milvus/internal/proxy/task_database.go
Tianx 2c0c5ef41e
feat: timestamptz expression & index & timezone (#44080)
issue: https://github.com/milvus-io/milvus/issues/27467

>My plan is as follows.
>- [x] M1 Create collection with timestamptz field
>- [x] M2 Insert timestamptz field data
>- [x] M3 Retrieve timestamptz field data
>- [x] M4 Implement handoff
>- [x] M5 Implement compare operator
>- [x] M6 Implement extract operator
 >- [x] M8 Support database/collection level default timezone
>- [x] M7 Support STL-SORT index for datatype timestamptz

---

The third PR of issue: https://github.com/milvus-io/milvus/issues/27467,
which completes M5, M6, M7, M8 described above.

## M8 Default Timezone

We will be able to use alter_collection() and alter_database() in a
future Python SDK release to modify the default timezone at the
collection or database level.

For insert requests, the timezone will be resolved using the following
order of precedence: String Literal-> Collection Default -> Database
Default.
For retrieval requests, the timezone will be resolved in this order:
Query Parameters -> Collection Default -> Database Default.
In both cases, the final fallback timezone is UTC.


## M5: Comparison Operators

We can now use the following expression format to filter on the
timestamptz field:

- `timestamptz_field [+/- INTERVAL 'interval_string'] {comparison_op}
ISO 'iso_string' `

- The interval_string follows the ISO 8601 duration format, for example:
P1Y2M3DT1H2M3S.

- The iso_string follows the ISO 8601 timestamp format, for example:
2025-01-03T00:00:00+08:00.

- Example expressions: "tsz + INTERVAL 'P0D' != ISO
'2025-01-03T00:00:00+08:00'" or "tsz != ISO
'2025-01-03T00:00:00+08:00'".

## M6: Extract

We will be able to extract sepecific time filed by kwargs in a future
Python SDK release.
The key is `time_fields`, and value should be one or more of "year,
month, day, hour, minute, second, microsecond", seperated by comma or
space. Then the result of each record would be an array of int64.



## M7: Indexing Support

Expressions without interval arithmetic can be accelerated using an
STL-SORT index. However, expressions that include interval arithmetic
cannot be indexed. This is because the result of an interval calculation
depends on the specific timestamp value. For example, adding one month
to a date in February results in a different number of added days than
adding one month to a date in March.

--- 

After this PR, the input / output type of timestamptz would be iso
string. Timestampz would be stored as timestamptz data, which is int64_t
finally.

