDataClear(&state->blockData, 1);
tBlockDataClear(state->pBlockData, 1);
state->pBlockData = NULL;
}
@ -609,8 +607,8 @@ int32_t clearNextRowFromFS(void *iter) {
state->aBlockIdx = NULL;
}
if (state->pBlockData) {
// tBlockDataClear(&state->blockData);
tBlockDataClear(state->pBlockData);
// tBlockDataClear(&state->blockData, 1);
tBlockDataClear(state->pBlockData, 1);
state->pBlockData = NULL;
}

17
source/dnode/vnode/src/tsdb/tsdbCommit.c
View File

@ -263,7 +263,7 @@ static int32_t tsdbCommitFileDataStart(SCommitter *pCommitter) {
taosArrayClear(pCommitter->aBlockIdx);
tMapDataReset(&pCommitter->oBlockMap);
tBlockDataReset(&pCommitter->oBlockData);
pRSet = tsdbFSStateGetDFileSet(pTsdb->fs->nState, pCommitter->commitFid);
pRSet = tsdbFSStateGetDFileSet(pTsdb->fs->nState, pCommitter->commitFid, TD_EQ);
if (pRSet) {
code = tsdbDataFReaderOpen(&pCommitter->pReader, pTsdb, pRSet);
if (code) goto _err;
@ -284,16 +284,7 @@ static int32_t tsdbCommitFileDataStart(SCommitter *pCommitter) {
.fLast = {.commitID = pCommitter->commitID, .size = 0},
.fSma = pRSet->fSma};
} else {
STfs *pTfs = pTsdb->pVnode->pTfs;
SDiskID did = {.level = 0, .id = 0};
// TODO: alloc a new disk
// tfsAllocDisk(pTfs, 0, &did);
// create the directory
tfsMkdirRecurAt(pTfs, pTsdb->path, did);
wSet = (SDFileSet){.diskId = did,
wSet = (SDFileSet){.diskId = (SDiskID){.level = 0, .id = 0},
.fid = pCommitter->commitFid,
.fHead = {.commitID = pCommitter->commitID, .offset = 0, .size = 0},
.fData = {.commitID = pCommitter->commitID, .size = 0},
@ -1001,10 +992,10 @@ _exit:
static void tsdbCommitDataEnd(SCommitter *pCommitter) {
taosArrayDestroy(pCommitter->aBlockIdx);
tMapDataClear(&pCommitter->oBlockMap);
tBlockDataClear(&pCommitter->oBlockData);
tBlockDataClear(&pCommitter->oBlockData, 1);
taosArrayDestroy(pCommitter->aBlockIdxN);
tMapDataClear(&pCommitter->nBlockMap);
tBlockDataClear(&pCommitter->nBlockData);
tBlockDataClear(&pCommitter->nBlockData, 1);
tTSchemaDestroy(pCommitter->skmTable.pTSchema);
tTSchemaDestroy(pCommitter->skmRow.pTSchema);
}

4
source/dnode/vnode/src/tsdb/tsdbFS.c
View File

@ -698,6 +698,6 @@ void tsdbFSStateDeleteDFileSet(STsdbFSState *pState, int32_t fid) {
SDelFile *tsdbFSStateGetDelFile(STsdbFSState *pState) { return pState->pDelFile; }
SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid) {
return (SDFileSet *)taosArraySearch(pState->aDFileSet, &(SDFileSet){.fid = fid}, tDFileSetCmprFn, TD_EQ);
SDFileSet *tsdbFSStateGetDFileSet(STsdbFSState *pState, int32_t fid, int32_t flag) {
return (SDFileSet *)taosArraySearch(pState->aDFileSet, &(SDFileSet){.fid = fid}, tDFileSetCmprFn, flag);
}

23
source/dnode/vnode/src/tsdb/tsdbRead.c
View File

@ -63,10 +63,10 @@ typedef struct SBlockLoadSuppInfo {
} SBlockLoadSuppInfo;
typedef struct SFilesetIter {
int32_t numOfFiles; // number of total files
int32_t index; // current accessed index in the list
SArray* pFileList; // data file list
int32_t order;
int32_t numOfFiles; // number of total files
int32_t index; // current accessed index in the list
SArray* pFileList; // data file list
int32_t order;
} SFilesetIter;
typedef struct SFileDataBlockInfo {
@ -830,8 +830,8 @@ static int32_t doLoadFileBlockData(STsdbReader* pReader, SDataBlockIter* pBlockI
SBlockLoadSuppInfo* pSupInfo = &pReader->suppInfo;
SFileBlockDumpInfo* pDumpInfo = &pReader->status.fBlockDumpInfo;
int32_t code = tsdbReadColData(pReader->pFileReader, &pBlockScanInfo->blockIdx, pBlock, pSupInfo->colIds, numOfCols,
pBlockData, NULL, NULL);
int32_t code = tsdbReadColData(pReader->pFileReader, &pBlockScanInfo->blockIdx, pBlock, pSupInfo->colIds, numOfCols,
pBlockData, NULL, NULL);
if (code != TSDB_CODE_SUCCESS) {
goto _error;
}
@ -1991,7 +1991,7 @@ static TSDBKEY getCurrentKeyInBuf(SDataBlockIter* pBlockIter, STsdbReader* pRead
static int32_t moveToNextFile(STsdbReader* pReader, int32_t* numOfBlocks) {
SReaderStatus* pStatus = &pReader->status;
SArray* pIndexList = taosArrayInit(4, sizeof(SBlockIdx));
SArray* pIndexList = taosArrayInit(4, sizeof(SBlockIdx));
while (1) {
bool hasNext = filesetIteratorNext(&pStatus->fileIter, pReader);
@ -3006,14 +3006,14 @@ SArray* tsdbRetrieveDataBlock(STsdbReader* pReader, SArray* pIdList) {
code = doLoadFileBlockData(pReader, &pStatus->blockIter, pBlockScanInfo, &pStatus->fileBlockData);
if (code != TSDB_CODE_SUCCESS) {
tBlockDataClear(&pStatus->fileBlockData);
tBlockDataClear(&pStatus->fileBlockData, 1);
terrno = code;
return NULL;
}
copyBlockDataToSDataBlock(pReader, pBlockScanInfo);
tBlockDataClear(&pStatus->fileBlockData);
tBlockDataClear(&pStatus->fileBlockData, 1);
return pReader->pResBlock->pDataBlock;
}
@ -3132,8 +3132,8 @@ int32_t tsdbGetFileBlocksDistInfo(STsdbReader* pReader, STableBlockDistInfo* pTa
hasNext = (pBlockIter->numOfBlocks > 0);
}
// tsdbDebug("%p %d blocks found in file for %d table(s), fid:%d, %s", pReader, numOfBlocks, numOfTables,
// pReader->pFileGroup->fid, pReader->idStr);
// tsdbDebug("%p %d blocks found in file for %d table(s), fid:%d, %s", pReader, numOfBlocks, numOfTables,
// pReader->pFileGroup->fid, pReader->idStr);
}
return code;
@ -3204,4 +3204,3 @@ int32_t tsdbGetTableSchema(SVnode* pVnode, int64_t uid, STSchema** pSchema, int6
return TSDB_CODE_SUCCESS;
}

28
source/dnode/vnode/src/tsdb/tsdbReaderWriter.c
View File

@ -979,21 +979,21 @@ int32_t tsdbReadColData(SDataFReader *pReader, SBlockIdx *pBlockIdx, SBlock *pBl
code = tBlockDataCopy(pBlockData, pBlockData2);
if (code) {
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
goto _err;
}
code = tBlockDataMerge(pBlockData1, pBlockData2, pBlockData);
if (code) {
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
goto _err;
}
}
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
}
tFree(pBuf1);
@ -1115,29 +1115,29 @@ int32_t tsdbReadBlockData(SDataFReader *pReader, SBlockIdx *pBlockIdx, SBlock *p
for (iSubBlock = 1; iSubBlock < pBlock->nSubBlock; iSubBlock++) {
code = tsdbReadSubBlockData(pReader, pBlockIdx, pBlock, iSubBlock, pBlockData1, ppBuf1, ppBuf2);
if (code) {
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
goto _err;
}
code = tBlockDataCopy(pBlockData, pBlockData2);
if (code) {
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
goto _err;
}
// merge two block data
code = tBlockDataMerge(pBlockData1, pBlockData2, pBlockData);
if (code) {
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
goto _err;
}
}
tBlockDataClear(pBlockData1);
tBlockDataClear(pBlockData2);
tBlockDataClear(pBlockData1, 1);
tBlockDataClear(pBlockData2, 1);
}
ASSERT(pBlock->nRow == pBlockData->nRow);

888
source/dnode/vnode/src/tsdb/tsdbSnapshot.c
View File

File diff suppressed because it is too large Load Diff

183
source/dnode/vnode/src/tsdb/tsdbUtil.c
View File

@ -36,15 +36,15 @@ int32_t tMapDataPutItem(SMapData *pMapData, void *pItem, int32_t (*tPutItemFn)(u
// alloc
code = tRealloc((uint8_t **)&pMapData->aOffset, sizeof(int32_t) * pMapData->nItem);
if (code) goto _err;
if (code) goto _exit;
code = tRealloc(&pMapData->pData, pMapData->nData);
if (code) goto _err;
if (code) goto _exit;
// put
pMapData->aOffset[nItem] = offset;
tPutItemFn(pMapData->pData + offset, pItem);
_err:
_exit:
return code;
}
@ -189,25 +189,12 @@ static FORCE_INLINE int32_t tGetTSDBKEY(uint8_t *p, TSDBKEY *pKey) {
}
// SBlockIdx ======================================================
void tBlockIdxReset(SBlockIdx *pBlockIdx) {
pBlockIdx->minKey = TSKEY_MAX;
pBlockIdx->maxKey = TSKEY_MIN;
pBlockIdx->minVersion = VERSION_MAX;
pBlockIdx->maxVersion = VERSION_MIN;
pBlockIdx->offset = -1;
pBlockIdx->size = -1;
}
int32_t tPutBlockIdx(uint8_t *p, void *ph) {
int32_t n = 0;
SBlockIdx *pBlockIdx = (SBlockIdx *)ph;
n += tPutI64(p ? p + n : p, pBlockIdx->suid);
n += tPutI64(p ? p + n : p, pBlockIdx->uid);
n += tPutI64(p ? p + n : p, pBlockIdx->minKey);
n += tPutI64(p ? p + n : p, pBlockIdx->maxKey);
n += tPutI64v(p ? p + n : p, pBlockIdx->minVersion);
n += tPutI64v(p ? p + n : p, pBlockIdx->maxVersion);
n += tPutI64v(p ? p + n : p, pBlockIdx->offset);
n += tPutI64v(p ? p + n : p, pBlockIdx->size);
@ -220,10 +207,6 @@ int32_t tGetBlockIdx(uint8_t *p, void *ph) {
n += tGetI64(p + n, &pBlockIdx->suid);
n += tGetI64(p + n, &pBlockIdx->uid);
n += tGetI64(p + n, &pBlockIdx->minKey);
n += tGetI64(p + n, &pBlockIdx->maxKey);
n += tGetI64v(p + n, &pBlockIdx->minVersion);
n += tGetI64v(p + n, &pBlockIdx->maxVersion);
n += tGetI64v(p + n, &pBlockIdx->offset);
n += tGetI64v(p + n, &pBlockIdx->size);
@ -921,6 +904,76 @@ _exit:
return code;
}
int32_t tPutColData(uint8_t *p, SColData *pColData) {
int32_t n = 0;
n += tPutI16v(p ? p + n : p, pColData->cid);
n += tPutI8(p ? p + n : p, pColData->type);
n += tPutI8(p ? p + n : p, pColData->smaOn);
n += tPutI32v(p ? p + n : p, pColData->nVal);
n += tPutU8(p ? p + n : p, pColData->flag);
if (pColData->flag == HAS_NONE || pColData->flag == HAS_NULL) goto _exit;
if (pColData->flag != HAS_VALUE) {
// bitmap
int32_t size = BIT2_SIZE(pColData->nVal);
if (p) {
memcpy(p + n, pColData->pBitMap, size);
}
n += size;
}
if (IS_VAR_DATA_TYPE(pColData->type)) {
// offset
int32_t size = sizeof(int32_t) * pColData->nVal;
if (p) {
memcpy(p + n, pColData->aOffset, size);
}
n += size;
}
n += tPutI32v(p ? p + n : p, pColData->nData);
if (p) {
memcpy(p + n, pColData->pData, pColData->nData);
}
n += pColData->nData;
_exit:
return n;
}
int32_t tGetColData(uint8_t *p, SColData *pColData) {
int32_t n = 0;
n += tGetI16v(p + n, &pColData->cid);
n += tGetI8(p + n, &pColData->type);
n += tGetI8(p + n, &pColData->smaOn);
n += tGetI32v(p + n, &pColData->nVal);
n += tGetU8(p + n, &pColData->flag);
if (pColData->flag == HAS_NONE || pColData->flag == HAS_NULL) goto _exit;
if (pColData->flag != HAS_VALUE) {
// bitmap
int32_t size = BIT2_SIZE(pColData->nVal);
pColData->pBitMap = p + n;
n += size;
}
if (IS_VAR_DATA_TYPE(pColData->type)) {
// offset
int32_t size = sizeof(int32_t) * pColData->nVal;
pColData->aOffset = (int32_t *)(p + n);
n += size;
}
n += tGetI32v(p + n, &pColData->nData);
pColData->pData = p + n;
n += pColData->nData;
_exit:
return n;
}
static FORCE_INLINE int32_t tColDataCmprFn(const void *p1, const void *p2) {
SColData *pColData1 = (SColData *)p1;
SColData *pColData2 = (SColData *)p2;
@ -962,11 +1015,11 @@ void tBlockDataReset(SBlockData *pBlockData) {
taosArrayClear(pBlockData->aIdx);
}
void tBlockDataClear(SBlockData *pBlockData) {
void tBlockDataClear(SBlockData *pBlockData, int8_t deepClear) {
tFree((uint8_t *)pBlockData->aVersion);
tFree((uint8_t *)pBlockData->aTSKEY);
taosArrayDestroy(pBlockData->aIdx);
taosArrayDestroyEx(pBlockData->aColData, tColDataClear);
taosArrayDestroyEx(pBlockData->aColData, deepClear ? tColDataClear : NULL);
}
int32_t tBlockDataSetSchema(SBlockData *pBlockData, STSchema *pTSchema) {
@ -1079,6 +1132,46 @@ _err:
return code;
}
int32_t tBlockDataCorrectSchema(SBlockData *pBlockData, SBlockData *pBlockDataFrom) {
int32_t code = 0;
int32_t iColData = 0;
for (int32_t iColDataFrom = 0; iColDataFrom < taosArrayGetSize(pBlockDataFrom->aIdx); iColDataFrom++) {
SColData *pColDataFrom = tBlockDataGetColDataByIdx(pBlockDataFrom, iColDataFrom);
while (true) {
SColData *pColData;
if (iColData < taosArrayGetSize(pBlockData->aIdx)) {
pColData = tBlockDataGetColDataByIdx(pBlockData, iColData);
} else {
pColData = NULL;
}
if (pColData == NULL || pColData->cid > pColDataFrom->cid) {
code = tBlockDataAddColData(pBlockData, iColData, &pColData);
if (code) goto _exit;
tColDataInit(pColData, pColDataFrom->cid, pColDataFrom->type, pColDataFrom->smaOn);
for (int32_t iRow = 0; iRow < pBlockData->nRow; iRow++) {
code = tColDataAppendValue(pColData, &COL_VAL_NONE(pColData->cid, pColData->type));
if (code) goto _exit;
}
iColData++;
break;
} else if (pColData->cid == pColDataFrom->cid) {
iColData++;
break;
} else {
iColData++;
}
}
}
_exit:
return code;
}
int32_t tBlockDataMerge(SBlockData *pBlockData1, SBlockData *pBlockData2, SBlockData *pBlockData) {
int32_t code = 0;
@ -1239,6 +1332,52 @@ void tBlockDataGetColData(SBlockData *pBlockData, int16_t cid, SColData **ppColD
*ppColData = NULL;
}
int32_t tPutBlockData(uint8_t *p, SBlockData *pBlockData) {
int32_t n = 0;
n += tPutI32v(p ? p + n : p, pBlockData->nRow);
if (p) {
memcpy(p + n, pBlockData->aVersion, sizeof(int64_t) * pBlockData->nRow);
}
n = n + sizeof(int64_t) * pBlockData->nRow;
if (p) {
memcpy(p + n, pBlockData->aTSKEY, sizeof(TSKEY) * pBlockData->nRow);
}
n = n + sizeof(TSKEY) * pBlockData->nRow;
int32_t nCol = taosArrayGetSize(pBlockData->aIdx);
n += tPutI32v(p ? p + n : p, nCol);
for (int32_t iCol = 0; iCol < nCol; iCol++) {
SColData *pColData = tBlockDataGetColDataByIdx(pBlockData, iCol);
n += tPutColData(p ? p + n : p, pColData);
}
return n;
}
int32_t tGetBlockData(uint8_t *p, SBlockData *pBlockData) {
int32_t n = 0;
tBlockDataReset(pBlockData);
n += tGetI32v(p + n, &pBlockData->nRow);
pBlockData->aVersion = (int64_t *)(p + n);
n = n + sizeof(int64_t) * pBlockData->nRow;
pBlockData->aTSKEY = (TSKEY *)(p + n);
n = n + sizeof(TSKEY) * pBlockData->nRow;
int32_t nCol;
n += tGetI32v(p + n, &nCol);
for (int32_t iCol = 0; iCol < nCol; iCol++) {
SColData *pColData;
if (tBlockDataAddColData(pBlockData, iCol, &pColData)) return -1;
n += tGetColData(p + n, pColData);
}
return n;
}
// ALGORITHM ==============================
void tsdbCalcColDataSMA(SColData *pColData, SColumnDataAgg *pColAgg) {
SColVal colVal;

8
source/dnode/vnode/src/vnd/vnodeCommit.c
View File

@ -233,7 +233,8 @@ int vnodeCommit(SVnode *pVnode) {
walBeginSnapshot(pVnode->pWal, pVnode->state.applied);
// preCommit
smaPreCommit(pVnode->pSma);
// smaSyncPreCommit(pVnode->pSma);
smaAsyncPreCommit(pVnode->pSma);
// commit each sub-system
if (metaCommit(pVnode->pMeta) < 0) {
@ -242,6 +243,8 @@ int vnodeCommit(SVnode *pVnode) {
}
if (VND_IS_RSMA(pVnode)) {
smaAsyncCommit(pVnode->pSma);
if (tsdbCommit(VND_RSMA0(pVnode)) < 0) {
ASSERT(0);
return -1;
@ -276,7 +279,8 @@ int vnodeCommit(SVnode *pVnode) {
pVnode->state.committed = info.state.committed;
// postCommit
smaPostCommit(pVnode->pSma);
// smaSyncPostCommit(pVnode->pSma);
smaAsyncPostCommit(pVnode->pSma);
// apply the commit (TODO)
walEndSnapshot(pVnode->pWal);

6
source/dnode/vnode/src/vnd/vnodeQuery.c
View File

@ -239,9 +239,9 @@ int32_t vnodeGetLoad(SVnode *pVnode, SVnodeLoad *pLoad) {
pLoad->vgId = TD_VID(pVnode);
pLoad->syncState = syncGetMyRole(pVnode->sync);
pLoad->numOfTables = metaGetTbNum(pVnode->pMeta);
pLoad->numOfTimeSeries = 400;
pLoad->totalStorage = 300;
pLoad->compStorage = 200;
pLoad->numOfTimeSeries = metaGetTimeSeriesNum(pVnode->pMeta);
pLoad->totalStorage = (int64_t)3 * 1073741824;
pLoad->compStorage = (int64_t)2 * 1073741824;
pLoad->pointsWritten = 100;
pLoad->numOfSelectReqs = 1;
pLoad->numOfInsertReqs = 3;

