github.com/pingcap/ticdc@v0.0.0-20220526033649-485a10ef2652/pkg/scheduler/table_number.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 scheduler
    15  
    16  import "github.com/pingcap/ticdc/cdc/model"
    17  
    18  // TableNumberScheduler provides a feature that scheduling by the table number
    19  type TableNumberScheduler struct {
    20  	workloads workloads
    21  }
    22  
    23  // newTableNumberScheduler creates a new table number scheduler
    24  func newTableNumberScheduler() *TableNumberScheduler {
    25  	return &TableNumberScheduler{
    26  		workloads: make(workloads),
    27  	}
    28  }
    29  
    30  // ResetWorkloads implements the Scheduler interface
    31  func (t *TableNumberScheduler) ResetWorkloads(captureID model.CaptureID, workloads model.TaskWorkload) {
    32  	t.workloads.SetCapture(captureID, workloads)
    33  }
    34  
    35  // AlignCapture implements the Scheduler interface
    36  func (t *TableNumberScheduler) AlignCapture(captureIDs map[model.CaptureID]struct{}) {
    37  	t.workloads.AlignCapture(captureIDs)
    38  }
    39  
    40  // Skewness implements the Scheduler interface
    41  func (t *TableNumberScheduler) Skewness() float64 {
    42  	return t.workloads.Skewness()
    43  }
    44  
    45  // CalRebalanceOperates implements the Scheduler interface
    46  func (t *TableNumberScheduler) CalRebalanceOperates(targetSkewness float64) (
    47  	skewness float64, moveTableJobs map[model.TableID]*model.MoveTableJob) {
    48  	var totalTableNumber uint64
    49  	for _, captureWorkloads := range t.workloads {
    50  		totalTableNumber += uint64(len(captureWorkloads))
    51  	}
    52  	limitTableNumber := (float64(totalTableNumber) / float64(len(t.workloads))) + 1
    53  	appendTables := make(map[model.TableID]model.Ts)
    54  	moveTableJobs = make(map[model.TableID]*model.MoveTableJob)
    55  
    56  	for captureID, captureWorkloads := range t.workloads {
    57  		for float64(len(captureWorkloads)) >= limitTableNumber {
    58  			for tableID := range captureWorkloads {
    59  				// find a table in this capture
    60  				appendTables[tableID] = 0
    61  				moveTableJobs[tableID] = &model.MoveTableJob{
    62  					From:    captureID,
    63  					TableID: tableID,
    64  				}
    65  				t.workloads.RemoveTable(captureID, tableID)
    66  				break
    67  			}
    68  		}
    69  	}
    70  	addOperations := t.DistributeTables(appendTables)
    71  	for captureID, tableOperations := range addOperations {
    72  		for tableID := range tableOperations {
    73  			job := moveTableJobs[tableID]
    74  			job.To = captureID
    75  			if job.From == job.To {
    76  				delete(moveTableJobs, tableID)
    77  			}
    78  		}
    79  	}
    80  	skewness = t.Skewness()
    81  	return
    82  }
    83  
    84  // DistributeTables implements the Scheduler interface
    85  func (t *TableNumberScheduler) DistributeTables(tableIDs map[model.TableID]model.Ts) map[model.CaptureID]map[model.TableID]*model.TableOperation {
    86  	result := make(map[model.CaptureID]map[model.TableID]*model.TableOperation, len(t.workloads))
    87  	for tableID, boundaryTs := range tableIDs {
    88  		captureID := t.workloads.SelectIdleCapture()
    89  		operations := result[captureID]
    90  		if operations == nil {
    91  			operations = make(map[model.TableID]*model.TableOperation)
    92  			result[captureID] = operations
    93  		}
    94  		operations[tableID] = &model.TableOperation{
    95  			BoundaryTs: boundaryTs,
    96  		}
    97  		t.workloads.SetTable(captureID, tableID, model.WorkloadInfo{Workload: 1})
    98  	}
    99  	return result
   100  }