> for more information, see https://en.wikipedia.org/wiki/ISO_8601

---------

Signed-off-by: xtx <xtianx@smail.nju.edu.cn>
2025-09-23 10:24:12 +08:00

415 lines
9.7 KiB
Go

package proxy
import (
"context"
"fmt"
"go.uber.org/zap"
"github.com/milvus-io/milvus-proto/go-api/v2/commonpb"
"github.com/milvus-io/milvus-proto/go-api/v2/milvuspb"
"github.com/milvus-io/milvus/internal/types"
"github.com/milvus-io/milvus/pkg/v2/common"
"github.com/milvus-io/milvus/pkg/v2/log"
"github.com/milvus-io/milvus/pkg/v2/proto/rootcoordpb"
"github.com/milvus-io/milvus/pkg/v2/util/commonpbutil"
"github.com/milvus-io/milvus/pkg/v2/util/merr"
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
)
type createDatabaseTask struct {
baseTask
Condition
*milvuspb.CreateDatabaseRequest
ctx context.Context
mixCoord types.MixCoordClient
result *commonpb.Status
}
func (cdt *createDatabaseTask) TraceCtx() context.Context {
return cdt.ctx
}
func (cdt *createDatabaseTask) ID() UniqueID {
return cdt.Base.MsgID
}
func (cdt *createDatabaseTask) SetID(uid UniqueID) {
cdt.Base.MsgID = uid
}
func (cdt *createDatabaseTask) Name() string {
return CreateDatabaseTaskName
}
func (cdt *createDatabaseTask) Type() commonpb.MsgType {
return cdt.Base.MsgType
}
func (cdt *createDatabaseTask) BeginTs() Timestamp {
return cdt.Base.Timestamp
}
func (cdt *createDatabaseTask) EndTs() Timestamp {
return cdt.Base.Timestamp
}
func (cdt *createDatabaseTask) SetTs(ts Timestamp) {
cdt.Base.Timestamp = ts
}
func (cdt *createDatabaseTask) OnEnqueue() error {
if cdt.Base == nil {
cdt.Base = commonpbutil.NewMsgBase()
}
cdt.Base.MsgType = commonpb.MsgType_CreateDatabase
cdt.Base.SourceID = paramtable.GetNodeID()
return nil
}
func (cdt *createDatabaseTask) PreExecute(ctx context.Context) error {
return ValidateDatabaseName(cdt.GetDbName())
}
func (cdt *createDatabaseTask) Execute(ctx context.Context) error {
var err error
cdt.result, err = cdt.mixCoord.CreateDatabase(ctx, cdt.CreateDatabaseRequest)
err = merr.CheckRPCCall(cdt.result, err)
return err
}
func (cdt *createDatabaseTask) PostExecute(ctx context.Context) error {
return nil
}
type dropDatabaseTask struct {
baseTask
Condition
*milvuspb.DropDatabaseRequest
ctx context.Context
mixCoord types.MixCoordClient
result *commonpb.Status
}
func (ddt *dropDatabaseTask) TraceCtx() context.Context {
return ddt.ctx
}
func (ddt *dropDatabaseTask) ID() UniqueID {
return ddt.Base.MsgID
}
func (ddt *dropDatabaseTask) SetID(uid UniqueID) {
ddt.Base.MsgID = uid
}
func (ddt *dropDatabaseTask) Name() string {
return DropCollectionTaskName
}
func (ddt *dropDatabaseTask) Type() commonpb.MsgType {
return ddt.Base.MsgType
}
func (ddt *dropDatabaseTask) BeginTs() Timestamp {
return ddt.Base.Timestamp
}
func (ddt *dropDatabaseTask) EndTs() Timestamp {
return ddt.Base.Timestamp
}
func (ddt *dropDatabaseTask) SetTs(ts Timestamp) {
ddt.Base.Timestamp = ts
}
func (ddt *dropDatabaseTask) OnEnqueue() error {
if ddt.Base == nil {
ddt.Base = commonpbutil.NewMsgBase()
}
ddt.Base.MsgType = commonpb.MsgType_DropDatabase
ddt.Base.SourceID = paramtable.GetNodeID()
return nil
}
func (ddt *dropDatabaseTask) PreExecute(ctx context.Context) error {
return ValidateDatabaseName(ddt.GetDbName())
}
func (ddt *dropDatabaseTask) Execute(ctx context.Context) error {
var err error
ddt.result, err = ddt.mixCoord.DropDatabase(ctx, ddt.DropDatabaseRequest)
err = merr.CheckRPCCall(ddt.result, err)
if err == nil {
globalMetaCache.RemoveDatabase(ctx, ddt.DbName)
}
return err
}
func (ddt *dropDatabaseTask) PostExecute(ctx context.Context) error {
return nil
}
type listDatabaseTask struct {
baseTask
Condition
*milvuspb.ListDatabasesRequest
ctx context.Context
mixCoord types.MixCoordClient
result *milvuspb.ListDatabasesResponse
}
func (ldt *listDatabaseTask) TraceCtx() context.Context {
return ldt.ctx
}
func (ldt *listDatabaseTask) ID() UniqueID {
return ldt.Base.MsgID
}
func (ldt *listDatabaseTask) SetID(uid UniqueID) {
ldt.Base.MsgID = uid
}
func (ldt *listDatabaseTask) Name() string {
return ListDatabaseTaskName
}
func (ldt *listDatabaseTask) Type() commonpb.MsgType {
return ldt.Base.MsgType
}
func (ldt *listDatabaseTask) BeginTs() Timestamp {
return ldt.Base.Timestamp
}
func (ldt *listDatabaseTask) EndTs() Timestamp {
return ldt.Base.Timestamp
}
func (ldt *listDatabaseTask) SetTs(ts Timestamp) {
ldt.Base.Timestamp = ts
}
func (ldt *listDatabaseTask) OnEnqueue() error {
ldt.Base = commonpbutil.NewMsgBase()
ldt.Base.MsgType = commonpb.MsgType_ListDatabases
ldt.Base.SourceID = paramtable.GetNodeID()
return nil
}
func (ldt *listDatabaseTask) PreExecute(ctx context.Context) error {
return nil
}
func (ldt *listDatabaseTask) Execute(ctx context.Context) error {
var err error
ctx = AppendUserInfoForRPC(ctx)
ldt.result, err = ldt.mixCoord.ListDatabases(ctx, ldt.ListDatabasesRequest)
return merr.CheckRPCCall(ldt.result, err)