139
source/dnode/vnode/src/vnd/vnodeSnapshot.c
View File

@ -20,13 +20,13 @@ struct SVSnapReader {
SVnode *pVnode;
int64_t sver;
int64_t ever;
int64_t index;
// meta
int8_t metaDone;
SMetaSnapReader *pMetaReader;
// tsdb
int8_t tsdbDone;
STsdbSnapReader *pTsdbReader;
uint8_t *pData;
};
int32_t vnodeSnapReaderOpen(SVnode *pVnode, int64_t sver, int64_t ever, SVSnapReader **ppReader) {
@ -42,12 +42,7 @@ int32_t vnodeSnapReaderOpen(SVnode *pVnode, int64_t sver, int64_t ever, SVSnapRe
pReader->sver = sver;
pReader->ever = ever;
code = metaSnapReaderOpen(pVnode->pMeta, sver, ever, &pReader->pMetaReader);
if (code) goto _err;
code = tsdbSnapReaderOpen(pVnode->pTsdb, sver, ever, &pReader->pTsdbReader);
if (code) goto _err;
vInfo("vgId:%d vnode snapshot reader opened, sver:%" PRId64 " ever:%" PRId64, TD_VID(pVnode), sver, ever);
*ppReader = pReader;
return code;
@ -60,54 +55,85 @@ _err:
int32_t vnodeSnapReaderClose(SVSnapReader *pReader) {
int32_t code = 0;
tFree(pReader->pData);
if (pReader->pTsdbReader) tsdbSnapReaderClose(&pReader->pTsdbReader);
if (pReader->pMetaReader) metaSnapReaderClose(&pReader->pMetaReader);
taosMemoryFree(pReader);
if (pReader->pTsdbReader) {
tsdbSnapReaderClose(&pReader->pTsdbReader);
}
if (pReader->pMetaReader) {
metaSnapReaderClose(&pReader->pMetaReader);
}
vInfo("vgId:%d vnode snapshot reader closed", TD_VID(pReader->pVnode));
taosMemoryFree(pReader);
return code;
}
int32_t vnodeSnapRead(SVSnapReader *pReader, uint8_t **ppData, uint32_t *nData) {
int32_t code = 0;
// META ==============
if (!pReader->metaDone) {
code = metaSnapRead(pReader->pMetaReader, &pReader->pData);
// open reader if not
if (pReader->pMetaReader == NULL) {
code = metaSnapReaderOpen(pReader->pVnode->pMeta, pReader->sver, pReader->ever, &pReader->pMetaReader);
if (code) goto _err;
}
code = metaSnapRead(pReader->pMetaReader, ppData);
if (code) {
if (code == TSDB_CODE_VND_READ_END) {
goto _err;
} else {
if (*ppData) {
goto _exit;
} else {
pReader->metaDone = 1;
} else {
goto _err;
code = metaSnapReaderClose(&pReader->pMetaReader);
if (code) goto _err;
}
} else {
*ppData = pReader->pData;
*nData = sizeof(SSnapDataHdr) + ((SSnapDataHdr *)pReader->pData)->size;
goto _exit;
}
}
// TSDB ==============
if (!pReader->tsdbDone) {
code = tsdbSnapRead(pReader->pTsdbReader, &pReader->pData);
// open if not
if (pReader->pTsdbReader == NULL) {
code = tsdbSnapReaderOpen(pReader->pVnode->pTsdb, pReader->sver, pReader->ever, &pReader->pTsdbReader);
if (code) goto _err;
}
code = tsdbSnapRead(pReader->pTsdbReader, ppData);
if (code) {
if (code == TSDB_CODE_VND_READ_END) {
pReader->tsdbDone = 1;
} else {
goto _err;
}
goto _err;
} else {
*ppData = pReader->pData;
*nData = sizeof(SSnapDataHdr) + ((SSnapDataHdr *)pReader->pData)->size;
goto _exit;
if (*ppData) {
goto _exit;
} else {
pReader->tsdbDone = 1;
code = tsdbSnapReaderClose(&pReader->pTsdbReader);
if (code) goto _err;
}
}
}
code = TSDB_CODE_VND_READ_END;
*ppData = NULL;
*nData = 0;
_exit:
if (*ppData) {
SSnapDataHdr *pHdr = (SSnapDataHdr *)(*ppData);
pReader->index++;
*nData = sizeof(SSnapDataHdr) + pHdr->size;
pHdr->index = pReader->index;
vInfo("vgId:%d vnode snapshot read data,index:%" PRId64 " type:%d nData:%d ", TD_VID(pReader->pVnode),
pReader->index, pHdr->type, *nData);
} else {
vInfo("vgId:%d vnode snapshot read data end, index:%" PRId64, TD_VID(pReader->pVnode), pReader->index);
}
return code;
_err:
vError("vgId:% snapshot read failed since %s", TD_VID(pReader->pVnode), tstrerror(code));
vError("vgId:% vnode snapshot read failed since %s", TD_VID(pReader->pVnode), tstrerror(code));
return code;
}
@ -116,24 +142,13 @@ struct SVSnapWriter {
SVnode *pVnode;
int64_t sver;
int64_t ever;
int64_t index;
// meta
SMetaSnapWriter *pMetaSnapWriter;
// tsdb
STsdbSnapWriter *pTsdbSnapWriter;
};
static int32_t vnodeSnapRollback(SVSnapWriter *pWriter) {
int32_t code = 0;
// TODO
return code;
}
static int32_t vnodeSnapCommit(SVSnapWriter *pWriter) {
int32_t code = 0;
// TODO
return code;
}
int32_t vnodeSnapWriterOpen(SVnode *pVnode, int64_t sver, int64_t ever, SVSnapWriter **ppWriter) {
int32_t code = 0;
SVSnapWriter *pWriter = NULL;
@ -148,62 +163,78 @@ int32_t vnodeSnapWriterOpen(SVnode *pVnode, int64_t sver, int64_t ever, SVSnapWr
pWriter->sver = sver;
pWriter->ever = ever;
vInfo("vgId:%d vnode snapshot writer opened", TD_VID(pVnode));
*ppWriter = pWriter;
return code;
_err:
vError("vgId:%d vnode snapshot writer open failed since %s", TD_VID(pVnode), tstrerror(code));
*ppWriter = NULL;
return code;
}
int32_t vnodeSnapWriterClose(SVSnapWriter *pWriter, int8_t rollback) {
int32_t code = 0;
if (rollback) {
code = vnodeSnapRollback(pWriter);
if (code) goto _err;
} else {
code = vnodeSnapCommit(pWriter);
if (pWriter->pMetaSnapWriter) {
code = metaSnapWriterClose(&pWriter->pMetaSnapWriter, rollback);
if (code) goto _err;
}
if (pWriter->pTsdbSnapWriter) {
code = tsdbSnapWriterClose(&pWriter->pTsdbSnapWriter, rollback);
if (code) goto _err;
}
_exit:
vInfo("vgId:%d vnode snapshot writer closed, rollback:%d", TD_VID(pWriter->pVnode), rollback);
taosMemoryFree(pWriter);
return code;
_err:
vError("vgId:%d vnode snapshow writer close failed since %s", TD_VID(pWriter->pVnode), tstrerror(code));
vError("vgId:%d vnode snapshot writer close failed since %s", TD_VID(pWriter->pVnode), tstrerror(code));
return code;
}
int32_t vnodeSnapWrite(SVSnapWriter *pWriter, uint8_t *pData, uint32_t nData) {
int32_t code = 0;
SSnapDataHdr *pSnapDataHdr = (SSnapDataHdr *)pData;
SSnapDataHdr *pHdr = (SSnapDataHdr *)pData;
SVnode *pVnode = pWriter->pVnode;
ASSERT(pSnapDataHdr->size + sizeof(SSnapDataHdr) == nData);
ASSERT(pHdr->size + sizeof(SSnapDataHdr) == nData);
ASSERT(pHdr->index == pWriter->index + 1);
pWriter->index = pHdr->index;
if (pSnapDataHdr->type == 0) {
vInfo("vgId:%d vnode snapshot write data, index:%" PRId64 " type:%d nData:%d", TD_VID(pVnode), pHdr->index,
pHdr->type, nData);
if (pHdr->type == 0) {
// meta
if (pWriter->pMetaSnapWriter == NULL) {
code = metaSnapWriterOpen(pVnode->pMeta, pWriter->sver, pWriter->ever, &pWriter->pMetaSnapWriter);
if (code) goto _err;
}
code = metaSnapWrite(pWriter->pMetaSnapWriter, pData + sizeof(SSnapDataHdr), nData - sizeof(SSnapDataHdr));
code = metaSnapWrite(pWriter->pMetaSnapWriter, pData, nData);
if (code) goto _err;
} else {
// tsdb
if (pWriter->pTsdbSnapWriter == NULL) {
code = tsdbSnapWriterOpen(pVnode->pTsdb, pWriter->sver, pWriter->ever, &pWriter->pTsdbSnapWriter);
if (code) goto _err;
}
code = tsdbSnapWrite(pWriter->pTsdbSnapWriter, pData + sizeof(SSnapDataHdr), nData - sizeof(SSnapDataHdr));
code = tsdbSnapWrite(pWriter->pTsdbSnapWriter, pData, nData);
if (code) goto _err;
}
_exit:
return code;
_err:
vError("vgId:%d vnode snapshot write failed since %s", TD_VID(pVnode), tstrerror(code));
vError("vgId:%d vnode snapshot write failed since %s, index:%" PRId64 " type:%d nData:%d", TD_VID(pVnode),
tstrerror(code), pHdr->index, pHdr->type, nData);
return code;
}

3
source/dnode/vnode/src/vnd/vnodeSvr.c
View File

@ -689,6 +689,7 @@ _exit:
tEncoderInit(&encoder, pRsp->pCont, pRsp->contLen);
tEncodeSVDropTbBatchRsp(&encoder, &rsp);
tEncoderClear(&encoder);
taosArrayDestroy(rsp.pArray);
return 0;
}
@ -900,7 +901,7 @@ static int32_t vnodeProcessCreateTSmaReq(SVnode *pVnode, int64_t version, void *
_err:
tDecoderClear(&coder);
vError("vgId:%d, failed to create tsma %s:%" PRIi64 " version %" PRIi64 "for table %" PRIi64 " since %s",
TD_VID(pVnode), req.indexName, req.indexUid, version, req.tableUid, terrstr(terrno));
TD_VID(pVnode), req.indexName, req.indexUid, version, req.tableUid, terrstr());
return -1;
}

6
source/libs/catalog/src/ctgAsync.c
View File

@ -163,7 +163,7 @@ int32_t ctgInitGetQnodeTask(SCtgJob *pJob, int32_t taskIdx, void* param) {
taosArrayPush(pJob->pTasks, &task);
qDebug("QID:0x%" PRIx64 " the %d task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
qDebug("QID:0x%" PRIx64 " the %dth task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
return TSDB_CODE_SUCCESS;
}
@ -178,7 +178,7 @@ int32_t ctgInitGetDnodeTask(SCtgJob *pJob, int32_t taskIdx, void* param) {
taosArrayPush(pJob->pTasks, &task);
qDebug("QID:0x%" PRIx64 " the %d task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
qDebug("QID:0x%" PRIx64 " the %dth task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
return TSDB_CODE_SUCCESS;
}
@ -264,7 +264,7 @@ int32_t ctgInitGetSvrVerTask(SCtgJob *pJob, int32_t taskIdx, void* param) {
taosArrayPush(pJob->pTasks, &task);
qDebug("QID:0x%" PRIx64 " [%dth] task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
qDebug("QID:0x%" PRIx64 " the %dth task type %s initialized", pJob->queryId, taskIdx, ctgTaskTypeStr(task.type));
return TSDB_CODE_SUCCESS;
}

4
source/libs/catalog/src/ctgUtil.c
View File

@ -272,7 +272,7 @@ void ctgFreeHandle(SCatalog* pCtg) {
taosMemoryFree(pCtg);
ctgInfo("handle freed, culsterId:0x%" PRIx64, clusterId);
ctgInfo("handle freed, clusterId:0x%" PRIx64, clusterId);
}
void ctgClearHandle(SCatalog* pCtg) {
@ -303,7 +303,7 @@ void ctgClearHandle(SCatalog* pCtg) {
CTG_CACHE_STAT_INC(numOfClear, 1);
ctgInfo("handle cleared, culsterId:0x%" PRIx64, clusterId);
ctgInfo("handle cleared, clusterId:0x%" PRIx64, clusterId);
}
void ctgFreeSUseDbOutput(SUseDbOutput* pOutput) {

3
source/libs/executor/src/executil.c
View File

@ -115,9 +115,6 @@ void initGroupedResultInfo(SGroupResInfo* pGroupResInfo, SHashObj* pHashmap, int
p->groupId = *(uint64_t*)key;
p->pos = *(SResultRowPosition*)pData;
memcpy(p->key, (char*)key + sizeof(uint64_t), keyLen - sizeof(uint64_t));
#ifdef BUF_PAGE_DEBUG
qDebug("page_groupRes, groupId:%" PRIu64 ",pageId:%d,offset:%d\n", p->groupId, p->pos.pageId, p->pos.offset);
#endif
taosArrayPush(pGroupResInfo->pRows, &p);
}

13
source/libs/executor/src/executorimpl.c
View File

@ -1506,15 +1506,11 @@ int32_t doCopyToSDataBlock(SExecTaskInfo* pTaskInfo, SSDataBlock* pBlock, SExprI
int32_t numOfExprs) {
int32_t numOfRows = getNumOfTotalRes(pGroupResInfo);
int32_t start = pGroupResInfo->index;
#ifdef BUF_PAGE_DEBUG
qDebug("\npage_copytoblock rows:%d", numOfRows);
#endif
for (int32_t i = start; i < numOfRows; i += 1) {
SResKeyPos* pPos = taosArrayGetP(pGroupResInfo->pRows, i);
SFilePage* page = getBufPage(pBuf, pPos->pos.pageId);
#ifdef BUF_PAGE_DEBUG
qDebug("page_copytoblock pos pageId:%d, offset:%d", pPos->pos.pageId, pPos->pos.offset);
#endif
SResultRow* pRow = (SResultRow*)((char*)page + pPos->pos.offset);
doUpdateNumOfRows(pRow, numOfExprs, rowCellOffset);
@ -1980,6 +1976,7 @@ int32_t loadRemoteDataCallback(void* param, SDataBuf* pMsg, int32_t code) {
qDebug("%s fetch rsp received, index:%d, rows:%d", pSourceDataInfo->taskId, index, pRsp->numOfRows);
} else {
pSourceDataInfo->code = code;
qDebug("%s fetch rsp received, index:%d, error:%d", pSourceDataInfo->taskId, index, tstrerror(code));
}
pSourceDataInfo->status = EX_SOURCE_DATA_READY;
@ -2221,6 +2218,8 @@ static SSDataBlock* concurrentlyLoadRemoteDataImpl(SOperatorInfo* pOperator, SEx
if (completed == totalSources) {
return setAllSourcesCompleted(pOperator, startTs);
}
sched_yield();
}
_error:
@ -3747,7 +3746,7 @@ void doDestroyExchangeOperatorInfo(void* param) {
taosArrayDestroy(pExInfo->pSources);
taosArrayDestroy(pExInfo->pSourceDataInfo);
if (pExInfo->pResult != NULL) {
blockDataDestroy(pExInfo->pResult);
pExInfo->pResult = blockDataDestroy(pExInfo->pResult);
}
tsem_destroy(&pExInfo->ready);

69
source/libs/executor/src/groupoperator.c
View File

@ -29,7 +29,7 @@
static void* getCurrentDataGroupInfo(const SPartitionOperatorInfo* pInfo, SDataGroupInfo** pGroupInfo, int32_t len);
static int32_t* setupColumnOffset(const SSDataBlock* pBlock, int32_t rowCapacity);
static int32_t setGroupResultOutputBuf(SOperatorInfo* pOperator, SOptrBasicInfo* binfo, int32_t numOfCols, char* pData, int16_t bytes,
int32_t groupId, SDiskbasedBuf* pBuf, SAggSupporter* pAggSup);
uint64_t groupId, SDiskbasedBuf* pBuf, SAggSupporter* pAggSup);
static void destroyGroupOperatorInfo(void* param, int32_t numOfOutput) {
SGroupbyOperatorInfo* pInfo = (SGroupbyOperatorInfo*)param;
@ -264,7 +264,7 @@ static void doHashGroupbyAgg(SOperatorInfo* pOperator, SSDataBlock* pBlock) {
}
len = buildGroupKeys(pInfo->keyBuf, pInfo->pGroupColVals);
int32_t ret = setGroupResultOutputBuf(pOperator, &(pInfo->binfo), pOperator->exprSupp.numOfExprs, pInfo->keyBuf, len, 0, pInfo->aggSup.pResultBuf, &pInfo->aggSup);
int32_t ret = setGroupResultOutputBuf(pOperator, &(pInfo->binfo), pOperator->exprSupp.numOfExprs, pInfo->keyBuf, len, pBlock->info.groupId, pInfo->aggSup.pResultBuf, &pInfo->aggSup);
if (ret != TSDB_CODE_SUCCESS) { // null data, too many state code
longjmp(pTaskInfo->env, TSDB_CODE_QRY_APP_ERROR);
}
@ -282,7 +282,7 @@ static void doHashGroupbyAgg(SOperatorInfo* pOperator, SSDataBlock* pBlock) {
len = buildGroupKeys(pInfo->keyBuf, pInfo->pGroupColVals);
int32_t ret =
setGroupResultOutputBuf(pOperator, &(pInfo->binfo), pOperator->exprSupp.numOfExprs, pInfo->keyBuf, len,
0, pInfo->aggSup.pResultBuf, &pInfo->aggSup);
pBlock->info.groupId, pInfo->aggSup.pResultBuf, &pInfo->aggSup);
if (ret != TSDB_CODE_SUCCESS) {
longjmp(pTaskInfo->env, TSDB_CODE_QRY_APP_ERROR);
}
@ -293,6 +293,29 @@ static void doHashGroupbyAgg(SOperatorInfo* pOperator, SSDataBlock* pBlock) {
}
}
static SSDataBlock* buildGroupResultDataBlock(SOperatorInfo* pOperator) {
SGroupbyOperatorInfo* pInfo = pOperator->info;
SSDataBlock* pRes = pInfo->binfo.pRes;
while(1) {
doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
doFilter(pInfo->pCondition, pRes);
bool hasRemain = hasDataInGroupInfo(&pInfo->groupResInfo);
if (!hasRemain) {
doSetOperatorCompleted(pOperator);
break;
}
if (pRes->info.rows > 0) {
break;
}
}
pOperator->resultInfo.totalRows += pRes->info.rows;
return (pRes->info.rows == 0)? NULL:pRes;
}
static SSDataBlock* hashGroupbyAggregate(SOperatorInfo* pOperator) {
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
@ -304,22 +327,7 @@ static SSDataBlock* hashGroupbyAggregate(SOperatorInfo* pOperator) {
SSDataBlock* pRes = pInfo->binfo.pRes;
if (pOperator->status == OP_RES_TO_RETURN) {
while(1) {
doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
doFilter(pInfo->pCondition, pRes);
bool hasRemain = hasDataInGroupInfo(&pInfo->groupResInfo);
if (!hasRemain) {
doSetOperatorCompleted(pOperator);
break;
}
if (pRes->info.rows > 0) {
break;
}
}
pOperator->resultInfo.totalRows += pRes->info.rows;
return (pRes->info.rows == 0)? NULL:pRes;
return buildGroupResultDataBlock(pOperator);
}
int32_t order = TSDB_ORDER_ASC;
@ -373,26 +381,7 @@ static SSDataBlock* hashGroupbyAggregate(SOperatorInfo* pOperator) {
initGroupedResultInfo(&pInfo->groupResInfo, pInfo->aggSup.pResultRowHashTable, 0);
pOperator->cost.openCost = (taosGetTimestampUs() - st) / 1000.0;
while(1) {
doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
doFilter(pInfo->pCondition, pRes);
bool hasRemain = hasDataInGroupInfo(&pInfo->groupResInfo);
if (!hasRemain) {
doSetOperatorCompleted(pOperator);
break;
}
if (pRes->info.rows > 0) {
break;
}
}
size_t rows = pRes->info.rows;
pOperator->resultInfo.totalRows += rows;
return (rows == 0)? NULL:pRes;
return buildGroupResultDataBlock(pOperator);
}
SOperatorInfo* createGroupOperatorInfo(SOperatorInfo* downstream, SExprInfo* pExprInfo, int32_t numOfCols,
@ -800,7 +789,7 @@ SOperatorInfo* createPartitionOperatorInfo(SOperatorInfo* downstream, SPartition
}
int32_t setGroupResultOutputBuf(SOperatorInfo* pOperator, SOptrBasicInfo* binfo, int32_t numOfCols, char* pData, int16_t bytes,
int32_t groupId, SDiskbasedBuf* pBuf, SAggSupporter* pAggSup) {
uint64_t groupId, SDiskbasedBuf* pBuf, SAggSupporter* pAggSup) {
SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
SResultRowInfo* pResultRowInfo = &binfo->resultRowInfo;
SqlFunctionCtx* pCtx = pOperator->exprSupp.pCtx;

