github.com/pingcap/tiflow@v0.0.0-20240520035814-5bf52d54e205/dm/chaos/cases/diff.go (about)

     1  // Copyright 2020 PingCAP, Inc.
     2  //
     3  // Licensed under the Apache License, Version 2.0 (the "License");
     4  // you may not use this file except in compliance with the License.
     5  // You may obtain a copy of the License at
     6  //
     7  //     http://www.apache.org/licenses/LICENSE-2.0
     8  //
     9  // Unless required by applicable law or agreed to in writing, software
    10  // distributed under the License is distributed on an "AS IS" BASIS,
    11  // See the License for the specific language governing permissions and
    12  // limitations under the License.
    13  
    14  package main
    15  
    16  import (
    17  	"context"
    18  	"database/sql"
    19  	"fmt"
    20  	"time"
    21  
    22  	"github.com/pingcap/errors"
    23  	"github.com/pingcap/tidb-tools/pkg/diff"
    24  	"github.com/pingcap/tidb/pkg/util/dbutil"
    25  	"github.com/pingcap/tiflow/dm/pkg/log"
    26  	"go.uber.org/zap"
    27  )
    28  
    29  // diffDataLoop checks whether target has the same data with source via `sync-diff-inspector` multiple times.
    30  func diffDataLoop(ctx context.Context, count int, interval time.Duration, schema string, tables []string, targetDB *sql.DB, sourceDBs ...*sql.DB) (err error) {
    31  	for i := 0; i < count; i++ {
    32  		select {
    33  		case <-ctx.Done():
    34  			return nil
    35  		case <-time.After(interval):
    36  			err = diffData(ctx, schema, tables, targetDB, sourceDBs...)
    37  			if err == nil {
    38  				return nil
    39  			}
    40  			log.L().Warn("diff data error", zap.Int("count", i+1), log.ShortError(err))
    41  		}
    42  	}
    43  	return err
    44  }
    45  
    46  // diffData checks whether target has the same data with source via `sync-diff-inspector`.
    47  func diffData(ctx context.Context, schema string, tables []string, targetDB *sql.DB, sourceDBs ...*sql.DB) error {
    48  	for _, table := range tables {
    49  		sourceTables := make([]*diff.TableInstance, 0, len(sourceDBs))
    50  		for i, sourceDB := range sourceDBs {
    51  			sourceTables = append(sourceTables, &diff.TableInstance{
    52  				Conn:       sourceDB,
    53  				Schema:     schema,
    54  				Table:      table,
    55  				InstanceID: fmt.Sprintf("source-%d", i),
    56  			})
    57  		}
    58  
    59  		targetTable := &diff.TableInstance{
    60  			Conn:       targetDB,
    61  			Schema:     schema,
    62  			Table:      table,
    63  			InstanceID: "target",
    64  		}
    65  
    66  		td := &diff.TableDiff{
    67  			SourceTables:     sourceTables,
    68  			TargetTable:      targetTable,
    69  			ChunkSize:        1000,
    70  			Sample:           100,
    71  			CheckThreadCount: 1,
    72  			UseChecksum:      true,
    73  			TiDBStatsSource:  targetTable,
    74  			CpDB:             targetDB,
    75  		}
    76  
    77  		structEqual, dataEqual, err := td.Equal(ctx, func(dml string) error {
    78  			return nil
    79  		})
    80  
    81  		if errors.Cause(err) == context.Canceled || errors.Cause(err) == context.DeadlineExceeded {
    82  			return nil
    83  		}
    84  		if !structEqual {
    85  			return fmt.Errorf("different struct for table %s", dbutil.TableName(schema, table))
    86  		} else if !dataEqual {
    87  			return fmt.Errorf("different data for table %s", dbutil.TableName(schema, table))
    88  		}
    89  		log.L().Info("data equal for table", zap.String("schema", schema), zap.String("table", table))
    90  	}
    91  
    92  	return nil
    93  }