}
func (ldt *listDatabaseTask) PostExecute(ctx context.Context) error {
return nil
}
type alterDatabaseTask struct {
baseTask
Condition
*milvuspb.AlterDatabaseRequest
ctx context.Context
mixCoord types.MixCoordClient
result *commonpb.Status
}
func (t *alterDatabaseTask) TraceCtx() context.Context {
return t.ctx
}
func (t *alterDatabaseTask) ID() UniqueID {
return t.Base.MsgID
}
func (t *alterDatabaseTask) SetID(uid UniqueID) {
t.Base.MsgID = uid
}
func (t *alterDatabaseTask) Name() string {
return AlterDatabaseTaskName
}
func (t *alterDatabaseTask) Type() commonpb.MsgType {
return t.Base.MsgType
}
func (t *alterDatabaseTask) BeginTs() Timestamp {
return t.Base.Timestamp
}
func (t *alterDatabaseTask) EndTs() Timestamp {
return t.Base.Timestamp
}
func (t *alterDatabaseTask) SetTs(ts Timestamp) {
t.Base.Timestamp = ts
}
func (t *alterDatabaseTask) OnEnqueue() error {
if t.Base == nil {
t.Base = commonpbutil.NewMsgBase()
}
t.Base.MsgType = commonpb.MsgType_AlterDatabase
t.Base.SourceID = paramtable.GetNodeID()
return nil
}
func (t *alterDatabaseTask) PreExecute(ctx context.Context) error {
if len(t.GetProperties()) > 0 {
// Check the validation of timezone
err := checkTimezone(t.Properties...)
if err != nil {
return err
}
}
_, ok := common.GetReplicateID(t.Properties)
if ok {
return merr.WrapErrParameterInvalidMsg("can't set the replicate id property in alter database request")
}
endTS, ok := common.GetReplicateEndTS(t.Properties)
if !ok { // not exist replicate end ts property
return nil
}
cacheInfo, err := globalMetaCache.GetDatabaseInfo(ctx, t.DbName)
if err != nil {
return err
}
oldReplicateEnable, _ := common.IsReplicateEnabled(cacheInfo.properties)
if !oldReplicateEnable { // old replicate enable is false
return merr.WrapErrParameterInvalidMsg("can't set the replicate end ts property in alter database request when db replicate is disabled")
}
allocResp, err := t.mixCoord.AllocTimestamp(ctx, &rootcoordpb.AllocTimestampRequest{
Count: 1,
BlockTimestamp: endTS,
})
if err = merr.CheckRPCCall(allocResp, err); err != nil {
return merr.WrapErrServiceInternal("alloc timestamp failed", err.Error())
}
if allocResp.GetTimestamp() <= endTS {
return merr.WrapErrServiceInternal("alter database: alloc timestamp failed, timestamp is not greater than endTS",
fmt.Sprintf("timestamp = %d, endTS = %d", allocResp.GetTimestamp(), endTS))
}
return nil
}
func (t *alterDatabaseTask) Execute(ctx context.Context) error {
var err error
req := &rootcoordpb.AlterDatabaseRequest{
Base: t.AlterDatabaseRequest.GetBase(),
DbName: t.AlterDatabaseRequest.GetDbName(),
DbId: t.AlterDatabaseRequest.GetDbId(),
Properties: t.AlterDatabaseRequest.GetProperties(),
DeleteKeys: t.AlterDatabaseRequest.GetDeleteKeys(),
}
ret, err := t.mixCoord.AlterDatabase(ctx, req)
err = merr.CheckRPCCall(ret, err)
if err != nil {
return err
}
t.result = ret
return nil
}
func (t *alterDatabaseTask) PostExecute(ctx context.Context) error {
return nil
}
type describeDatabaseTask struct {
baseTask
Condition
*milvuspb.DescribeDatabaseRequest
ctx context.Context
mixCoord types.MixCoordClient
result *milvuspb.DescribeDatabaseResponse
}
func (t *describeDatabaseTask) TraceCtx() context.Context {
return t.ctx
}
func (t *describeDatabaseTask) ID() UniqueID {
return t.Base.MsgID
}
func (t *describeDatabaseTask) SetID(uid UniqueID) {
t.Base.MsgID = uid
}
func (t *describeDatabaseTask) Name() string {
return AlterDatabaseTaskName
}
func (t *describeDatabaseTask) Type() commonpb.MsgType {
return t.Base.MsgType
}
func (t *describeDatabaseTask) BeginTs() Timestamp {
return t.Base.Timestamp
}
func (t *describeDatabaseTask) EndTs() Timestamp {
return t.Base.Timestamp
}
func (t *describeDatabaseTask) SetTs(ts Timestamp) {
t.Base.Timestamp = ts
}
func (t *describeDatabaseTask) OnEnqueue() error {
if t.Base == nil {
t.Base = commonpbutil.NewMsgBase()
}
t.Base.MsgType = commonpb.MsgType_DescribeDatabase
t.Base.SourceID = paramtable.GetNodeID()
return nil
}
func (t *describeDatabaseTask) PreExecute(ctx context.Context) error {
return nil
}
func (t *describeDatabaseTask) Execute(ctx context.Context) error {
req := &rootcoordpb.DescribeDatabaseRequest{
Base: t.DescribeDatabaseRequest.GetBase(),
DbName: t.DescribeDatabaseRequest.GetDbName(),
}
ctx = AppendUserInfoForRPC(ctx)
ret, err := t.mixCoord.DescribeDatabase(ctx, req)
if err != nil {
log.Ctx(ctx).Warn("DescribeDatabase failed", zap.Error(err))
return err
}
if err := merr.CheckRPCCall(ret, err); err != nil {
log.Ctx(ctx).Warn("DescribeDatabase failed", zap.Error(err))
return err
}
t.result = &milvuspb.DescribeDatabaseResponse{
Status: ret.GetStatus(),
DbName: ret.GetDbName(),
DbID: ret.GetDbID(),
CreatedTimestamp: ret.GetCreatedTimestamp(),
Properties: ret.GetProperties(),
}
return nil
}
func (t *describeDatabaseTask) PostExecute(ctx context.Context) error {
return nil
}