595
source/libs/executor/src/scanoperator.c
View File

@ -1143,7 +1143,7 @@ static void checkUpdateData(SStreamScanInfo* pInfo, bool invertible, SSDataBlock
STimeWindow win = getActiveTimeWindow(NULL, &dumyInfo, tsCol[rowId], &pInfo->interval, TSDB_ORDER_ASC);
// must check update info first.
bool update = updateInfoIsUpdated(pInfo->pUpdateInfo, pBlock->info.uid, tsCol[rowId]);
if ( (update || (isSignleIntervalWindow(pInfo) && isCloseWindow(&win, &pInfo->twAggSup)) ) && out) {
if ((update || (isSignleIntervalWindow(pInfo) && isCloseWindow(&win, &pInfo->twAggSup))) && out) {
taosArrayPush(pInfo->tsArray, &rowId);
}
}
@ -1596,7 +1596,8 @@ SOperatorInfo* createStreamScanOperatorInfo(SReadHandle* pHandle, STableScanPhys
pInfo->pUpdateRes = createResDataBlock(pDescNode);
pInfo->pCondition = pScanPhyNode->node.pConditions;
pInfo->scanMode = STREAM_SCAN_FROM_READERHANDLE;
pInfo->sessionSup = (SessionWindowSupporter){.pStreamAggSup = NULL, .gap = -1, .parentType = QUERY_NODE_PHYSICAL_PLAN};
pInfo->sessionSup =
(SessionWindowSupporter){.pStreamAggSup = NULL, .gap = -1, .parentType = QUERY_NODE_PHYSICAL_PLAN};
pInfo->groupId = 0;
pInfo->pPullDataRes = createPullDataBlock();
pInfo->pStreamScanOp = pOperator;
@ -1630,7 +1631,8 @@ static void destroySysScanOperator(void* param, int32_t numOfOutput) {
blockDataDestroy(pInfo->pRes);
const char* name = tNameGetTableName(&pInfo->name);
if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0 || pInfo->pCur != NULL) {
if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0 ||
strncasecmp(name, TSDB_INS_TABLE_USER_TAGS, TSDB_TABLE_FNAME_LEN) == 0 || pInfo->pCur != NULL) {
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
}
@ -1777,14 +1779,14 @@ static SSDataBlock* doFilterResult(SSysTableScanInfo* pInfo) {
return pInfo->pRes->info.rows == 0 ? NULL : pInfo->pRes;
}
static SSDataBlock* buildSysTableMetaBlock() {
static SSDataBlock* buildInfoSchemaTableMetaBlock(char* tableName) {
size_t size = 0;
const SSysTableMeta* pMeta = NULL;
getInfosDbMeta(&pMeta, &size);
int32_t index = 0;
for (int32_t i = 0; i < size; ++i) {
if (strcmp(pMeta[i].name, TSDB_INS_TABLE_USER_TABLES) == 0) {
if (strcmp(pMeta[i].name, tableName) == 0) {
index = i;
break;
}
@ -1800,185 +1802,418 @@ static SSDataBlock* buildSysTableMetaBlock() {
return pBlock;
}
// TODO: check more datatype, json? and return detailed error when len is not enough
static int32_t convertTagDataToTagVarchar(int8_t tagType, char* tagVal, uint32_t tagLen, char* varData,
int32_t bufSize) {
int outputLen = -1;
switch (tagType) {
case TSDB_DATA_TYPE_TINYINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%d", *((int8_t*)tagVal));
break;
case TSDB_DATA_TYPE_UTINYINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%u", *((uint8_t*)tagVal));
break;
case TSDB_DATA_TYPE_SMALLINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%d", *((int16_t*)tagVal));
break;
case TSDB_DATA_TYPE_USMALLINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%u", *((uint16_t*)tagVal));
break;
case TSDB_DATA_TYPE_INT:
outputLen = snprintf(varDataVal(varData), bufSize, "%d", *((int32_t*)tagVal));
break;
case TSDB_DATA_TYPE_UINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%u", *((uint32_t*)tagVal));
break;
case TSDB_DATA_TYPE_BIGINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%" PRId64, *((int64_t*)tagVal));
break;
case TSDB_DATA_TYPE_UBIGINT:
outputLen = snprintf(varDataVal(varData), bufSize, "%" PRIu64, *((uint64_t*)tagVal));
break;
case TSDB_DATA_TYPE_FLOAT: {
float fv = 0;
fv = GET_FLOAT_VAL(tagVal);
outputLen = snprintf(varDataVal(varData), bufSize, "%f", fv);
break;
}
case TSDB_DATA_TYPE_DOUBLE: {
double dv = 0;
dv = GET_DOUBLE_VAL(tagVal);
outputLen = snprintf(varDataVal(varData), bufSize, "%lf", dv);
break;
}
case TSDB_DATA_TYPE_BINARY:
case TSDB_DATA_TYPE_NCHAR:
case TSDB_DATA_TYPE_JSON: {
memcpy(varDataVal(varData), tagVal, tagLen);
outputLen = tagLen;
break;
}
case TSDB_DATA_TYPE_TIMESTAMP:
outputLen = snprintf(varDataVal(varData), bufSize, "%" PRId64, *((int64_t*)tagVal));
break;
case TSDB_DATA_TYPE_BOOL:
outputLen = snprintf(varDataVal(varData), bufSize, "%d", *((int8_t*)tagVal));
break;
default:
return TSDB_CODE_FAILED;
}
if (outputLen < 0 || outputLen == bufSize && !IS_VAR_DATA_TYPE(tagType) || outputLen > bufSize) {
return TSDB_CODE_FAILED;
}
varDataSetLen(varData, outputLen);
return TSDB_CODE_SUCCESS;
}
static SSDataBlock* sysTableScanUserTags(SOperatorInfo* pOperator) {
SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
SSysTableScanInfo* pInfo = pOperator->info;
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
}
if (pInfo->pCur == NULL) {
pInfo->pCur = metaOpenTbCursor(pInfo->readHandle.meta);
}
blockDataCleanup(pInfo->pRes);
int32_t numOfRows = 0;
const char* db = NULL;
int32_t vgId = 0;
vnodeGetInfo(pInfo->readHandle.vnode, &db, &vgId);
SName sn = {0};
char dbname[TSDB_DB_FNAME_LEN + VARSTR_HEADER_SIZE] = {0};
tNameFromString(&sn, db, T_NAME_ACCT | T_NAME_DB);
tNameGetDbName(&sn, varDataVal(dbname));
varDataSetLen(dbname, strlen(varDataVal(dbname)));
SSDataBlock* p = buildInfoSchemaTableMetaBlock(TSDB_INS_TABLE_USER_TAGS);
blockDataEnsureCapacity(p, pOperator->resultInfo.capacity);
int32_t ret = 0;
while ((ret = metaTbCursorNext(pInfo->pCur)) == 0) {
if (pInfo->pCur->mr.me.type != TSDB_CHILD_TABLE) {
continue;
}
char tableName[TSDB_TABLE_NAME_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(tableName, pInfo->pCur->mr.me.name);
SMetaReader smr = {0};
metaReaderInit(&smr, pInfo->readHandle.meta, 0);
uint64_t suid = pInfo->pCur->mr.me.ctbEntry.suid;
int32_t code = metaGetTableEntryByUid(&smr, suid);
if (code != TSDB_CODE_SUCCESS) {
qError("failed to get super table meta, uid:0x%" PRIx64 ", code:%s, %s", suid, tstrerror(terrno),
GET_TASKID(pTaskInfo));
metaReaderClear(&smr);
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
longjmp(pTaskInfo->env, terrno);
}
char stableName[TSDB_TABLE_NAME_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(stableName, smr.me.name);
int32_t numOfTags = smr.me.stbEntry.schemaTag.nCols;
for (int32_t i = 0; i < numOfTags; ++i) {
SColumnInfoData* pColInfoData = NULL;
// table name
pColInfoData = taosArrayGet(p->pDataBlock, 0);
colDataAppend(pColInfoData, numOfRows, tableName, false);
// database name
pColInfoData = taosArrayGet(p->pDataBlock, 1);
colDataAppend(pColInfoData, numOfRows, dbname, false);
// super table name
pColInfoData = taosArrayGet(p->pDataBlock, 2);
colDataAppend(pColInfoData, numOfRows, stableName, false);
char tagName[TSDB_COL_NAME_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(tagName, smr.me.stbEntry.schemaTag.pSchema[i].name);
pColInfoData = taosArrayGet(p->pDataBlock, 3);
colDataAppend(pColInfoData, numOfRows, tagName, false);
int8_t tagType = smr.me.stbEntry.schemaTag.pSchema[i].type;
pColInfoData = taosArrayGet(p->pDataBlock, 4);
colDataAppend(pColInfoData, numOfRows, (char*)&tagType, false);
STagVal tagVal = {0};
tagVal.cid = smr.me.stbEntry.schemaTag.pSchema[i].colId;
char* tagData = NULL;
uint32_t tagLen = 0;
if (tagType == TSDB_DATA_TYPE_JSON) {
// TODO: json type?+varheader+data
tagData = varDataVal(pInfo->pCur->mr.me.ctbEntry.pTags + 1);
tagLen = varDataLen(pInfo->pCur->mr.me.ctbEntry.pTags + 1);
} else {
bool exist = tTagGet((STag*)pInfo->pCur->mr.me.ctbEntry.pTags, &tagVal);
if (exist) {
if (IS_VAR_DATA_TYPE(tagType)) {
tagData = (char*)tagVal.pData;
tagLen = tagVal.nData;
} else {
tagData = (char*)&tagVal.i64;
tagLen = tDataTypes[tagType].bytes;
}
}
}
int32_t bufSize = IS_VAR_DATA_TYPE(tagType) ? (tagLen + VARSTR_HEADER_SIZE)
: (3 + DBL_MANT_DIG - DBL_MIN_EXP + VARSTR_HEADER_SIZE);
char* tagVarChar = NULL;
if (tagData != NULL) {
tagVarChar = taosMemoryMalloc(bufSize);
code = convertTagDataToTagVarchar(tagType, tagData, tagLen, tagVarChar, bufSize);
if (code != TSDB_CODE_SUCCESS) {
qError("failed to get super table meta, uid:0x%" PRIx64 ", code:%s, %s", suid, tstrerror(terrno),
GET_TASKID(pTaskInfo));
taosMemoryFree(tagVarChar);
metaReaderClear(&smr);
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
longjmp(pTaskInfo->env, terrno);
}
}
pColInfoData = taosArrayGet(p->pDataBlock, 5);
colDataAppend(pColInfoData, numOfRows, tagVarChar,
(tagData == NULL) || (tagType == TSDB_DATA_TYPE_JSON && tTagIsJsonNull(tagData)));
taosMemoryFree(tagVarChar);
++numOfRows;
}
metaReaderClear(&smr);
if (numOfRows >= pOperator->resultInfo.capacity) {
break;
}
}
// todo temporarily free the cursor here, the true reason why the free is not valid needs to be found
if (ret != 0) {
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
doSetOperatorCompleted(pOperator);
}
p->info.rows = numOfRows;
pInfo->pRes->info.rows = numOfRows;
relocateColumnData(pInfo->pRes, pInfo->scanCols, p->pDataBlock, false);
doFilterResult(pInfo);
blockDataDestroy(p);
pInfo->loadInfo.totalRows += pInfo->pRes->info.rows;
return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
}
static SSDataBlock* sysTableScanUserTables(SOperatorInfo* pOperator) {
SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
SSysTableScanInfo* pInfo = pOperator->info;
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
}
// the retrieve is executed on the mnode, so return tables that belongs to the information schema database.
if (pInfo->readHandle.mnd != NULL) {
buildSysDbTableInfo(pInfo, pOperator->resultInfo.capacity);
doFilterResult(pInfo);
pInfo->loadInfo.totalRows += pInfo->pRes->info.rows;
doSetOperatorCompleted(pOperator);
return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
} else {
if (pInfo->pCur == NULL) {
pInfo->pCur = metaOpenTbCursor(pInfo->readHandle.meta);
}
blockDataCleanup(pInfo->pRes);
int32_t numOfRows = 0;
const char* db = NULL;
int32_t vgId = 0;
vnodeGetInfo(pInfo->readHandle.vnode, &db, &vgId);
SName sn = {0};
char dbname[TSDB_DB_FNAME_LEN + VARSTR_HEADER_SIZE] = {0};
tNameFromString(&sn, db, T_NAME_ACCT | T_NAME_DB);
tNameGetDbName(&sn, varDataVal(dbname));
varDataSetLen(dbname, strlen(varDataVal(dbname)));
SSDataBlock* p = buildInfoSchemaTableMetaBlock(TSDB_INS_TABLE_USER_TABLES);
blockDataEnsureCapacity(p, pOperator->resultInfo.capacity);
char n[TSDB_TABLE_NAME_LEN + VARSTR_HEADER_SIZE] = {0};
int32_t ret = 0;
while ((ret = metaTbCursorNext(pInfo->pCur)) == 0) {
STR_TO_VARSTR(n, pInfo->pCur->mr.me.name);
// table name
SColumnInfoData* pColInfoData = taosArrayGet(p->pDataBlock, 0);
colDataAppend(pColInfoData, numOfRows, n, false);
// database name
pColInfoData = taosArrayGet(p->pDataBlock, 1);
colDataAppend(pColInfoData, numOfRows, dbname, false);
// vgId
pColInfoData = taosArrayGet(p->pDataBlock, 6);
colDataAppend(pColInfoData, numOfRows, (char*)&vgId, false);
int32_t tableType = pInfo->pCur->mr.me.type;
if (tableType == TSDB_CHILD_TABLE) {
// create time
int64_t ts = pInfo->pCur->mr.me.ctbEntry.ctime;
pColInfoData = taosArrayGet(p->pDataBlock, 2);
colDataAppend(pColInfoData, numOfRows, (char*)&ts, false);
SMetaReader mr = {0};
metaReaderInit(&mr, pInfo->readHandle.meta, 0);
uint64_t suid = pInfo->pCur->mr.me.ctbEntry.suid;
int32_t code = metaGetTableEntryByUid(&mr, suid);
if (code != TSDB_CODE_SUCCESS) {
qError("failed to get super table meta, uid:0x%" PRIx64 ", code:%s, %s", suid, tstrerror(terrno),
GET_TASKID(pTaskInfo));
metaReaderClear(&mr);
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
longjmp(pTaskInfo->env, terrno);
}
// number of columns
pColInfoData = taosArrayGet(p->pDataBlock, 3);
colDataAppend(pColInfoData, numOfRows, (char*)&mr.me.stbEntry.schemaRow.nCols, false);
// super table name
STR_TO_VARSTR(n, mr.me.name);
pColInfoData = taosArrayGet(p->pDataBlock, 4);
colDataAppend(pColInfoData, numOfRows, n, false);
metaReaderClear(&mr);
// table comment
pColInfoData = taosArrayGet(p->pDataBlock, 8);
if (pInfo->pCur->mr.me.ctbEntry.commentLen > 0) {
char comment[TSDB_TB_COMMENT_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, pInfo->pCur->mr.me.ctbEntry.comment);
colDataAppend(pColInfoData, numOfRows, comment, false);
} else if (pInfo->pCur->mr.me.ctbEntry.commentLen == 0) {
char comment[VARSTR_HEADER_SIZE + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, "");
colDataAppend(pColInfoData, numOfRows, comment, false);
} else {
colDataAppendNULL(pColInfoData, numOfRows);
}
// uid
pColInfoData = taosArrayGet(p->pDataBlock, 5);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.uid, false);
// ttl
pColInfoData = taosArrayGet(p->pDataBlock, 7);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ctbEntry.ttlDays, false);
STR_TO_VARSTR(n, "CHILD_TABLE");
} else if (tableType == TSDB_NORMAL_TABLE) {
// create time
pColInfoData = taosArrayGet(p->pDataBlock, 2);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.ctime, false);
// number of columns
pColInfoData = taosArrayGet(p->pDataBlock, 3);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.schemaRow.nCols, false);
// super table name
pColInfoData = taosArrayGet(p->pDataBlock, 4);
colDataAppendNULL(pColInfoData, numOfRows);
// table comment
pColInfoData = taosArrayGet(p->pDataBlock, 8);
if (pInfo->pCur->mr.me.ntbEntry.commentLen > 0) {
char comment[TSDB_TB_COMMENT_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, pInfo->pCur->mr.me.ntbEntry.comment);
colDataAppend(pColInfoData, numOfRows, comment, false);
} else if (pInfo->pCur->mr.me.ntbEntry.commentLen == 0) {
char comment[VARSTR_HEADER_SIZE + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, "");
colDataAppend(pColInfoData, numOfRows, comment, false);
} else {
colDataAppendNULL(pColInfoData, numOfRows);
}
// uid
pColInfoData = taosArrayGet(p->pDataBlock, 5);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.uid, false);
// ttl
pColInfoData = taosArrayGet(p->pDataBlock, 7);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.ttlDays, false);
STR_TO_VARSTR(n, "NORMAL_TABLE");
}
pColInfoData = taosArrayGet(p->pDataBlock, 9);
colDataAppend(pColInfoData, numOfRows, n, false);
if (++numOfRows >= pOperator->resultInfo.capacity) {
break;
}
}
// todo temporarily free the cursor here, the true reason why the free is not valid needs to be found
if (ret != 0) {
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
doSetOperatorCompleted(pOperator);
}
p->info.rows = numOfRows;
pInfo->pRes->info.rows = numOfRows;
relocateColumnData(pInfo->pRes, pInfo->scanCols, p->pDataBlock, false);
doFilterResult(pInfo);
blockDataDestroy(p);
pInfo->loadInfo.totalRows += pInfo->pRes->info.rows;
return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
}
}
static SSDataBlock* doSysTableScan(SOperatorInfo* pOperator) {
// build message and send to mnode to fetch the content of system tables.
SExecTaskInfo* pTaskInfo = pOperator->pTaskInfo;
SSysTableScanInfo* pInfo = pOperator->info;
// retrieve local table list info from vnode
const char* name = tNameGetTableName(&pInfo->name);
if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0) {
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
}
// the retrieve is executed on the mnode, so return tables that belongs to the information schema database.
if (pInfo->readHandle.mnd != NULL) {
buildSysDbTableInfo(pInfo, pOperator->resultInfo.capacity);
doFilterResult(pInfo);
pInfo->loadInfo.totalRows += pInfo->pRes->info.rows;
doSetOperatorCompleted(pOperator);
return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
} else {
if (pInfo->pCur == NULL) {
pInfo->pCur = metaOpenTbCursor(pInfo->readHandle.meta);
}
blockDataCleanup(pInfo->pRes);
int32_t numOfRows = 0;
const char* db = NULL;
int32_t vgId = 0;
vnodeGetInfo(pInfo->readHandle.vnode, &db, &vgId);
SName sn = {0};
char dbname[TSDB_DB_FNAME_LEN + VARSTR_HEADER_SIZE] = {0};
tNameFromString(&sn, db, T_NAME_ACCT | T_NAME_DB);
tNameGetDbName(&sn, varDataVal(dbname));
varDataSetLen(dbname, strlen(varDataVal(dbname)));
SSDataBlock* p = buildSysTableMetaBlock();
blockDataEnsureCapacity(p, pOperator->resultInfo.capacity);
char n[TSDB_TABLE_NAME_LEN + VARSTR_HEADER_SIZE] = {0};
int32_t ret = 0;
while ((ret = metaTbCursorNext(pInfo->pCur)) == 0) {
STR_TO_VARSTR(n, pInfo->pCur->mr.me.name);
// table name
SColumnInfoData* pColInfoData = taosArrayGet(p->pDataBlock, 0);
colDataAppend(pColInfoData, numOfRows, n, false);
// database name
pColInfoData = taosArrayGet(p->pDataBlock, 1);
colDataAppend(pColInfoData, numOfRows, dbname, false);
// vgId
pColInfoData = taosArrayGet(p->pDataBlock, 6);
colDataAppend(pColInfoData, numOfRows, (char*)&vgId, false);
int32_t tableType = pInfo->pCur->mr.me.type;
if (tableType == TSDB_CHILD_TABLE) {
// create time
int64_t ts = pInfo->pCur->mr.me.ctbEntry.ctime;
pColInfoData = taosArrayGet(p->pDataBlock, 2);
colDataAppend(pColInfoData, numOfRows, (char*)&ts, false);
SMetaReader mr = {0};
metaReaderInit(&mr, pInfo->readHandle.meta, 0);
uint64_t suid = pInfo->pCur->mr.me.ctbEntry.suid;
int32_t code = metaGetTableEntryByUid(&mr, suid);
if (code != TSDB_CODE_SUCCESS) {
qError("failed to get super table meta, uid:0x%" PRIx64 ", code:%s, %s", suid, tstrerror(terrno),
GET_TASKID(pTaskInfo));
metaReaderClear(&mr);
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
longjmp(pTaskInfo->env, terrno);
}
// number of columns
pColInfoData = taosArrayGet(p->pDataBlock, 3);
colDataAppend(pColInfoData, numOfRows, (char*)&mr.me.stbEntry.schemaRow.nCols, false);
// super table name
STR_TO_VARSTR(n, mr.me.name);
pColInfoData = taosArrayGet(p->pDataBlock, 4);
colDataAppend(pColInfoData, numOfRows, n, false);
metaReaderClear(&mr);
// table comment
pColInfoData = taosArrayGet(p->pDataBlock, 8);
if (pInfo->pCur->mr.me.ctbEntry.commentLen > 0) {
char comment[TSDB_TB_COMMENT_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, pInfo->pCur->mr.me.ctbEntry.comment);
colDataAppend(pColInfoData, numOfRows, comment, false);
} else if (pInfo->pCur->mr.me.ctbEntry.commentLen == 0) {
char comment[VARSTR_HEADER_SIZE + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, "");
colDataAppend(pColInfoData, numOfRows, comment, false);
} else {
colDataAppendNULL(pColInfoData, numOfRows);
}
// uid
pColInfoData = taosArrayGet(p->pDataBlock, 5);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.uid, false);
// ttl
pColInfoData = taosArrayGet(p->pDataBlock, 7);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ctbEntry.ttlDays, false);
STR_TO_VARSTR(n, "CHILD_TABLE");
} else if (tableType == TSDB_NORMAL_TABLE) {
// create time
pColInfoData = taosArrayGet(p->pDataBlock, 2);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.ctime, false);
// number of columns
pColInfoData = taosArrayGet(p->pDataBlock, 3);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.schemaRow.nCols, false);
// super table name
pColInfoData = taosArrayGet(p->pDataBlock, 4);
colDataAppendNULL(pColInfoData, numOfRows);
// table comment
pColInfoData = taosArrayGet(p->pDataBlock, 8);
if (pInfo->pCur->mr.me.ntbEntry.commentLen > 0) {
char comment[TSDB_TB_COMMENT_LEN + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, pInfo->pCur->mr.me.ntbEntry.comment);
colDataAppend(pColInfoData, numOfRows, comment, false);
} else if (pInfo->pCur->mr.me.ntbEntry.commentLen == 0) {
char comment[VARSTR_HEADER_SIZE + VARSTR_HEADER_SIZE] = {0};
STR_TO_VARSTR(comment, "");
colDataAppend(pColInfoData, numOfRows, comment, false);
} else {
colDataAppendNULL(pColInfoData, numOfRows);
}
// uid
pColInfoData = taosArrayGet(p->pDataBlock, 5);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.uid, false);
// ttl
pColInfoData = taosArrayGet(p->pDataBlock, 7);
colDataAppend(pColInfoData, numOfRows, (char*)&pInfo->pCur->mr.me.ntbEntry.ttlDays, false);
STR_TO_VARSTR(n, "NORMAL_TABLE");
}
pColInfoData = taosArrayGet(p->pDataBlock, 9);
colDataAppend(pColInfoData, numOfRows, n, false);
if (++numOfRows >= pOperator->resultInfo.capacity) {
break;
}
}
// todo temporarily free the cursor here, the true reason why the free is not valid needs to be found
if (ret != 0) {
metaCloseTbCursor(pInfo->pCur);
pInfo->pCur = NULL;
doSetOperatorCompleted(pOperator);
}
p->info.rows = numOfRows;
pInfo->pRes->info.rows = numOfRows;
relocateColumnData(pInfo->pRes, pInfo->scanCols, p->pDataBlock, false);
doFilterResult(pInfo);
blockDataDestroy(p);
pInfo->loadInfo.totalRows += pInfo->pRes->info.rows;
return (pInfo->pRes->info.rows == 0) ? NULL : pInfo->pRes;
}
return sysTableScanUserTables(pOperator);
} else if (strncasecmp(name, TSDB_INS_TABLE_USER_TAGS, TSDB_TABLE_FNAME_LEN) == 0) {
return sysTableScanUserTags(pOperator);
} else { // load the meta from mnode of the given epset
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
@ -2058,7 +2293,7 @@ static SSDataBlock* doSysTableScan(SOperatorInfo* pOperator) {
}
int32_t buildSysDbTableInfo(const SSysTableScanInfo* pInfo, int32_t capacity) {
SSDataBlock* p = buildSysTableMetaBlock();
SSDataBlock* p = buildInfoSchemaTableMetaBlock(TSDB_INS_TABLE_USER_TABLES);
blockDataEnsureCapacity(p, capacity);
size_t size = 0;
@ -2147,7 +2382,8 @@ SOperatorInfo* createSysTableScanOperatorInfo(void* readHandle, SSystemTableScan
tNameAssign(&pInfo->name, &pScanNode->tableName);
const char* name = tNameGetTableName(&pInfo->name);
if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0) {
if (strncasecmp(name, TSDB_INS_TABLE_USER_TABLES, TSDB_TABLE_FNAME_LEN) == 0 ||
strncasecmp(name, TSDB_INS_TABLE_USER_TAGS, TSDB_TABLE_FNAME_LEN) == 0) {
pInfo->readHandle = *(SReadHandle*)readHandle;
blockDataEnsureCapacity(pInfo->pRes, pOperator->resultInfo.capacity);
} else {
@ -2941,4 +3177,3 @@ _error:
taosMemoryFree(pOperator);
return NULL;
}

6
source/libs/executor/src/sortoperator.c
View File

@ -234,9 +234,9 @@ void destroyOrderOperatorInfo(void* param, int32_t numOfOutput) {
SSortOperatorInfo* pInfo = (SSortOperatorInfo*)param;
pInfo->binfo.pRes = blockDataDestroy(pInfo->binfo.pRes);
tsortDestroySortHandle(pInfo->pSortHandle);
taosArrayDestroy(pInfo->pSortInfo);
taosArrayDestroy(pInfo->pColMatchInfo);
taosMemoryFreeClear(param);
}
@ -539,14 +539,12 @@ int32_t doOpenMultiwayMergeOperator(SOperatorInfo* pOperator) {
}
pInfo->startTs = taosGetTimestampUs();
int32_t numOfBufPage = pInfo->sortBufSize / pInfo->bufPageSize;
pInfo->pSortHandle = tsortCreateSortHandle(pInfo->pSortInfo, SORT_MULTISOURCE_MERGE, pInfo->bufPageSize, numOfBufPage,
pInfo->pInputBlock, pTaskInfo->id.str);
tsortSetFetchRawDataFp(pInfo->pSortHandle, loadNextDataBlock, NULL, NULL);
tsortSetCompareGroupId(pInfo->pSortHandle, pInfo->groupSort);
for (int32_t i = 0; i < pOperator->numOfDownstream; ++i) {
@ -556,7 +554,6 @@ int32_t doOpenMultiwayMergeOperator(SOperatorInfo* pOperator) {
}
int32_t code = tsortOpen(pInfo->pSortHandle);
if (code != TSDB_CODE_SUCCESS) {
longjmp(pTaskInfo->env, terrno);
}
@ -674,6 +671,7 @@ void destroyMultiwayMergeOperatorInfo(void* param, int32_t numOfOutput) {
pInfo->binfo.pRes = blockDataDestroy(pInfo->binfo.pRes);
pInfo->pInputBlock = blockDataDestroy(pInfo->pInputBlock);
tsortDestroySortHandle(pInfo->pSortHandle);
taosArrayDestroy(pInfo->pSortInfo);
taosArrayDestroy(pInfo->pColMatchInfo);

52
source/libs/executor/src/timewindowoperator.c
View File

@ -1353,13 +1353,13 @@ static int32_t closeIntervalWindow(SHashObj* pHashMap, STimeWindowAggSupp* pSup,
if (chIds && pPullDataMap) {
SArray* chAy = *(SArray**)chIds;
int32_t size = taosArrayGetSize(chAy);
qDebug("window %" PRId64 " wait child size:%d", win.skey, size);
qDebug("===stream===window %" PRId64 " wait child size:%d", win.skey, size);
for (int32_t i = 0; i < size; i++) {
qDebug("window %" PRId64 " wait child id:%d", win.skey, *(int32_t*)taosArrayGet(chAy, i));
qDebug("===stream===window %" PRId64 " wait child id:%d", win.skey, *(int32_t*)taosArrayGet(chAy, i));
}
continue;
} else if (pPullDataMap) {
qDebug("close window %" PRId64, win.skey);
qDebug("===stream===close window %" PRId64, win.skey);
}
SResultRowPosition* pPos = (SResultRowPosition*)pIte;
if (pSup->calTrigger == STREAM_TRIGGER_WINDOW_CLOSE) {
@ -2482,7 +2482,9 @@ static void doHashInterval(SOperatorInfo* pOperatorInfo, SSDataBlock* pSDataBloc
SPullWindowInfo pull = {.window = nextWin, .groupId = tableGroupId};
// add pull data request
taosArrayPush(pInfo->pPullWins, &pull);
addPullWindow(pInfo->pPullDataMap, &winRes, taosArrayGetSize(pInfo->pChildren));
int32_t size = taosArrayGetSize(pInfo->pChildren);
addPullWindow(pInfo->pPullDataMap, &winRes, size);
qDebug("===stream===prepare retrive %" PRId64 ", size:%d", winRes.ts, size);
} else {
int32_t index = -1;
SArray* chArray = NULL;
@ -2492,14 +2494,14 @@ static void doHashInterval(SOperatorInfo* pOperatorInfo, SSDataBlock* pSDataBloc
chId = getChildIndex(pSDataBlock);
index = taosArraySearchIdx(chArray, &chId, compareInt32Val, TD_EQ);
}
if (index != -1 && pSDataBlock->info.type == STREAM_PULL_DATA) {
qDebug("======delete child id %d", chId);
taosArrayRemove(chArray, index);
if (taosArrayGetSize(chArray) == 0) {
// pull data is over
taosHashRemove(pInfo->pPullDataMap, &winRes, sizeof(SWinRes));
}
}
// if (index != -1 && pSDataBlock->info.type == STREAM_PULL_DATA) {
// qDebug("===stream===delete child id %d", chId);
// taosArrayRemove(chArray, index);
// if (taosArrayGetSize(chArray) == 0) {
// // pull data is over
// taosHashRemove(pInfo->pPullDataMap, &winRes, sizeof(SWinRes));
// }
// }
if (index == -1 || pSDataBlock->info.type == STREAM_PULL_DATA) {
ignore = false;
}
@ -2623,6 +2625,7 @@ void processPullOver(SSDataBlock* pBlock, SHashObj* pMap) {
SArray* chArray = *(SArray**)chIds;
int32_t index = taosArraySearchIdx(chArray, &chId, compareInt32Val, TD_EQ);
if (index != -1) {
qDebug("===stream===window %" PRId64 " delete child id %d", winRes.ts, chId);
taosArrayRemove(chArray, index);
if (taosArrayGetSize(chArray) == 0) {
// pull data is over
@ -2641,7 +2644,7 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
SExprSupp* pSup = &pOperator->exprSupp;
qDebug("interval status %d %s", pOperator->status, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
qDebug("interval status %d %s", pOperator->status, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
if (pOperator->status == OP_EXEC_DONE) {
return NULL;
@ -2657,18 +2660,18 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
}
return NULL;
}
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->binfo.pRes;
} else {
doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
if (pInfo->binfo.pRes->info.rows != 0) {
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->binfo.pRes;
}
if (pInfo->pUpdateRes->info.rows != 0 && pInfo->returnUpdate) {
pInfo->returnUpdate = false;
ASSERT(!IS_FINAL_OP(pInfo));
printDataBlock(pInfo->pUpdateRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pUpdateRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
// process the rest of the data
return pInfo->pUpdateRes;
}
@ -2676,13 +2679,13 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
if (pInfo->pPullDataRes->info.rows != 0) {
// process the rest of the data
ASSERT(IS_FINAL_OP(pInfo));
printDataBlock(pInfo->pPullDataRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pPullDataRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->pPullDataRes;
}
doBuildDeleteResult(pInfo->pDelWins, &pInfo->delIndex, pInfo->pDelRes);
if (pInfo->pDelRes->info.rows != 0) {
// process the rest of the data
printDataBlock(pInfo->pDelRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pDelRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->pDelRes;
}
}
@ -2693,10 +2696,10 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
clearSpecialDataBlock(pInfo->pUpdateRes);
removeDeleteResults(pUpdated, pInfo->pDelWins);
pOperator->status = OP_RES_TO_RETURN;
qDebug("%s return data", IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
qDebug("%s return data", IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
break;
}
printDataBlock(pBlock, IS_FINAL_OP(pInfo) ? "interval Final recv" : "interval Semi recv");
printDataBlock(pBlock, IS_FINAL_OP(pInfo) ? "interval Final recv" : "interval Semi recv");
maxTs = TMAX(maxTs, pBlock->info.window.ekey);
if (pBlock->info.type == STREAM_NORMAL || pBlock->info.type == STREAM_PULL_DATA ||
@ -2771,6 +2774,7 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
SStreamFinalIntervalOperatorInfo* pTmpInfo = pChildOp->info;
pTmpInfo->twAggSup.calTrigger = STREAM_TRIGGER_AT_ONCE;
taosArrayPush(pInfo->pChildren, &pChildOp);
qDebug("===stream===add child, id:%d", chIndex);
}
SOperatorInfo* pChildOp = taosArrayGetP(pInfo->pChildren, chIndex);
SStreamFinalIntervalOperatorInfo* pChInfo = pChildOp->info;
@ -2795,14 +2799,14 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
blockDataEnsureCapacity(pInfo->binfo.pRes, pOperator->resultInfo.capacity);
doBuildResultDatablock(pOperator, &pInfo->binfo, &pInfo->groupResInfo, pInfo->aggSup.pResultBuf);
if (pInfo->binfo.pRes->info.rows != 0) {
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->binfo.pRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->binfo.pRes;
}
if (pInfo->pUpdateRes->info.rows != 0 && pInfo->returnUpdate) {
pInfo->returnUpdate = false;
ASSERT(!IS_FINAL_OP(pInfo));
printDataBlock(pInfo->pUpdateRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pUpdateRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
// process the rest of the data
return pInfo->pUpdateRes;
}
@ -2811,14 +2815,14 @@ static SSDataBlock* doStreamFinalIntervalAgg(SOperatorInfo* pOperator) {
if (pInfo->pPullDataRes->info.rows != 0) {
// process the rest of the data
ASSERT(IS_FINAL_OP(pInfo));
printDataBlock(pInfo->pPullDataRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pPullDataRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->pPullDataRes;
}
doBuildDeleteResult(pInfo->pDelWins, &pInfo->delIndex, pInfo->pDelRes);
if (pInfo->pDelRes->info.rows != 0) {
// process the rest of the data
printDataBlock(pInfo->pDelRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
printDataBlock(pInfo->pDelRes, IS_FINAL_OP(pInfo) ? "interval Final" : "interval Semi");
return pInfo->pDelRes;
}
// ASSERT(false);

5
source/libs/executor/src/tsort.c
View File

@ -109,6 +109,10 @@ static int32_t sortComparClearup(SMsortComparParam* cmpParam) {
}
void tsortDestroySortHandle(SSortHandle* pSortHandle) {
if (pSortHandle == NULL) {
return;
}
tsortClose(pSortHandle);
if (pSortHandle->pMergeTree != NULL) {
tMergeTreeDestroy(pSortHandle->pMergeTree);
@ -119,7 +123,6 @@ void tsortDestroySortHandle(SSortHandle* pSortHandle) {
blockDataDestroy(pSortHandle->pDataBlock);
for (size_t i = 0; i < taosArrayGetSize(pSortHandle->pOrderedSource); i++){
SSortSource** pSource = taosArrayGet(pSortHandle->pOrderedSource, i);
blockDataDestroy((*pSource)->src.pBlock);
taosMemoryFreeClear(*pSource);
}
taosArrayDestroy(pSortHandle->pOrderedSource);

32
source/libs/nodes/src/nodesUtilFuncs.c
View File

@ -1543,7 +1543,7 @@ typedef struct SCollectFuncsCxt {
int32_t errCode;
FFuncClassifier classifier;
SNodeList* pFuncs;
SHashObj* pAliasName;
SHashObj* pFuncsSet;
} SCollectFuncsCxt;
static EDealRes collectFuncs(SNode* pNode, void* pContext) {
@ -1551,28 +1551,40 @@ static EDealRes collectFuncs(SNode* pNode, void* pContext) {
if (QUERY_NODE_FUNCTION == nodeType(pNode) && pCxt->classifier(((SFunctionNode*)pNode)->funcId) &&
!(((SExprNode*)pNode)->orderAlias)) {
SExprNode* pExpr = (SExprNode*)pNode;
if (NULL == taosHashGet(pCxt->pAliasName, pExpr->aliasName, strlen(pExpr->aliasName))) {
if (NULL == taosHashGet(pCxt->pFuncsSet, &pExpr, POINTER_BYTES)) {
pCxt->errCode = nodesListStrictAppend(pCxt->pFuncs, nodesCloneNode(pNode));
taosHashPut(pCxt->pAliasName, pExpr->aliasName, strlen(pExpr->aliasName), &pExpr, POINTER_BYTES);
taosHashPut(pCxt->pFuncsSet, &pExpr, POINTER_BYTES, &pExpr, POINTER_BYTES);
}
return (TSDB_CODE_SUCCESS == pCxt->errCode ? DEAL_RES_IGNORE_CHILD : DEAL_RES_ERROR);
}
return DEAL_RES_CONTINUE;
}
static uint32_t funcNodeHash(const char* pKey, uint32_t len) {
SExprNode* pExpr = *(SExprNode**)pKey;
return MurmurHash3_32(pExpr->aliasName, strlen(pExpr->aliasName));
}
static int32_t funcNodeEqual(const void* pLeft, const void* pRight, size_t len) {
if (0 != strcmp((*(const SExprNode**)pLeft)->aliasName, (*(const SExprNode**)pRight)->aliasName)) {
return 1;
}
return nodesEqualNode(*(const SNode**)pLeft, *(const SNode**)pRight) ? 0 : 1;
}
int32_t nodesCollectFuncs(SSelectStmt* pSelect, ESqlClause clause, FFuncClassifier classifier, SNodeList** pFuncs) {
if (NULL == pSelect || NULL == pFuncs) {
return TSDB_CODE_FAILED;
}
SCollectFuncsCxt cxt = {
.errCode = TSDB_CODE_SUCCESS,
.classifier = classifier,
.pFuncs = (NULL == *pFuncs ? nodesMakeList() : *pFuncs),
.pAliasName = taosHashInit(4, taosGetDefaultHashFunction(TSDB_DATA_TYPE_VARCHAR), false, false)};
if (NULL == cxt.pFuncs) {
SCollectFuncsCxt cxt = {.errCode = TSDB_CODE_SUCCESS,
.classifier = classifier,
.pFuncs = (NULL == *pFuncs ? nodesMakeList() : *pFuncs),
.pFuncsSet = taosHashInit(4, funcNodeHash, false, false)};
if (NULL == cxt.pFuncs || NULL == cxt.pFuncsSet) {
return TSDB_CODE_OUT_OF_MEMORY;
}
taosHashSetEqualFp(cxt.pFuncsSet, funcNodeEqual);
*pFuncs = NULL;
nodesWalkSelectStmt(pSelect, clause, collectFuncs, &cxt);
if (TSDB_CODE_SUCCESS == cxt.errCode) {
@ -1584,7 +1596,7 @@ int32_t nodesCollectFuncs(SSelectStmt* pSelect, ESqlClause clause, FFuncClassifi
} else {
nodesDestroyList(cxt.pFuncs);
}
taosHashCleanup(cxt.pAliasName);
taosHashCleanup(cxt.pFuncsSet);
return cxt.errCode;
}

15
source/libs/parser/src/parAstParser.c
View File

@ -371,6 +371,19 @@ static int32_t collectMetaKeyFromShowTables(SCollectMetaKeyCxt* pCxt, SShowStmt*
return code;
}
static int32_t collectMetaKeyFromShowTags(SCollectMetaKeyCxt* pCxt, SShowStmt* pStmt) {
int32_t code = reserveTableMetaInCache(pCxt->pParseCxt->acctId, TSDB_INFORMATION_SCHEMA_DB,
TSDB_INS_TABLE_USER_TAGS, pCxt->pMetaCache);
if (TSDB_CODE_SUCCESS == code) {
if (NULL != pStmt->pDbName) {
code = reserveDbVgInfoInCache(pCxt->pParseCxt->acctId, ((SValueNode*)pStmt->pDbName)->literal, pCxt->pMetaCache);
} else {
code = reserveDbVgInfoInCache(pCxt->pParseCxt->acctId, TSDB_INFORMATION_SCHEMA_DB, pCxt->pMetaCache);
}
}
return code;
}
static int32_t collectMetaKeyFromShowUsers(SCollectMetaKeyCxt* pCxt, SShowStmt* pStmt) {
return reserveTableMetaInCache(pCxt->pParseCxt->acctId, TSDB_INFORMATION_SCHEMA_DB, TSDB_INS_TABLE_USER_USERS,
pCxt->pMetaCache);
@ -537,6 +550,8 @@ static int32_t collectMetaKeyFromQuery(SCollectMetaKeyCxt* pCxt, SNode* pStmt) {
return collectMetaKeyFromShowStreams(pCxt, (SShowStmt*)pStmt);
case QUERY_NODE_SHOW_TABLES_STMT:
return collectMetaKeyFromShowTables(pCxt, (SShowStmt*)pStmt);
case QUERY_NODE_SHOW_TAGS_STMT:
return collectMetaKeyFromShowTags(pCxt, (SShowStmt*)pStmt);
case QUERY_NODE_SHOW_USERS_STMT:
return collectMetaKeyFromShowUsers(pCxt, (SShowStmt*)pStmt);
case QUERY_NODE_SHOW_LICENCE_STMT:

18
source/libs/parser/src/parTranslater.c
View File

@ -868,7 +868,8 @@ static EDealRes translateNormalValue(STranslateContext* pCxt, SValueNode* pVal,
}
case TSDB_DATA_TYPE_VARCHAR:
case TSDB_DATA_TYPE_VARBINARY: {
if (strict && (pVal->node.resType.bytes > targetDt.bytes - VARSTR_HEADER_SIZE)) {
if (strict && (!IS_VAR_DATA_TYPE(pVal->node.resType.type) ||
pVal->node.resType.bytes > targetDt.bytes - VARSTR_HEADER_SIZE)) {
return generateDealNodeErrMsg(pCxt, TSDB_CODE_PAR_WRONG_VALUE_TYPE, pVal->literal);
}
pVal->datum.p = taosMemoryCalloc(1, targetDt.bytes + 1);
@ -888,6 +889,9 @@ static EDealRes translateNormalValue(STranslateContext* pCxt, SValueNode* pVal,
break;
}
case TSDB_DATA_TYPE_NCHAR: {
if (strict && !IS_VAR_DATA_TYPE(pVal->node.resType.type)) {
return generateDealNodeErrMsg(pCxt, TSDB_CODE_PAR_WRONG_VALUE_TYPE, pVal->literal);
}
pVal->datum.p = taosMemoryCalloc(1, targetDt.bytes + 1);
if (NULL == pVal->datum.p) {
return generateDealNodeErrMsg(pCxt, TSDB_CODE_OUT_OF_MEMORY);
@ -1168,7 +1172,7 @@ static int32_t translateRepeatScanFunc(STranslateContext* pCxt, SFunctionNode* p
return TSDB_CODE_SUCCESS;
}
if (isSelectStmt(pCxt->pCurrStmt)) {
//select percentile() without from clause is also valid
// select percentile() without from clause is also valid
if (NULL == ((SSelectStmt*)pCxt->pCurrStmt)->pFromTable) {
return TSDB_CODE_SUCCESS;
}
@ -1681,7 +1685,8 @@ static int32_t dnodeToVgroupsInfo(SArray* pDnodes, SVgroupsInfo** pVgsInfo) {
static bool sysTableFromVnode(const char* pTable) {
return (0 == strcmp(pTable, TSDB_INS_TABLE_USER_TABLES)) ||
(0 == strcmp(pTable, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED));
(0 == strcmp(pTable, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED) ||
(0 == strcmp(pTable, TSDB_INS_TABLE_USER_TAGS)));
}
static bool sysTableFromDnode(const char* pTable) { return 0 == strcmp(pTable, TSDB_INS_TABLE_DNODE_VARIABLES); }
@ -1697,7 +1702,7 @@ static int32_t setVnodeSysTableVgroupList(STranslateContext* pCxt, SName* pName,
code = getDBVgInfoImpl(pCxt, pName, &vgroupList);
}
if (TSDB_CODE_SUCCESS == code) {
if (TSDB_CODE_SUCCESS == code && 0 == strcmp(pRealTable->table.tableName, TSDB_INS_TABLE_USER_TABLES)) {
code = addMnodeToVgroupList(&pCxt->pParseCxt->mgmtEpSet, &vgroupList);
}
@ -1786,7 +1791,8 @@ static bool isSingleTable(SRealTableNode* pRealTable) {
int8_t tableType = pRealTable->pMeta->tableType;
if (TSDB_SYSTEM_TABLE == tableType) {
return 0 != strcmp(pRealTable->table.tableName, TSDB_INS_TABLE_USER_TABLES) &&
0 != strcmp(pRealTable->table.tableName, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED);
0 != strcmp(pRealTable->table.tableName, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED) &&
0 != strcmp(pRealTable->table.tableName, TSDB_INS_TABLE_USER_TAGS);
}
return (TSDB_CHILD_TABLE == tableType || TSDB_NORMAL_TABLE == tableType);
}
@ -5059,6 +5065,8 @@ static const char* getSysTableName(ENodeType type) {
return TSDB_INS_TABLE_USER_DATABASES;
case QUERY_NODE_SHOW_TABLES_STMT:
return TSDB_INS_TABLE_USER_TABLES;
case QUERY_NODE_SHOW_TAGS_STMT:
return TSDB_INS_TABLE_USER_TAGS;
case QUERY_NODE_SHOW_STABLES_STMT:
return TSDB_INS_TABLE_USER_STABLES;
case QUERY_NODE_SHOW_USERS_STMT:

2
source/libs/planner/src/planLogicCreater.c
View File

@ -282,7 +282,7 @@ static int32_t createScanLogicNode(SLogicPlanContext* pCxt, SSelectStmt* pSelect
pScan->hasNormalCols = true;
}
if (TSDB_CODE_SUCCESS == code) {
if (TSDB_CODE_SUCCESS == code && SCAN_TYPE_SYSTEM_TABLE != pScan->scanType) {
code = addPrimaryKeyCol(pScan->tableId, &pScan->pScanCols);
}

21
source/libs/planner/src/planOptimizer.c
View File

@ -1050,8 +1050,11 @@ static int32_t sortPriKeyOptApply(SOptimizeContext* pCxt, SLogicSubplan* pLogicS
}
}
int32_t code =
replaceLogicNode(pLogicSubplan, (SLogicNode*)pSort, (SLogicNode*)nodesListGetNode(pSort->node.pChildren, 0));
SLogicNode* pChild = (SLogicNode*)nodesListGetNode(pSort->node.pChildren, 0);
if (NULL == pSort->node.pParent) {
TSWAP(pSort->node.pTargets, pChild->pTargets);
}
int32_t code = replaceLogicNode(pLogicSubplan, (SLogicNode*)pSort, pChild);
if (TSDB_CODE_SUCCESS == code) {
NODES_CLEAR_LIST(pSort->node.pChildren);
nodesDestroyNode((SNode*)pSort);
@ -1982,11 +1985,15 @@ static int32_t rewriteUniqueOptimize(SOptimizeContext* pCxt, SLogicSubplan* pLog
}
static bool lastRowScanOptMayBeOptimized(SLogicNode* pNode) {
if (QUERY_NODE_LOGIC_PLAN_AGG != nodeType(pNode) || !(((SAggLogicNode*)pNode)->hasLastRow) ||
NULL != ((SAggLogicNode*)pNode)->pGroupKeys || 1 != LIST_LENGTH(pNode->pChildren) ||
QUERY_NODE_LOGIC_PLAN_SCAN != nodeType(nodesListGetNode(pNode->pChildren, 0)) ||
NULL != ((SScanLogicNode*)nodesListGetNode(pNode->pChildren, 0))->node.pConditions ||
0 == ((SScanLogicNode*)nodesListGetNode(pNode->pChildren, 0))->cacheLastMode) {
if (QUERY_NODE_LOGIC_PLAN_AGG != nodeType(pNode) || 1 != LIST_LENGTH(pNode->pChildren) ||
QUERY_NODE_LOGIC_PLAN_SCAN != nodeType(nodesListGetNode(pNode->pChildren, 0))) {
return false;
}
SAggLogicNode* pAgg = (SAggLogicNode*)pNode;
SScanLogicNode* pScan = (SScanLogicNode*)nodesListGetNode(pNode->pChildren, 0);
if (!pAgg->hasLastRow || NULL != pAgg->pGroupKeys || NULL != pScan->node.pConditions || 0 == pScan->cacheLastMode ||
IS_TSWINDOW_SPECIFIED(pScan->scanRange)) {
return false;
}

3
source/libs/planner/src/planPhysiCreater.c
View File

@ -570,7 +570,8 @@ static int32_t createSystemTableScanPhysiNode(SPhysiPlanContext* pCxt, SSubplan*
pScan->showRewrite = pScanLogicNode->showRewrite;
pScan->accountId = pCxt->pPlanCxt->acctId;
if (0 == strcmp(pScanLogicNode->tableName.tname, TSDB_INS_TABLE_USER_TABLES) ||
0 == strcmp(pScanLogicNode->tableName.tname, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED)) {
0 == strcmp(pScanLogicNode->tableName.tname, TSDB_INS_TABLE_USER_TABLE_DISTRIBUTED) ||
0 == strcmp(pScanLogicNode->tableName.tname, TSDB_INS_TABLE_USER_TAGS)) {
vgroupInfoToNodeAddr(pScanLogicNode->pVgroupList->vgroups, &pSubplan->execNode);
} else {
pSubplan->execNode.nodeId = MNODE_HANDLE;

6
source/libs/planner/test/planJoinTest.cpp
View File

@ -45,6 +45,12 @@ TEST_F(PlanJoinTest, withWhere) {
"WHERE t1.c1 > t2.c1 AND t1.c2 = 'abc' AND t2.c2 = 'qwe'");
}
TEST_F(PlanJoinTest, withAggAndOrderBy) {
useDb("root", "test");
run("SELECT t1.ts, TOP(t2.c1, 10) FROM st1s1 t1 JOIN st1s2 t2 ON t1.ts = t2.ts ORDER BY t2.ts");
}
TEST_F(PlanJoinTest, multiJoin) {
useDb("root", "test");

6
source/libs/planner/test/planOptimizeTest.cpp
View File

@ -84,6 +84,12 @@ TEST_F(PlanOptimizeTest, eliminateProjection) {
// run("select 1-abs(c1) from (select unique(c1) c1 from st1s3) order by 1 nulls first");
}
TEST_F(PlanOptimizeTest, mergeProjects) {
useDb("root", "test");
run("SELECT * FROM (SELECT * FROM t1 WHERE c1 > 10 ORDER BY ts) ORDER BY ts");
}
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");

16
source/libs/qworker/inc/qwInt.h
View File

@ -75,7 +75,9 @@ typedef struct SQWDebug {
bool lockEnable;
bool statusEnable;
bool dumpEnable;
bool tmp;
bool sleepSimulate;
bool deadSimulate;
bool redirectSimulate;
} SQWDebug;
extern SQWDebug gQWDebug;
@ -130,12 +132,11 @@ typedef struct SQWTaskCtx {
int8_t taskType;
int8_t explain;
int8_t needFetch;
int32_t queryType;
int32_t msgType;
int32_t fetchType;
int32_t execId;
bool queryRsped;
bool queryFetched;
bool queryEnd;
bool queryContinue;
bool queryInQueue;
@ -228,6 +229,7 @@ typedef struct SQWorkerMgmt {
#define QW_SET_EVENT_PROCESSED(ctx, event) atomic_store_8(&(ctx)->events[event], QW_EVENT_PROCESSED)
#define QW_GET_PHASE(ctx) atomic_load_8(&(ctx)->phase)
#define QW_SET_PHASE(ctx, _value) do { if ((_value) != QW_PHASE_PRE_FETCH && (_value) != QW_PHASE_POST_FETCH) { atomic_store_8(&(ctx)->phase, _value); } } while (0)
#define QW_SET_RSP_CODE(ctx, code) atomic_store_32(&(ctx)->rspCode, code)
#define QW_UPDATE_RSP_CODE(ctx, code) atomic_val_compare_exchange_32(&(ctx)->rspCode, 0, code)
@ -362,7 +364,7 @@ int32_t qwAcquireTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx **ctx);
int32_t qwGetTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx **ctx);
int32_t qwAddAcquireTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx **ctx);
void qwReleaseTaskCtx(SQWorker *mgmt, void *ctx);
int32_t qwKillTaskHandle(QW_FPARAMS_DEF, SQWTaskCtx *ctx);
int32_t qwKillTaskHandle(SQWTaskCtx *ctx);
int32_t qwUpdateTaskStatus(QW_FPARAMS_DEF, int8_t status);
int32_t qwDropTask(QW_FPARAMS_DEF);
void qwSaveTbVersionInfo(qTaskInfo_t pTaskInfo, SQWTaskCtx *ctx);
@ -372,13 +374,15 @@ int32_t qwUpdateTimeInQueue(SQWorker *mgmt, int64_t ts, EQueueType type);
int64_t qwGetTimeInQueue(SQWorker *mgmt, EQueueType type);
void qwClearExpiredSch(SQWorker *mgmt, SArray* pExpiredSch);
int32_t qwAcquireScheduler(SQWorker *mgmt, uint64_t sId, int32_t rwType, SQWSchStatus **sch);
void qwFreeTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx *ctx);
void qwFreeTaskCtx(SQWTaskCtx *ctx);
void qwDbgDumpMgmtInfo(SQWorker *mgmt);
int32_t qwDbgValidateStatus(QW_FPARAMS_DEF, int8_t oriStatus, int8_t newStatus, bool *ignore);
int32_t qwDbgBuildAndSendRedirectRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, SEpSet *pEpSet);
int32_t qwAddTaskCtx(QW_FPARAMS_DEF);
int32_t qwDbgResponseRedirect(SQWMsg *qwMsg, SQWTaskCtx *ctx);
void qwDbgSimulateRedirect(SQWMsg *qwMsg, SQWTaskCtx *ctx, bool *rsped);
void qwDbgSimulateSleep(void);
void qwDbgSimulateDead(QW_FPARAMS_DEF, SQWTaskCtx *ctx, bool *rsped);
#ifdef __cplusplus

2
source/libs/qworker/inc/qwMsg.h
View File

@ -40,11 +40,13 @@ void qwBuildFetchRsp(void *msg, SOutputData *input, int32_t len, bool qComple
int32_t qwBuildAndSendCQueryMsg(QW_FPARAMS_DEF, SRpcHandleInfo *pConn);
int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, SQWTaskCtx *ctx);
int32_t qwBuildAndSendExplainRsp(SRpcHandleInfo *pConn, SExplainExecInfo *execInfo, int32_t num);
int32_t qwBuildAndSendErrorRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code);
void qwFreeFetchRsp(void *msg);
int32_t qwMallocFetchRsp(int32_t length, SRetrieveTableRsp **rsp);
int32_t qwBuildAndSendHbRsp(SRpcHandleInfo *pConn, SSchedulerHbRsp *rsp, int32_t code);
int32_t qwRegisterQueryBrokenLinkArg(QW_FPARAMS_DEF, SRpcHandleInfo *pConn);
int32_t qwRegisterHbBrokenLinkArg(SQWorker *mgmt, uint64_t sId, SRpcHandleInfo *pConn);
int32_t qwBuildAndSendDropMsg(QW_FPARAMS_DEF, SRpcHandleInfo *pConn);
#ifdef __cplusplus
}

89
source/libs/qworker/src/qwDbg.c
View File

@ -9,7 +9,7 @@
#include "tmsg.h"
#include "tname.h"
SQWDebug gQWDebug = {.statusEnable = true, .dumpEnable = false, .tmp = false};
SQWDebug gQWDebug = {.statusEnable = true, .dumpEnable = false, .redirectSimulate = false, .deadSimulate = false, .sleepSimulate = false};
int32_t qwDbgValidateStatus(QW_FPARAMS_DEF, int8_t oriStatus, int8_t newStatus, bool *ignore) {
if (!gQWDebug.statusEnable) {
@ -147,8 +147,17 @@ int32_t qwDbgBuildAndSendRedirectRsp(int32_t rspType, SRpcHandleInfo *pConn, int
return TSDB_CODE_SUCCESS;
}
int32_t qwDbgResponseRedirect(SQWMsg *qwMsg, SQWTaskCtx *ctx) {
if (gQWDebug.tmp) {
void qwDbgSimulateRedirect(SQWMsg *qwMsg, SQWTaskCtx *ctx, bool *rsped) {
static int32_t ignoreTime = 0;
if (*rsped) {
return;
}
if (gQWDebug.redirectSimulate) {
if (++ignoreTime <= 10) {
return;
}
if (TDMT_SCH_QUERY == qwMsg->msgType && (0 == taosRand() % 3)) {
SEpSet epSet = {0};
epSet.inUse = 1;
@ -162,42 +171,94 @@ int32_t qwDbgResponseRedirect(SQWMsg *qwMsg, SQWTaskCtx *ctx) {
ctx->phase = QW_PHASE_POST_QUERY;
qwDbgBuildAndSendRedirectRsp(qwMsg->msgType + 1, &qwMsg->connInfo, TSDB_CODE_RPC_REDIRECT, &epSet);
return TSDB_CODE_SUCCESS;
*rsped = true;
return;
}
if (TDMT_SCH_MERGE_QUERY == qwMsg->msgType && (0 == taosRand() % 3)) {
ctx->phase = QW_PHASE_POST_QUERY;
QW_SET_PHASE(ctx, QW_PHASE_POST_QUERY);
qwDbgBuildAndSendRedirectRsp(qwMsg->msgType + 1, &qwMsg->connInfo, TSDB_CODE_RPC_REDIRECT, NULL);
return TSDB_CODE_SUCCESS;
*rsped = true;
return;
}
if ((TDMT_SCH_FETCH == qwMsg->msgType) && (0 == taosRand() % 9)) {
qwDbgBuildAndSendRedirectRsp(qwMsg->msgType + 1, &qwMsg->connInfo, TSDB_CODE_RPC_REDIRECT, NULL);
*rsped = true;
return;
}
}
return TSDB_CODE_SUCCESS;
}
void qwDbgSimulateSleep(void) {
if (!gQWDebug.sleepSimulate) {
return;
}
static int32_t ignoreTime = 0;
if (++ignoreTime > 10) {
taosSsleep(taosRand() % 20);
}
}
void qwDbgSimulateDead(QW_FPARAMS_DEF, SQWTaskCtx *ctx, bool *rsped) {
if (!gQWDebug.deadSimulate) {
return;
}
if (*rsped) {
return;
}
static int32_t ignoreTime = 0;
if (++ignoreTime > 10 && 0 == taosRand() % 9) {
SRpcHandleInfo *pConn = ((ctx->msgType == TDMT_SCH_FETCH || ctx->msgType == TDMT_SCH_MERGE_FETCH) ? &ctx->dataConnInfo : &ctx->ctrlConnInfo);
qwBuildAndSendErrorRsp(ctx->msgType + 1, pConn, TSDB_CODE_RPC_BROKEN_LINK);
qwBuildAndSendDropMsg(QW_FPARAMS(), pConn);
*rsped = true;
return;
}
}
int32_t qwDbgEnableDebug(char *option) {
if (0 == strcasecmp(option, "lock")) {
gQWDebug.lockEnable = true;
qDebug("qw lock debug enabled");
qError("qw lock debug enabled");
return TSDB_CODE_SUCCESS;
}
if (0 == strcasecmp(option, "status")) {
gQWDebug.statusEnable = true;
qDebug("qw status debug enabled");
qError("qw status debug enabled");
return TSDB_CODE_SUCCESS;
}
if (0 == strcasecmp(option, "dump")) {
gQWDebug.dumpEnable = true;
qDebug("qw dump debug enabled");
qError("qw dump debug enabled");
return TSDB_CODE_SUCCESS;
}
if (0 == strcasecmp(option, "tmp")) {
gQWDebug.tmp = true;
qDebug("qw tmp debug enabled");
if (0 == strcasecmp(option, "sleep")) {
gQWDebug.sleepSimulate = true;
qError("qw sleep debug enabled");
return TSDB_CODE_SUCCESS;
}
if (0 == strcasecmp(option, "dead")) {
gQWDebug.sleepSimulate = true;
qError("qw dead debug enabled");
return TSDB_CODE_SUCCESS;
}
if (0 == strcasecmp(option, "redirect")) {
gQWDebug.redirectSimulate = true;
qError("qw redirect debug enabled");
return TSDB_CODE_SUCCESS;
}

18
source/libs/qworker/src/qwMsg.c
View File

@ -43,6 +43,20 @@ void qwFreeFetchRsp(void *msg) {
}
}
int32_t qwBuildAndSendErrorRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code) {
SRpcMsg rpcRsp = {
.msgType = rspType,
.pCont = NULL,
.contLen = 0,
.code = code,
.info = *pConn,
};
tmsgSendRsp(&rpcRsp);
return TSDB_CODE_SUCCESS;
}
int32_t qwBuildAndSendQueryRsp(int32_t rspType, SRpcHandleInfo *pConn, int32_t code, SQWTaskCtx *ctx) {
STbVerInfo* tbInfo = ctx ? &ctx->tbInfo : NULL;
int64_t affectedRows = ctx ? ctx->affectedRows : 0;
@ -184,7 +198,6 @@ int32_t qwBuildAndSendDropMsg(QW_FPARAMS_DEF, SRpcHandleInfo *pConn) {
int32_t code = tmsgPutToQueue(&mgmt->msgCb, FETCH_QUEUE, &pNewMsg);
if (TSDB_CODE_SUCCESS != code) {
QW_SCH_TASK_ELOG("put drop task msg to queue failed, vgId:%d, code:%s", mgmt->nodeId, tstrerror(code));
rpcFreeCont(req);
QW_ERR_RET(code);
}
@ -374,8 +387,7 @@ int32_t qWorkerProcessQueryMsg(void *node, void *qWorkerMgmt, SRpcMsg *pMsg, int
qwMsg.msgInfo.needFetch = msg->needFetch;
char * sql = strndup(msg->msg, msg->sqlLen);
QW_SCH_TASK_DLOG("processQuery start, node:%p, type:%s, handle:%p, sql:%s", node, TMSG_INFO(pMsg->msgType), pMsg->info.handle, sql);
QW_SCH_TASK_DLOG("processQuery start, node:%p, type:%s, handle:%p, SQL:%s", node, TMSG_INFO(pMsg->msgType), pMsg->info.handle, sql);
QW_ERR_RET(qwProcessQuery(QW_FPARAMS(), &qwMsg, sql));
QW_SCH_TASK_DLOG("processQuery end, node:%p", node);

26
source/libs/qworker/src/qwUtil.c
View File

@ -270,7 +270,7 @@ int32_t qwAddAcquireTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx **ctx) { return qwAddTask
void qwReleaseTaskCtx(SQWorker *mgmt, void *ctx) { taosHashRelease(mgmt->ctxHash, ctx); }
void qwFreeTaskHandle(QW_FPARAMS_DEF, qTaskInfo_t *taskHandle) {
void qwFreeTaskHandle(qTaskInfo_t *taskHandle) {
// Note: free/kill may in RC
qTaskInfo_t otaskHandle = atomic_load_ptr(taskHandle);
if (otaskHandle && atomic_val_compare_exchange_ptr(taskHandle, otaskHandle, NULL)) {
@ -278,7 +278,7 @@ void qwFreeTaskHandle(QW_FPARAMS_DEF, qTaskInfo_t *taskHandle) {
}
}
int32_t qwKillTaskHandle(QW_FPARAMS_DEF, SQWTaskCtx *ctx) {
int32_t qwKillTaskHandle(SQWTaskCtx *ctx) {
int32_t code = 0;
// Note: free/kill may in RC
qTaskInfo_t taskHandle = atomic_load_ptr(&ctx->taskHandle);
@ -290,7 +290,7 @@ int32_t qwKillTaskHandle(QW_FPARAMS_DEF, SQWTaskCtx *ctx) {
QW_RET(code);
}
void qwFreeTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx *ctx) {
void qwFreeTaskCtx(SQWTaskCtx *ctx) {
if (ctx->ctrlConnInfo.handle) {
tmsgReleaseHandle(&ctx->ctrlConnInfo, TAOS_CONN_SERVER);
}
@ -300,7 +300,7 @@ void qwFreeTaskCtx(QW_FPARAMS_DEF, SQWTaskCtx *ctx) {
// NO need to release dataConnInfo
qwFreeTaskHandle(QW_FPARAMS(), &ctx->taskHandle);
qwFreeTaskHandle(&ctx->taskHandle);
if (ctx->sinkHandle) {
dsDestroyDataSinker(ctx->sinkHandle);
@ -336,7 +336,7 @@ int32_t qwDropTaskCtx(QW_FPARAMS_DEF) {
QW_ERR_RET(TSDB_CODE_QRY_TASK_CTX_NOT_EXIST);
}
qwFreeTaskCtx(QW_FPARAMS(), &octx);
qwFreeTaskCtx(&octx);
QW_TASK_DLOG_E("task ctx dropped");
@ -463,13 +463,21 @@ void qwDestroyImpl(void *pMgmt) {
mgmt->hbTimer = NULL;
taosTmrCleanUp(mgmt->timer);
// TODO STOP ALL QUERY
// TODO FREE ALL
uint64_t qId, tId;
int32_t eId;
void *pIter = taosHashIterate(mgmt->ctxHash, NULL);
while (pIter) {
SQWTaskCtx *ctx = (SQWTaskCtx *)pIter;
void *key = taosHashGetKey(pIter, NULL);
QW_GET_QTID(key, qId, tId, eId);
qwFreeTaskCtx(ctx);
QW_TASK_DLOG_E("task ctx freed");
pIter = taosHashIterate(mgmt->ctxHash, pIter);
}
taosHashCleanup(mgmt->ctxHash);
void *pIter = taosHashIterate(mgmt->schHash, NULL);
pIter = taosHashIterate(mgmt->schHash, NULL);
while (pIter) {
SQWSchStatus *sch = (SQWSchStatus *)pIter;
qwDestroySchStatus(sch);

76
source/libs/qworker/src/qworker.c
View File

@ -83,6 +83,7 @@ int32_t qwExecTask(QW_FPARAMS_DEF, SQWTaskCtx *ctx, bool *queryEnd) {
// if *taskHandle is NULL, it's killed right now
if (taskHandle) {
qwDbgSimulateSleep();
code = qExecTask(taskHandle, &pRes, &useconds);
if (code) {
if (code != TSDB_CODE_OPS_NOT_SUPPORT) {
@ -293,11 +294,7 @@ int32_t qwHandlePrePhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inpu
QW_LOCK(QW_WRITE, &ctx->lock);
if (QW_PHASE_PRE_FETCH == phase) {
atomic_store_8((int8_t *)&ctx->queryFetched, true);
} else {
atomic_store_8(&ctx->phase, phase);
}
QW_SET_PHASE(ctx, phase);
if (atomic_load_8((int8_t *)&ctx->queryEnd)) {
QW_TASK_ELOG_E("query already end");
@ -370,6 +367,7 @@ int32_t qwHandlePrePhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inpu
}
_return:
if (ctx) {
QW_UPDATE_RSP_CODE(ctx, code);
@ -390,7 +388,6 @@ int32_t qwHandlePostPhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inp
int32_t code = 0;
SQWTaskCtx *ctx = NULL;
SRpcHandleInfo connInfo = {0};
SRpcHandleInfo *rspConnection = NULL;
QW_TASK_DLOG("start to handle event at phase %s", qwPhaseStr(phase));
@ -403,13 +400,6 @@ int32_t qwHandlePostPhaseEvents(QW_FPARAMS_DEF, int8_t phase, SQWPhaseInput *inp
QW_ERR_JRET(TSDB_CODE_QRY_TASK_DROPPED);
}
if (QW_PHASE_POST_QUERY == phase) {
connInfo = ctx->ctrlConnInfo;
rspConnection = &connInfo;
ctx->queryRsped = true;
}
if (QW_EVENT_RECEIVED(ctx, QW_EVENT_DROP)) {
if (QW_PHASE_POST_FETCH == phase) {
QW_TASK_WLOG("drop received at wrong phase %s", qwPhaseStr(phase));
@ -437,17 +427,23 @@ _return:
qwUpdateTaskStatus(QW_FPARAMS(), JOB_TASK_STATUS_PART_SUCC);
}
if (rspConnection) {
qwBuildAndSendQueryRsp(input->msgType + 1, rspConnection, code, ctx);
QW_TASK_DLOG("query msg rsped, handle:%p, code:%x - %s", rspConnection->handle, code, tstrerror(code));
if (QW_PHASE_POST_QUERY == phase && ctx) {
ctx->queryRsped = true;
bool rsped = false;
SQWMsg qwMsg = {.msgType = ctx->msgType, .connInfo = ctx->ctrlConnInfo};
qwDbgSimulateRedirect(&qwMsg, ctx, &rsped);
qwDbgSimulateDead(QW_FPARAMS(), ctx, &rsped);
if (!rsped) {
qwBuildAndSendQueryRsp(input->msgType + 1, &ctx->ctrlConnInfo, code, ctx);
QW_TASK_DLOG("query msg rsped, handle:%p, code:%x - %s", ctx->ctrlConnInfo.handle, code, tstrerror(code));
}
}
if (ctx) {
QW_UPDATE_RSP_CODE(ctx, code);
if (QW_PHASE_POST_FETCH != phase) {
atomic_store_8(&ctx->phase, phase);
}
QW_SET_PHASE(ctx, phase);
QW_UNLOCK(QW_WRITE, &ctx->lock);
qwReleaseTaskCtx(mgmt, ctx);
@ -488,8 +484,6 @@ int32_t qwPreprocessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
QW_ERR_JRET(qwAddTaskStatus(QW_FPARAMS(), JOB_TASK_STATUS_INIT));
qwDbgResponseRedirect(qwMsg, ctx);
_return:
if (ctx) {
@ -517,7 +511,7 @@ int32_t qwProcessQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg, const char* sql) {
ctx->taskType = qwMsg->msgInfo.taskType;
ctx->explain = qwMsg->msgInfo.explain;
ctx->needFetch = qwMsg->msgInfo.needFetch;
ctx->queryType = qwMsg->msgType;
ctx->msgType = qwMsg->msgType;
//QW_TASK_DLOGL("subplan json string, len:%d, %s", qwMsg->msgLen, qwMsg->msg);
@ -636,8 +630,8 @@ int32_t qwProcessCQuery(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
QW_LOCK(QW_WRITE, &ctx->lock);
if (queryEnd || code || 0 == atomic_load_8((int8_t *)&ctx->queryContinue)) {
// Note: if necessary, fetch need to put cquery to queue again
atomic_store_8(&ctx->phase, 0);
// Note: query is not running anymore
QW_SET_PHASE(ctx, 0);
QW_UNLOCK(QW_WRITE, &ctx->lock);
break;
}
@ -662,14 +656,13 @@ int32_t qwProcessFetch(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
QW_ERR_JRET(qwGetTaskCtx(QW_FPARAMS(), &ctx));
ctx->queryType = qwMsg->msgType;
ctx->msgType = qwMsg->msgType;
ctx->dataConnInfo = qwMsg->connInfo;
SOutputData sOutput = {0};
QW_ERR_JRET(qwGetQueryResFromSink(QW_FPARAMS(), ctx, &dataLen, &rsp, &sOutput));
if (NULL == rsp) {
ctx->dataConnInfo = qwMsg->connInfo;
QW_SET_EVENT_RECEIVED(ctx, QW_EVENT_FETCH);
} else {
bool qComplete = (DS_BUF_EMPTY == sOutput.bufStatus && sOutput.queryEnd);
@ -714,9 +707,16 @@ _return:
}
if (code || rsp) {
qwBuildAndSendFetchRsp(qwMsg->msgType + 1, &qwMsg->connInfo, rsp, dataLen, code);
QW_TASK_DLOG("%s send, handle:%p, code:%x - %s, dataLen:%d", TMSG_INFO(qwMsg->msgType + 1), qwMsg->connInfo.handle, code, tstrerror(code),
dataLen);
bool rsped = false;
if (ctx) {
qwDbgSimulateRedirect(qwMsg, ctx, &rsped);
qwDbgSimulateDead(QW_FPARAMS(), ctx, &rsped);
}
if (!rsped) {
qwBuildAndSendFetchRsp(qwMsg->msgType + 1, &qwMsg->connInfo, rsp, dataLen, code);
QW_TASK_DLOG("%s send, handle:%p, code:%x - %s, dataLen:%d", TMSG_INFO(qwMsg->msgType + 1), qwMsg->connInfo.handle, code, tstrerror(code),
dataLen);
}
}
QW_RET(TSDB_CODE_SUCCESS);
@ -724,7 +724,7 @@ _return:
int32_t qwProcessDrop(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
int32_t code = 0;
bool rsped = false;
bool dropped = false;
SQWTaskCtx *ctx = NULL;
bool locked = false;
@ -740,18 +740,14 @@ int32_t qwProcessDrop(QW_FPARAMS_DEF, SQWMsg *qwMsg) {
}
if (QW_QUERY_RUNNING(ctx)) {
QW_ERR_JRET(qwKillTaskHandle(QW_FPARAMS(), ctx));
QW_ERR_JRET(qwKillTaskHandle(ctx));
qwUpdateTaskStatus(QW_FPARAMS(), JOB_TASK_STATUS_DROP);
} else if (ctx->phase > 0) {
QW_ERR_JRET(qwDropTask(QW_FPARAMS()));
rsped = true;
} else {
// task not started
QW_ERR_JRET(qwDropTask(QW_FPARAMS()));
dropped = true;
}
if (!rsped) {
ctx->ctrlConnInfo = qwMsg->connInfo;
if (!dropped) {
QW_SET_EVENT_RECEIVED(ctx, QW_EVENT_DROP);
}
@ -954,7 +950,7 @@ int32_t qwProcessDelete(QW_FPARAMS_DEF, SQWMsg *qwMsg, SDeleteRes *pRes) {
_return:
qwFreeTaskCtx(QW_FPARAMS(), &ctx);
qwFreeTaskCtx(&ctx);
QW_RET(TSDB_CODE_SUCCESS);
}

18
source/libs/scheduler/inc/schInt.h
View File

@ -55,13 +55,11 @@ typedef enum {
#define SCHEDULE_DEFAULT_MAX_TASK_NUM 1000
#define SCHEDULE_DEFAULT_MAX_NODE_TABLE_NUM 200 // unit is TSDB_TABLE_NUM_UNIT
#define SCHEDULE_DEFAULT_POLICY SCH_LOAD_SEQ
#define SCHEDULE_DEFAULT_MAX_NODE_NUM 20
#define SCH_DEFAULT_TASK_TIMEOUT_USEC 10000000
#define SCH_MAX_TASK_TIMEOUT_USEC 60000000
#define SCH_MAX_CANDIDATE_EP_NUM TSDB_MAX_REPLICA
#define SCH_DEFAULT_MAX_RETRY_NUM 6
typedef struct SSchDebug {
bool lockEnable;
@ -211,6 +209,7 @@ typedef struct SSchTask {
int32_t maxExecTimes; // task max exec times
int32_t maxRetryTimes; // task max retry times
int32_t retryTimes; // task retry times
bool waitRetry; // wait for retry
int32_t execId; // task current execute index
SSchLevel *level; // level
SRWLatch planLock; // task update plan lock
@ -274,7 +273,8 @@ typedef struct SSchJob {
int32_t errCode;
SRWLatch resLock;
SExecResult execRes;
void *resData; //TODO free it or not
void *fetchRes; //TODO free it or not
bool fetched;
int32_t resNumOfRows;
SSchResInfo userRes;
const char *sql;
@ -326,7 +326,7 @@ extern SSchedulerMgmt schMgmt;
#define SCH_IS_EXPLAIN_JOB(_job) (EXPLAIN_MODE_ANALYZE == (_job)->attr.explainMode)
#define SCH_NETWORK_ERR(_code) ((_code) == TSDB_CODE_RPC_BROKEN_LINK || (_code) == TSDB_CODE_RPC_NETWORK_UNAVAIL)
#define SCH_MERGE_TASK_NETWORK_ERR(_task, _code, _len) (SCH_NETWORK_ERR(_code) && (((_len) > 0) || (!SCH_IS_DATA_BIND_TASK(_task))))
#define SCH_REDIRECT_MSGTYPE(_msgType) ((_msgType) == TDMT_SCH_QUERY || (_msgType) == TDMT_SCH_MERGE_QUERY || (_msgType) == TDMT_SCH_FETCH || (_msgType) == TDMT_SCH_MERGE_FETCH)
#define SCH_REDIRECT_MSGTYPE(_msgType) ((_msgType) == TDMT_SCH_LINK_BROKEN || (_msgType) == TDMT_SCH_QUERY || (_msgType) == TDMT_SCH_MERGE_QUERY || (_msgType) == TDMT_SCH_FETCH || (_msgType) == TDMT_SCH_MERGE_FETCH)
#define SCH_TASK_NEED_REDIRECT(_task, _msgType, _code, _rspLen) (SCH_REDIRECT_MSGTYPE(_msgType) && (NEED_SCHEDULER_REDIRECT_ERROR(_code) || SCH_MERGE_TASK_NETWORK_ERR((_task), (_code), (_rspLen))))
#define SCH_NEED_RETRY(_msgType, _code) ((SCH_NETWORK_ERR(_code) && SCH_REDIRECT_MSGTYPE(_msgType)) || (_code) == TSDB_CODE_SCH_TIMEOUT_ERROR)
@ -368,6 +368,8 @@ extern SSchedulerMgmt schMgmt;
qError("QID:0x%" PRIx64 ",TID:0x%" PRIx64 ",EID:%d " param, pJob->queryId, SCH_TASK_ID(pTask), SCH_TASK_EID(pTask),__VA_ARGS__)
#define SCH_TASK_DLOG(param, ...) \
qDebug("QID:0x%" PRIx64 ",TID:0x%" PRIx64 ",EID:%d " param, pJob->queryId, SCH_TASK_ID(pTask), SCH_TASK_EID(pTask),__VA_ARGS__)
#define SCH_TASK_TLOG(param, ...) \
qTrace("QID:0x%" PRIx64 ",TID:0x%" PRIx64 ",EID:%d " param, pJob->queryId, SCH_TASK_ID(pTask), SCH_TASK_EID(pTask),__VA_ARGS__)
#define SCH_TASK_DLOGL(param, ...) \
qDebugL("QID:0x%" PRIx64 ",TID:0x%" PRIx64 ",EID:%d " param, pJob->queryId, SCH_TASK_ID(pTask), SCH_TASK_EID(pTask),__VA_ARGS__)
#define SCH_TASK_WLOG(param, ...) \
@ -441,7 +443,7 @@ void schFreeRpcCtx(SRpcCtx *pCtx);
int32_t schGetCallbackFp(int32_t msgType, __async_send_cb_fn_t *fp);
bool schJobNeedToStop(SSchJob *pJob, int8_t *pStatus);
int32_t schProcessOnTaskSuccess(SSchJob *pJob, SSchTask *pTask);
int32_t schSaveJobQueryRes(SSchJob *pJob, SQueryTableRsp *rsp);
int32_t schSaveJobExecRes(SSchJob *pJob, SQueryTableRsp *rsp);
int32_t schProcessOnExplainDone(SSchJob *pJob, SSchTask *pTask, SRetrieveTableRsp *pRsp);
void schProcessOnDataFetched(SSchJob *job);
int32_t schGetTaskInJob(SSchJob *pJob, uint64_t taskId, SSchTask **pTask);
@ -492,7 +494,7 @@ int32_t schSwitchTaskCandidateAddr(SSchJob *pJob, SSchTask *pTask);
void schDirectPostJobRes(SSchedulerReq* pReq, int32_t errCode);
int32_t schHandleJobFailure(SSchJob *pJob, int32_t errCode);
int32_t schHandleJobDrop(SSchJob *pJob, int32_t errCode);
bool schChkCurrentOp(SSchJob *pJob, int32_t op, bool sync);
bool schChkCurrentOp(SSchJob *pJob, int32_t op, int8_t sync);
extern SSchDebug gSCHDebug;

46
source/libs/scheduler/src/schJob.c
View File

@ -110,7 +110,7 @@ int32_t schUpdateJobStatus(SSchJob *pJob, int8_t newStatus) {
break;
case JOB_TASK_STATUS_PART_SUCC:
if (newStatus != JOB_TASK_STATUS_FAIL && newStatus != JOB_TASK_STATUS_SUCC &&
newStatus != JOB_TASK_STATUS_DROP) {
newStatus != JOB_TASK_STATUS_DROP && newStatus != JOB_TASK_STATUS_EXEC) {
SCH_ERR_JRET(TSDB_CODE_QRY_APP_ERROR);
}
@ -389,13 +389,18 @@ int32_t schDumpJobExecRes(SSchJob* pJob, SExecResult* pRes) {
int32_t schDumpJobFetchRes(SSchJob* pJob, void** pData) {
int32_t code = 0;
if (pJob->resData && ((SRetrieveTableRsp *)pJob->resData)->completed) {
SCH_ERR_RET(schSwitchJobStatus(pJob, JOB_TASK_STATUS_SUCC, NULL));
SCH_LOCK(SCH_WRITE, &pJob->resLock);
pJob->fetched = true;
if (pJob->fetchRes && ((SRetrieveTableRsp *)pJob->fetchRes)->completed) {
SCH_ERR_JRET(schSwitchJobStatus(pJob, JOB_TASK_STATUS_SUCC, NULL));
}
while (true) {
*pData = atomic_load_ptr(&pJob->resData);
if (*pData != atomic_val_compare_exchange_ptr(&pJob->resData, *pData, NULL)) {
*pData = atomic_load_ptr(&pJob->fetchRes);
if (*pData != atomic_val_compare_exchange_ptr(&pJob->fetchRes, *pData, NULL)) {
continue;
}
@ -414,7 +419,11 @@ int32_t schDumpJobFetchRes(SSchJob* pJob, void** pData) {
SCH_JOB_DLOG("fetch done, totalRows:%d", pJob->resNumOfRows);
return TSDB_CODE_SUCCESS;
_return:
SCH_UNLOCK(SCH_WRITE, &pJob->resLock);
return code;
}
int32_t schNotifyUserExecRes(SSchJob* pJob) {
@ -512,8 +521,12 @@ int32_t schHandleJobDrop(SSchJob *pJob, int32_t errCode) {
}
int32_t schProcessOnJobPartialSuccess(SSchJob *pJob) {
schPostJobRes(pJob, SCH_OP_EXEC);
int32_t schProcessOnJobPartialSuccess(SSchJob *pJob) {
if (schChkCurrentOp(pJob, SCH_OP_FETCH, -1)) {
SCH_ERR_RET(schLaunchFetchTask(pJob));
} else {
schPostJobRes(pJob, 0);
}
return TSDB_CODE_SUCCESS;
}
@ -526,7 +539,7 @@ int32_t schProcessOnExplainDone(SSchJob *pJob, SSchTask *pTask, SRetrieveTableRs
SCH_TASK_DLOG("got explain rsp, rows:%d, complete:%d", htonl(pRsp->numOfRows), pRsp->completed);
atomic_store_32(&pJob->resNumOfRows, htonl(pRsp->numOfRows));
atomic_store_ptr(&pJob->resData, pRsp);
atomic_store_ptr(&pJob->fetchRes, pRsp);
SCH_SET_TASK_STATUS(pTask, JOB_TASK_STATUS_SUCC);
@ -561,7 +574,7 @@ int32_t schLaunchJobLowerLevel(SSchJob *pJob, SSchTask *pTask) {
return TSDB_CODE_SUCCESS;
}
int32_t schSaveJobQueryRes(SSchJob *pJob, SQueryTableRsp *rsp) {
int32_t schSaveJobExecRes(SSchJob *pJob, SQueryTableRsp *rsp) {
if (rsp->tbFName[0]) {
SCH_LOCK(SCH_WRITE, &pJob->resLock);
@ -600,7 +613,7 @@ int32_t schGetTaskInJob(SSchJob *pJob, uint64_t taskId, SSchTask **pTask) {
int32_t schLaunchJob(SSchJob *pJob) {
if (EXPLAIN_MODE_STATIC == pJob->attr.explainMode) {
SCH_ERR_RET(qExecStaticExplain(pJob->pDag, (SRetrieveTableRsp **)&pJob->resData));
SCH_ERR_RET(qExecStaticExplain(pJob->pDag, (SRetrieveTableRsp **)&pJob->fetchRes));
SCH_ERR_RET(schSwitchJobStatus(pJob, JOB_TASK_STATUS_PART_SUCC, NULL));
} else {
SSchLevel *level = taosArrayGet(pJob->levels, pJob->levelIdx);
@ -661,7 +674,7 @@ void schFreeJobImpl(void *job) {
qDestroyQueryPlan(pJob->pDag);
taosMemoryFreeClear(pJob->userRes.execRes);
taosMemoryFreeClear(pJob->resData);
taosMemoryFreeClear(pJob->fetchRes);
taosMemoryFree(pJob);
int32_t jobNum = atomic_sub_fetch_32(&schMgmt.jobNum, 1);
@ -795,9 +808,14 @@ void schDirectPostJobRes(SSchedulerReq* pReq, int32_t errCode) {
}
}
bool schChkCurrentOp(SSchJob *pJob, int32_t op, bool sync) {
bool schChkCurrentOp(SSchJob *pJob, int32_t op, int8_t sync) {
bool r = false;
SCH_LOCK(SCH_READ, &pJob->opStatus.lock);
bool r = (pJob->opStatus.op == op) && (pJob->opStatus.syncReq == sync);
if (sync >= 0) {
r = (pJob->opStatus.op == op) && (pJob->opStatus.syncReq == sync);
} else {
r = (pJob->opStatus.op == op);
}
SCH_UNLOCK(SCH_READ, &pJob->opStatus.lock);
return r;

13
source/libs/scheduler/src/schRemote.c
View File

@ -256,7 +256,7 @@ int32_t schHandleResponseMsg(SSchJob *pJob, SSchTask *pTask, int32_t execId, SDa
SCH_ERR_JRET(rsp->code);
SCH_ERR_JRET(schSaveJobQueryRes(pJob, rsp));
SCH_ERR_JRET(schSaveJobExecRes(pJob, rsp));
atomic_add_fetch_32(&pJob->resNumOfRows, rsp->affectedRows);
@ -277,8 +277,8 @@ int32_t schHandleResponseMsg(SSchJob *pJob, SSchTask *pTask, int32_t execId, SDa
SCH_ERR_JRET(TSDB_CODE_QRY_INVALID_INPUT);
}
if (pJob->resData) {
SCH_TASK_ELOG("explain result is already generated, res:%p", pJob->resData);
if (pJob->fetchRes) {
SCH_TASK_ELOG("explain result is already generated, res:%p", pJob->fetchRes);
SCH_ERR_JRET(TSDB_CODE_SCH_STATUS_ERROR);
}
@ -325,13 +325,13 @@ int32_t schHandleResponseMsg(SSchJob *pJob, SSchTask *pTask, int32_t execId, SDa
return TSDB_CODE_SUCCESS;
}
if (pJob->resData) {
SCH_TASK_ELOG("got fetch rsp while res already exists, res:%p", pJob->resData);
if (pJob->fetchRes) {
SCH_TASK_ELOG("got fetch rsp while res already exists, res:%p", pJob->fetchRes);
taosMemoryFreeClear(rsp);
SCH_ERR_JRET(TSDB_CODE_SCH_STATUS_ERROR);
}
atomic_store_ptr(&pJob->resData, rsp);
atomic_store_ptr(&pJob->fetchRes, rsp);
atomic_add_fetch_32(&pJob->resNumOfRows, htonl(rsp->numOfRows));
if (rsp->completed) {
@ -1010,6 +1010,7 @@ int32_t schBuildAndSendMsg(SSchJob *pJob, SSchTask *pTask, SQueryNodeAddr *addr,
memcpy(pMsg->msg + len, pTask->msg, pTask->msgLen);
persistHandle = true;
SCH_SET_TASK_HANDLE(pTask, rpcAllocHandle());
break;
}
case TDMT_SCH_FETCH:

52
source/libs/scheduler/src/schTask.c
View File

@ -47,10 +47,10 @@ void schFreeTask(SSchJob *pJob, SSchTask *pTask) {
void schInitTaskRetryTimes(SSchJob *pJob, SSchTask *pTask, SSchLevel *pLevel) {
if (SCH_IS_DATA_BIND_TASK(pTask) || (!SCH_IS_QUERY_JOB(pJob)) || (SCH_ALL != schMgmt.cfg.schPolicy)) {
pTask->maxRetryTimes = SCH_MAX_CANDIDATE_EP_NUM;
pTask->maxRetryTimes = SCH_DEFAULT_MAX_RETRY_NUM;
} else {
int32_t nodeNum = taosArrayGetSize(pJob->nodeList);
pTask->maxRetryTimes = TMAX(nodeNum, SCH_MAX_CANDIDATE_EP_NUM);
pTask->maxRetryTimes = TMAX(nodeNum, SCH_DEFAULT_MAX_RETRY_NUM);
}
pTask->maxExecTimes = pTask->maxRetryTimes * (pLevel->level + 1);
@ -64,11 +64,11 @@ int32_t schInitTask(SSchJob *pJob, SSchTask *pTask, SSubplan *pPlan, SSchLevel *
pTask->execId = -1;
pTask->timeoutUsec = SCH_DEFAULT_TASK_TIMEOUT_USEC;
pTask->taskId = schGenTaskId();
pTask->execNodes =
taosHashInit(SCH_MAX_CANDIDATE_EP_NUM, taosGetDefaultHashFunction(TSDB_DATA_TYPE_INT), true, HASH_NO_LOCK);
schInitTaskRetryTimes(pJob, pTask, pLevel);
pTask->execNodes =
taosHashInit(pTask->maxExecTimes, taosGetDefaultHashFunction(TSDB_DATA_TYPE_INT), true, HASH_NO_LOCK);
pTask->profile.execTime = taosArrayInit(pTask->maxExecTimes, sizeof(int64_t));
if (NULL == pTask->execNodes || NULL == pTask->profile.execTime) {
SCH_ERR_JRET(TSDB_CODE_QRY_OUT_OF_MEMORY);
@ -125,8 +125,8 @@ int32_t schDropTaskExecNode(SSchJob *pJob, SSchTask *pTask, void *handle, int32_
SCH_TASK_DLOG("execId %d removed from execNodeList", execId);
}
if (execId != pTask->execId) { // ignore it
SCH_TASK_DLOG("execId %d is not current execId %d", execId, pTask->execId);
if ((execId != pTask->execId) || pTask->waitRetry) { // ignore it
SCH_TASK_DLOG("execId %d is already not current execId %d, waitRetry %d", execId, pTask->execId, pTask->waitRetry);
SCH_ERR_RET(TSDB_CODE_SCH_IGNORE_ERROR);
}
@ -138,7 +138,17 @@ int32_t schUpdateTaskExecNode(SSchJob *pJob, SSchTask *pTask, void *handle, int3
return TSDB_CODE_SUCCESS;
}
if ((execId != pTask->execId) || pTask->waitRetry) { // ignore it
SCH_TASK_DLOG("handle not updated since execId %d is already not current execId %d, waitRetry %d", execId, pTask->execId, pTask->waitRetry);
return TSDB_CODE_SUCCESS;
}
SSchNodeInfo *nodeInfo = taosHashGet(pTask->execNodes, &execId, sizeof(execId));
if (NULL == nodeInfo) { // ignore it
SCH_TASK_DLOG("handle not updated since execId %d already not exist, current execId %d, waitRetry %d", execId, pTask->execId, pTask->waitRetry);
return TSDB_CODE_SUCCESS;
}
nodeInfo->handle = handle;
SCH_TASK_DLOG("handle updated to %p for execId %d", handle, execId);
@ -335,6 +345,7 @@ int32_t schDoTaskRedirect(SSchJob *pJob, SSchTask *pTask, SDataBuf *pData, int32
return TSDB_CODE_SUCCESS;
}
pTask->waitRetry = true;
schDropTaskOnExecNode(pJob, pTask);
taosHashClear(pTask->execNodes);
SCH_ERR_JRET(schRemoveTaskFromExecList(pJob, pTask));
@ -394,6 +405,18 @@ _return:
int32_t schHandleRedirect(SSchJob *pJob, SSchTask *pTask, SDataBuf *pData, int32_t rspCode) {
int32_t code = 0;
if (JOB_TASK_STATUS_PART_SUCC == pJob->status) {
SCH_LOCK(SCH_WRITE, &pJob->resLock);
if (pJob->fetched) {
SCH_UNLOCK(SCH_WRITE, &pJob->resLock);
SCH_TASK_ELOG("already fetched while got error %s", tstrerror(rspCode));
SCH_ERR_RET(rspCode);
}
SCH_UNLOCK(SCH_WRITE, &pJob->resLock);
schUpdateJobStatus(pJob, JOB_TASK_STATUS_EXEC);
}
if (SCH_IS_DATA_BIND_TASK(pTask)) {
if (NULL == pData->pEpSet) {
SCH_TASK_ELOG("no epset updated while got error %s", tstrerror(rspCode));
@ -591,7 +614,7 @@ int32_t schSetAddrsFromNodeList(SSchJob *pJob, SSchTask *pTask) {
if (pJob->nodeList) {
nodeNum = taosArrayGetSize(pJob->nodeList);
for (int32_t i = 0; i < nodeNum && addNum < SCH_MAX_CANDIDATE_EP_NUM; ++i) {
for (int32_t i = 0; i < nodeNum; ++i) {
SQueryNodeLoad *nload = taosArrayGet(pJob->nodeList, i);
SQueryNodeAddr *naddr = &nload->addr;
@ -600,8 +623,8 @@ int32_t schSetAddrsFromNodeList(SSchJob *pJob, SSchTask *pTask) {
SCH_ERR_RET(TSDB_CODE_QRY_OUT_OF_MEMORY);
}
SCH_TASK_DLOG("set %dth candidate addr, id %d, fqdn:%s, port:%d", i, naddr->nodeId, SCH_GET_CUR_EP(naddr)->fqdn,
SCH_GET_CUR_EP(naddr)->port);
SCH_TASK_TLOG("set %dth candidate addr, id %d, inUse:%d/%d, fqdn:%s, port:%d", i, naddr->nodeId, naddr->epSet.inUse, naddr->epSet.numOfEps,
SCH_GET_CUR_EP(naddr)->fqdn, SCH_GET_CUR_EP(naddr)->port);
++addNum;
}
@ -621,9 +644,9 @@ int32_t schSetTaskCandidateAddrs(SSchJob *pJob, SSchTask *pTask) {
}
pTask->candidateIdx = 0;
pTask->candidateAddrs = taosArrayInit(SCH_MAX_CANDIDATE_EP_NUM, sizeof(SQueryNodeAddr));
pTask->candidateAddrs = taosArrayInit(SCHEDULE_DEFAULT_MAX_NODE_NUM, sizeof(SQueryNodeAddr));
if (NULL == pTask->candidateAddrs) {
SCH_TASK_ELOG("taosArrayInit %d condidate addrs failed", SCH_MAX_CANDIDATE_EP_NUM);
SCH_TASK_ELOG("taosArrayInit %d condidate addrs failed", SCHEDULE_DEFAULT_MAX_NODE_NUM);
SCH_ERR_RET(TSDB_CODE_QRY_OUT_OF_MEMORY);
}
@ -790,6 +813,7 @@ int32_t schLaunchTaskImpl(SSchJob *pJob, SSchTask *pTask) {
atomic_add_fetch_32(&pTask->level->taskLaunchedNum, 1);
pTask->execId++;
pTask->retryTimes++;
pTask->waitRetry = false;
SCH_TASK_DLOG("start to launch task, execId %d, retry %d", pTask->execId, pTask->retryTimes);
@ -885,9 +909,9 @@ void schDropTaskInHashList(SSchJob *pJob, SHashObj *list) {
int32_t schLaunchFetchTask(SSchJob *pJob) {
int32_t code = 0;
void *resData = atomic_load_ptr(&pJob->resData);
if (resData) {
SCH_JOB_DLOG("res already fetched, res:%p", resData);
void *fetchRes = atomic_load_ptr(&pJob->fetchRes);
if (fetchRes) {
SCH_JOB_DLOG("res already fetched, res:%p", fetchRes);
return TSDB_CODE_SUCCESS;
}

1
source/libs/sync/inc/syncInt.h
View File

@ -223,6 +223,7 @@ void syncNodeVoteForSelf(SSyncNode* pSyncNode);
// snapshot --------------
bool syncNodeHasSnapshot(SSyncNode* pSyncNode);
void syncNodeMaybeUpdateCommitBySnapshot(SSyncNode* pSyncNode);
SyncIndex syncNodeGetLastIndex(SSyncNode* pSyncNode);
SyncTerm syncNodeGetLastTerm(SSyncNode* pSyncNode);

5
source/libs/sync/src/syncAppendEntries.c
View File

@ -711,6 +711,9 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
syncNodeEventLog(ths, logBuf);
} while (0);
// maybe update commit index by snapshot
syncNodeMaybeUpdateCommitBySnapshot(ths);
// prepare response msg
SyncAppendEntriesReply* pReply = syncAppendEntriesReplyBuild(ths->vgId);
pReply->srcId = ths->myRaftId;
@ -718,7 +721,7 @@ int32_t syncNodeOnAppendEntriesSnapshot2Cb(SSyncNode* ths, SyncAppendEntriesBatc
pReply->term = ths->pRaftStore->currentTerm;
pReply->privateTerm = ths->pNewNodeReceiver->privateTerm;
pReply->success = false;
pReply->matchIndex = SYNC_INDEX_INVALID;
pReply->matchIndex = ths->commitIndex;
// msg event log
do {

23
source/libs/sync/src/syncAppendEntriesReply.c
View File

@ -147,6 +147,15 @@ static void syncNodeStartSnapshotOnce(SSyncNode* ths, SyncIndex beginIndex, Sync
int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntriesReply* pMsg) {
int32_t ret = 0;
// print log
do {
char logBuf[256];
snprintf(logBuf, sizeof(logBuf), "recv sync-append-entries-reply, term:%lu, match:%ld, success:%d", pMsg->term,
pMsg->matchIndex, pMsg->success);
syncNodeEventLog(ths, logBuf);
} while (0);
// if already drop replica, do not process
if (!syncNodeInRaftGroup(ths, &(pMsg->srcId)) && !ths->pRaftCfg->isStandBy) {
syncNodeEventLog(ths, "recv sync-append-entries-reply, maybe replica already dropped");
@ -238,7 +247,14 @@ int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntrie
SSnapshot oldSnapshot;
ths->pFsm->FpGetSnapshotInfo(ths->pFsm, &oldSnapshot);
SyncTerm newSnapshotTerm = oldSnapshot.lastApplyTerm;
syncNodeStartSnapshotOnce(ths, SYNC_INDEX_BEGIN, nextIndex, newSnapshotTerm, pMsg);
SyncIndex endIndex;
if (ths->pLogStore->syncLogExist(ths->pLogStore, nextIndex + 1)) {
endIndex = nextIndex;
} else {
endIndex = oldSnapshot.lastApplyIndex;
}
syncNodeStartSnapshotOnce(ths, pMsg->matchIndex + 1, endIndex, newSnapshotTerm, pMsg);
// get sender
SSyncSnapshotSender* pSender = syncNodeGetSnapshotSender(ths, &(pMsg->srcId));
@ -256,6 +272,11 @@ int32_t syncNodeOnAppendEntriesReplySnapshot2Cb(SSyncNode* ths, SyncAppendEntrie
}
syncIndexMgrSetIndex(ths->pNextIndex, &(pMsg->srcId), nextIndex);
SyncIndex oldMatchIndex = syncIndexMgrGetIndex(ths->pMatchIndex, &(pMsg->srcId));
if (pMsg->matchIndex > oldMatchIndex) {
syncIndexMgrSetIndex(ths->pMatchIndex, &(pMsg->srcId), pMsg->matchIndex);
}
// event log, update next-index
do {
char host[64];

11
source/libs/sync/src/syncMain.c
View File

@ -1083,6 +1083,17 @@ SSyncNode* syncNodeOpen(const SSyncInfo* pOldSyncInfo) {
return pSyncNode;
}
void syncNodeMaybeUpdateCommitBySnapshot(SSyncNode* pSyncNode) {
if (pSyncNode->pFsm != NULL && pSyncNode->pFsm->FpGetSnapshotInfo != NULL) {
SSnapshot snapshot;
int32_t code = pSyncNode->pFsm->FpGetSnapshotInfo(pSyncNode->pFsm, &snapshot);
ASSERT(code == 0);
if (snapshot.lastApplyIndex > pSyncNode->commitIndex) {
pSyncNode->commitIndex = snapshot.lastApplyIndex;
}
}
}
void syncNodeStart(SSyncNode* pSyncNode) {
// start raft
if (pSyncNode->replicaNum == 1) {

47
source/libs/tdb/src/db/tdbBtree.c
View File

@ -67,7 +67,8 @@ static int tdbBtreeCellSize(const SPage *pPage, SCell *pCell, int dropOfp, TXN *
static int tdbBtcMoveDownward(SBTC *pBtc);
static int tdbBtcMoveUpward(SBTC *pBtc);
int tdbBtreeOpen(int keyLen, int valLen, SPager *pPager, tdb_cmpr_fn_t kcmpr, SBTree **ppBt) {
int tdbBtreeOpen(int keyLen, int valLen, SPager *pPager, char const *tbname, SPgno pgno, tdb_cmpr_fn_t kcmpr,
SBTree **ppBt) {
SBTree *pBt;
int ret;
@ -99,13 +100,54 @@ int tdbBtreeOpen(int keyLen, int valLen, SPager *pPager, tdb_cmpr_fn_t kcmpr, SB
// pBt->minLeaf
pBt->minLeaf = pBt->minLocal;
// if pgno == 0 fetch new btree root leaf page
if (pgno == 0) {
// fetch page & insert into main db
// allocate a new child page
SPage *pPage;
TXN txn;
tdbTxnOpen(&txn, 0, tdbDefaultMalloc, tdbDefaultFree, NULL, 0);
pPager->inTran = 1;
SBtreeInitPageArg zArg;
zArg.flags = 0x1 | 0x2; // root leaf node;
zArg.pBt = pBt;
ret = tdbPagerFetchPage(pPager, &pgno, &pPage, tdbBtreeInitPage, &zArg, &txn);
if (ret < 0) {
return -1;
}
// TODO: Need to zero the page
ret = tdbPagerWrite(pPager, pPage);
if (ret < 0) {
return -1;
}
if (strcmp(TDB_MAINDB_NAME, tbname)) {
ret = tdbTbInsert(pPager->pEnv->pMainDb, tbname, strlen(tbname) + 1, &pgno, sizeof(SPgno), &txn);
if (ret < 0) {
return -1;
}
}
// tdbUnrefPage(pPage);
tdbPCacheRelease(pPager->pCache, pPage, &txn);
tdbCommit(pPager->pEnv, &txn);
tdbTxnClose(&txn);
}
ASSERT(pgno != 0);
pBt->root = pgno;
/*
// TODO: pBt->root
ret = tdbBtreeOpenImpl(pBt);
if (ret < 0) {
tdbOsFree(pBt);
return -1;
}
*/
*ppBt = pBt;
return 0;
}
@ -338,7 +380,6 @@ static int tdbBtreeOpenImpl(SBTree *pBt) {
ASSERT(pgno != 0);
pBt->root = pgno;
return 0;
}

14
source/libs/tdb/src/db/tdbDb.c
View File

@ -64,6 +64,14 @@ int32_t tdbOpen(const char *dbname, int32_t szPage, int32_t pages, TDB **ppDb) {
mkdir(dbname, 0755);
#ifdef USE_MAINDB
// open main db
ret = tdbTbOpen(TDB_MAINDB_NAME, -1, sizeof(SPgno), NULL, pDb, &pDb->pMainDb);
if (ret < 0) {
return -1;
}
#endif
*ppDb = pDb;
return 0;
}
@ -72,6 +80,10 @@ int tdbClose(TDB *pDb) {
SPager *pPager;
if (pDb) {
#ifdef USE_MAINDB
if (pDb->pMainDb) tdbTbClose(pDb->pMainDb);
#endif
for (pPager = pDb->pgrList; pPager; pPager = pDb->pgrList) {
pDb->pgrList = pPager->pNext;
tdbPagerClose(pPager);
@ -179,4 +191,4 @@ void tdbEnvRemovePager(TDB *pDb, SPager *pPager) {
if (pDb->nPgrHash > 8 && pDb->nPager < pDb->nPgrHash / 2) {
// TODO
}
}
}

22
source/libs/tdb/src/db/tdbPager.c
View File

@ -174,6 +174,13 @@ int tdbPagerWrite(SPager *pPager, SPage *pPage) {
for (ppPage = &pPager->pDirty; (*ppPage) && TDB_PAGE_PGNO(*ppPage) < TDB_PAGE_PGNO(pPage);
ppPage = &((*ppPage)->pDirtyNext)) {
}
if (*ppPage && TDB_PAGE_PGNO(*ppPage) == TDB_PAGE_PGNO(pPage)) {
tdbUnrefPage(pPage);
return 0;
}
ASSERT(*ppPage == NULL || TDB_PAGE_PGNO(*ppPage) > TDB_PAGE_PGNO(pPage));
pPage->pDirtyNext = *ppPage;
*ppPage = pPage;
@ -467,7 +474,7 @@ int tdbPagerRestore(SPager *pPager, SBTree *pBt) {
}
TXN txn;
tdbTxnOpen(&txn, 0, tdbDefaultMalloc, tdbDefaultFree, NULL, 0);
tdbTxnOpen(&txn, 0, tdbDefaultMalloc, tdbDefaultFree, NULL, TDB_TXN_WRITE | TDB_TXN_READ_UNCOMMITTED);
SBtreeInitPageArg iArg;
iArg.pBt = pBt;
iArg.flags = 0;
@ -487,6 +494,7 @@ int tdbPagerRestore(SPager *pPager, SBTree *pBt) {
return -1;
}
/*
ret = tdbPagerFetchPage(pPager, &pgno, &pPage, tdbBtreeInitPage, &iArg, &txn);
if (ret < 0) {
return -1;
@ -499,6 +507,18 @@ int tdbPagerRestore(SPager *pPager, SBTree *pBt) {
}
tdbPCacheRelease(pPager->pCache, pPage, &txn);
*/
i64 offset = pPager->pageSize * (pgno - 1);
if (tdbOsLSeek(pPager->fd, offset, SEEK_SET) < 0) {
ASSERT(0);
return -1;
}
ret = tdbOsWrite(pPager->fd, pageBuf, pPager->pageSize);
if (ret < 0) {
ASSERT(0);
return -1;
}
}
tdbOsFSync(pPager->fd);

56
source/libs/tdb/src/db/tdbTable.c
View File

@ -16,7 +16,7 @@
#include "tdbInt.h"
struct STTB {
TDB * pEnv;
TDB *pEnv;
SBTree *pBt;
};
@ -25,12 +25,16 @@ struct STBC {
};
int tdbTbOpen(const char *tbname, int keyLen, int valLen, tdb_cmpr_fn_t keyCmprFn, TDB *pEnv, TTB **ppTb) {
TTB * pTb;
TTB *pTb;
SPager *pPager;
int ret;
char fFullName[TDB_FILENAME_LEN];
SPage * pPage;
SPage *pPage;
SPgno pgno;
void *pKey = NULL;
int nKey = 0;
void *pData = NULL;
int nData = 0;
*ppTb = NULL;
@ -42,6 +46,48 @@ int tdbTbOpen(const char *tbname, int keyLen, int valLen, tdb_cmpr_fn_t keyCmprF
// pTb->pEnv
pTb->pEnv = pEnv;
#ifdef USE_MAINDB
snprintf(fFullName, TDB_FILENAME_LEN, "%s/%s", pEnv->dbName, TDB_MAINDB_NAME);
if (strcmp(TDB_MAINDB_NAME, tbname)) {
pPager = tdbEnvGetPager(pEnv, fFullName);
if (!pPager) {
return -1;
}
ret = tdbTbGet(pPager->pEnv->pMainDb, tbname, strlen(tbname) + 1, &pData, &nData);
if (ret < 0) {
// new pgno & insert into main db
pgno = 0;
} else {
pgno = *(SPgno *)pData;
tdbFree(pKey);
tdbFree(pData);
}
} else {
pPager = tdbEnvGetPager(pEnv, fFullName);
if (pPager == NULL) {
ret = tdbPagerOpen(pEnv->pCache, fFullName, &pPager);
if (ret < 0) {
return -1;
}
tdbEnvAddPager(pEnv, pPager);
pPager->pEnv = pEnv;
}
if (pPager->dbOrigSize > 0) {
pgno = 1;
} else {
pgno = 0;
}
}
#else
pPager = tdbEnvGetPager(pEnv, tbname);
if (pPager == NULL) {
snprintf(fFullName, TDB_FILENAME_LEN, "%s/%s", pEnv->dbName, tbname);
@ -53,10 +99,12 @@ int tdbTbOpen(const char *tbname, int keyLen, int valLen, tdb_cmpr_fn_t keyCmprF
tdbEnvAddPager(pEnv, pPager);
}
#endif
ASSERT(pPager != NULL);
// pTb->pBt
ret = tdbBtreeOpen(keyLen, valLen, pPager, keyCmprFn, &(pTb->pBt));
ret = tdbBtreeOpen(keyLen, valLen, pPager, tbname, pgno, keyCmprFn, &(pTb->pBt));
if (ret < 0) {
return -1;
}

15
source/libs/tdb/src/inc/tdbInt.h
View File

@ -150,7 +150,8 @@ struct SBTC {
};
// SBTree
int tdbBtreeOpen(int keyLen, int valLen, SPager *pFile, tdb_cmpr_fn_t kcmpr, SBTree **ppBt);
int tdbBtreeOpen(int keyLen, int valLen, SPager *pFile, char const *tbname, SPgno pgno, tdb_cmpr_fn_t kcmpr,
SBTree **ppBt);
int tdbBtreeClose(SBTree *pBt);
int tdbBtreeInsert(SBTree *pBt, const void *pKey, int kLen, const void *pVal, int vLen, TXN *pTxn);
int tdbBtreeDelete(SBTree *pBt, const void *pKey, int kLen, TXN *pTxn);
@ -356,6 +357,12 @@ static inline SCell *tdbPageGetCell(SPage *pPage, int idx) {
return pCell;
}
#define USE_MAINDB
#ifdef USE_MAINDB
#define TDB_MAINDB_NAME "main.tdb"
#endif
struct STDB {
char *dbName;
char *jnName;
@ -365,6 +372,9 @@ struct STDB {
int nPager;
int nPgrHash;
SPager **pgrHash;
#ifdef USE_MAINDB
TTB *pMainDb;
#endif
};
struct SPager {
@ -381,6 +391,9 @@ struct SPager {
u8 inTran;
SPager *pNext; // used by TDB
SPager *pHashNext; // used by TDB
#ifdef USE_MAINDB
TDB *pEnv;
#endif
};
#ifdef __cplusplus

2
source/libs/transport/src/trans.c
View File

@ -170,7 +170,7 @@ void rpcSetDefaultAddr(void* thandle, const char* ip, const char* fqdn) {
transSetDefaultAddr(thandle, ip, fqdn);
}
int64_t rpcAllocHandle() { return transAllocHandle(); }
void* rpcAllocHandle() { return (void*)transAllocHandle(); }
int32_t rpcInit() {
transInit();

17
source/libs/transport/src/transCli.c
View File

@ -1,4 +1,5 @@
/** 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
@ -809,7 +810,7 @@ SCliConn* cliGetConn(SCliMsg* pMsg, SCliThrd* pThrd, bool* ignore) {
conn = exh->handle;
if (conn == NULL) {
conn = getConnFromPool(pThrd->pool, EPSET_GET_INUSE_IP(&pCtx->epSet), EPSET_GET_INUSE_PORT(&pCtx->epSet));
*ignore = (conn && 0 == specifyConnRef(conn, true, refId)) ? false : true;
if (conn != NULL) specifyConnRef(conn, true, refId);
}
transReleaseExHandle(transGetRefMgt(), refId);
}
@ -849,14 +850,20 @@ void cliHandleReq(SCliMsg* pMsg, SCliThrd* pThrd) {
bool ignore = false;
SCliConn* conn = cliGetConn(pMsg, pThrd, &ignore);
if (ignore == true) {
tError("ignore msg");
return;
}
if (conn != NULL) {
transCtxMerge(&conn->ctx, &pCtx->appCtx);
transQueuePush(&conn->cliMsgs, pMsg);
cliSend(conn);
} else {
conn = cliCreateConn(pThrd);
int64_t refId = (int64_t)pMsg->msg.info.handle;
if (refId != 0) specifyConnRef(conn, true, refId);
transCtxMerge(&conn->ctx, &pCtx->appCtx);
transQueuePush(&conn->cliMsgs, pMsg);
@ -1206,7 +1213,13 @@ SCliThrd* transGetWorkThrd(STrans* trans, int64_t handle, bool* validHandle) {
if (idx < 0) return NULL;
return ((SCliObj*)trans->tcphandle)->pThreadObj[idx];
}
return transGetWorkThrdFromHandle(handle, validHandle);
SCliThrd* pThrd = transGetWorkThrdFromHandle(handle, validHandle);
if (*validHandle == true && pThrd == NULL) {
int idx = cliRBChoseIdx(trans);
if (idx < 0) return NULL;
pThrd = ((SCliObj*)trans->tcphandle)->pThreadObj[idx];
}
return pThrd;
}
void transReleaseCliHandle(void* handle) {
int idx = -1;

2
source/util/src/terror.c
View File

@ -336,8 +336,6 @@ TAOS_DEFINE_ERROR(TSDB_CODE_VND_TABLE_NOT_EXIST, "Table does not exists
TAOS_DEFINE_ERROR(TSDB_CODE_VND_INVALID_TABLE_ACTION, "Invalid table action")
TAOS_DEFINE_ERROR(TSDB_CODE_VND_COL_ALREADY_EXISTS, "Table column already exists")
TAOS_DEFINE_ERROR(TSDB_CODE_VND_TABLE_COL_NOT_EXISTS, "Table column not exists")
TAOS_DEFINE_ERROR(TSDB_CODE_VND_READ_END, "Read end")
// tsdb
TAOS_DEFINE_ERROR(TSDB_CODE_TDB_INVALID_TABLE_ID, "Invalid table ID")

28
tests/script/jenkins/basic.txt
View File

@ -266,26 +266,27 @@
./test.sh -f tsim/tmq/snapshot1.sim
# --- stable
./test.sh -f tsim/stable/alter_comment.sim
./test.sh -f tsim/stable/alter_count.sim
./test.sh -f tsim/stable/alter_import.sim
./test.sh -f tsim/stable/alter_insert1.sim
./test.sh -f tsim/stable/alter_insert2.sim
./test.sh -f tsim/stable/alter_metrics.sim
./test.sh -f tsim/stable/column_add.sim
./test.sh -f tsim/stable/column_drop.sim
./test.sh -f tsim/stable/column_modify.sim
./test.sh -f tsim/stable/disk.sim
./test.sh -f tsim/stable/dnode3.sim
./test.sh -f tsim/stable/metrics.sim
./test.sh -f tsim/stable/refcount.sim
./test.sh -f tsim/stable/show.sim
./test.sh -f tsim/stable/values.sim
./test.sh -f tsim/stable/vnode3.sim
./test.sh -f tsim/stable/column_add.sim
./test.sh -f tsim/stable/column_drop.sim
./test.sh -f tsim/stable/column_modify.sim
./test.sh -f tsim/stable/tag_add.sim
./test.sh -f tsim/stable/tag_drop.sim
./test.sh -f tsim/stable/tag_filter.sim
./test.sh -f tsim/stable/tag_modify.sim
./test.sh -f tsim/stable/tag_rename.sim
./test.sh -f tsim/stable/alter_comment.sim
./test.sh -f tsim/stable/alter_count.sim
./test.sh -f tsim/stable/alter_insert1.sim
./test.sh -f tsim/stable/alter_insert2.sim
./test.sh -f tsim/stable/alter_import.sim
./test.sh -f tsim/stable/tag_filter.sim
./test.sh -f tsim/stable/values.sim
./test.sh -f tsim/stable/vnode3.sim
# --- for multi process mode
./test.sh -f tsim/user/basic.sim -m
@ -309,6 +310,7 @@
./test.sh -f tsim/valgrind/checkError1.sim
./test.sh -f tsim/valgrind/checkError2.sim
./test.sh -f tsim/valgrind/checkError3.sim
./test.sh -f tsim/valgrind/checkError4.sim
# --- vnode
# unsupport ./test.sh -f tsim/vnode/replica3_basic.sim
@ -366,7 +368,7 @@
./test.sh -f tsim/compute/diff2.sim
./test.sh -f tsim/compute/first.sim
./test.sh -f tsim/compute/interval.sim
# jira ./test.sh -f tsim/compute/last_row.sim
./test.sh -f tsim/compute/last_row.sim
./test.sh -f tsim/compute/last.sim
./test.sh -f tsim/compute/leastsquare.sim
./test.sh -f tsim/compute/max.sim
@ -415,7 +417,7 @@
./test.sh -f tsim/tag/4.sim
./test.sh -f tsim/tag/5.sim
# jira ./test.sh -f tsim/tag/6.sim
# jira ./test.sh -f tsim/tag/add.sim
./test.sh -f tsim/tag/add.sim
./test.sh -f tsim/tag/bigint.sim
./test.sh -f tsim/tag/binary_binary.sim
./test.sh -f tsim/tag/binary.sim

2
tests/script/tsim/compute/last_row.sim
View File

@ -65,8 +65,6 @@ if $data00 != 19 then
return -1
endi
print =============== step7
sql select last_row(tbcol) from $mt
print ===> $data00

4
tests/script/tsim/show/basic.sim
View File

@ -99,7 +99,7 @@ if $rows != 1 then
endi
#sql select * from information_schema.`streams`
sql select * from information_schema.user_tables
if $rows != 30 then
if $rows != 31 then
return -1
endi
#sql select * from information_schema.user_table_distributed
@ -197,7 +197,7 @@ if $rows != 1 then
endi
#sql select * from performance_schema.`streams`
sql select * from information_schema.user_tables
if $rows != 30 then
if $rows != 31 then
return -1
endi
#sql select * from information_schema.user_table_distributed

3
tests/script/tsim/stable/alter_insert1.sim
View File

@ -934,11 +934,8 @@ if $data79 != null then
endi
print ======== step9
system sh/exec.sh -n dnode1 -s stop -x SIGINT
sleep 3000
system sh/exec.sh -n dnode1 -s start
sleep 3000
sql select * from tb order by ts asc
if $rows != 8 then

2
tests/script/tsim/stable/alter_insert2.sim
View File

@ -604,9 +604,7 @@ sql_error alter table tb drop column a
print ======== step9
system sh/exec.sh -n dnode1 -s stop -x SIGINT
sleep 3000
system sh/exec.sh -n dnode1 -s start
sleep 3000
sql select * from tb order by ts desc
if $rows != 7 then

Some files were not shown because too many files have changed in this diff Show More