Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

planner: introduce new cost formula for MPPAggs #35436

Merged
merged 7 commits into from
Jun 21, 2022
Merged

planner: introduce new cost formula for MPPAggs #35436

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7713e37
fixup
qw4990 Jun 16, 2022
e3ae955
fixup
qw4990 Jun 16, 2022
b4c3861
fixup
qw4990 Jun 16, 2022
f40eb02
Merge branch 'master' into master-cost-model-2-mpp-agg
qw4990 Jun 16, 2022
fab56ea
fixup
qw4990 Jun 17, 2022
2fcf7a1
Merge branch 'master' into master-cost-model-2-mpp-agg
qw4990 Jun 20, 2022
7988c12
Merge branch 'master' into master-cost-model-2-mpp-agg
qw4990 Jun 21, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 27 additions & 4 deletions planner/core/plan_cost.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,7 +312,12 @@ func (p *PhysicalTableReader) GetPlanCost(taskType property.TaskType, costFlag u
concurrency = float64(p.ctx.GetSessionVars().DistSQLScanConcurrency())
rowSize = getTblStats(p.tablePlan).GetAvgRowSize(p.ctx, p.tablePlan.Schema().Columns, false, false)
seekCost = estimateNetSeekCost(p.tablePlan)
childCost, err := p.tablePlan.GetPlanCost(property.CopSingleReadTaskType, costFlag)
tType := property.MppTaskType
if p.ctx.GetSessionVars().CostModelVersion == modelVer1 {
// regard the underlying tasks as cop-task on modelVer1 for compatibility
tType = property.CopSingleReadTaskType
}
childCost, err := p.tablePlan.GetPlanCost(tType, costFlag)
if err != nil {
return 0, err
}
Expand All @@ -326,7 +331,8 @@ func (p *PhysicalTableReader) GetPlanCost(taskType property.TaskType, costFlag u
// consider concurrency
p.planCost /= concurrency
// consider tidb_enforce_mpp
if isMPP && p.ctx.GetSessionVars().IsMPPEnforced() {
if isMPP && p.ctx.GetSessionVars().IsMPPEnforced() &&
!hasCostFlag(costFlag, CostFlagRecalculate) { // show the real cost in explain-statements
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will this make a different plan when we use explain or not?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, but I think it's expected. Currently, if we enable enforce_mpp, all plan costs will be zero, which is weird.

p.planCost /= 1000000000
}
}
Expand Down Expand Up @@ -892,12 +898,19 @@ func (p *PhysicalHashJoin) GetPlanCost(taskType property.TaskType, costFlag uint
}

// GetCost computes cost of stream aggregation considering CPU/memory.
func (p *PhysicalStreamAgg) GetCost(inputRows float64, isRoot bool, costFlag uint64) float64 {
func (p *PhysicalStreamAgg) GetCost(inputRows float64, isRoot, isMPP bool, costFlag uint64) float64 {
aggFuncFactor := p.getAggFuncCostFactor(false)
var cpuCost float64
sessVars := p.ctx.GetSessionVars()
if isRoot {
cpuCost = inputRows * sessVars.GetCPUFactor() * aggFuncFactor
} else if isMPP {
if p.ctx.GetSessionVars().CostModelVersion == modelVer2 {
// use the dedicated CPU factor for TiFlash on modelVer2
cpuCost = inputRows * sessVars.GetTiFlashCPUFactor() * aggFuncFactor
} else {
cpuCost = inputRows * sessVars.GetCopCPUFactor() * aggFuncFactor
}
} else {
cpuCost = inputRows * sessVars.GetCopCPUFactor() * aggFuncFactor
}
Expand All @@ -916,7 +929,7 @@ func (p *PhysicalStreamAgg) GetPlanCost(taskType property.TaskType, costFlag uin
return 0, err
}
p.planCost = childCost
p.planCost += p.GetCost(getCardinality(p.children[0], costFlag), taskType == property.RootTaskType, costFlag)
p.planCost += p.GetCost(getCardinality(p.children[0], costFlag), taskType == property.RootTaskType, taskType == property.MppTaskType, costFlag)
p.planCostInit = true
return p.planCost, nil
}
Expand All @@ -936,6 +949,13 @@ func (p *PhysicalHashAgg) GetCost(inputRows float64, isRoot, isMPP bool, costFla
// Cost of additional goroutines.
cpuCost += (con + 1) * sessVars.GetConcurrencyFactor()
}
} else if isMPP {
if p.ctx.GetSessionVars().CostModelVersion == modelVer2 {
// use the dedicated CPU factor for TiFlash on modelVer2
cpuCost = inputRows * sessVars.GetTiFlashCPUFactor() * aggFuncFactor
} else {
cpuCost = inputRows * sessVars.GetCopCPUFactor() * aggFuncFactor
}
} else {
cpuCost = inputRows * sessVars.GetCopCPUFactor() * aggFuncFactor
}
Expand Down Expand Up @@ -1144,6 +1164,9 @@ func (p *PhysicalExchangeReceiver) GetPlanCost(taskType property.TaskType, costF
}

func getOperatorActRows(operator PhysicalPlan) float64 {
if operator == nil {
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It can be nil in some update-statements.

return 0
}
runtimeInfo := operator.SCtx().GetSessionVars().StmtCtx.RuntimeStatsColl
id := operator.ID()
actRows := 0.0
Expand Down
4 changes: 2 additions & 2 deletions planner/core/task.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1665,7 +1665,7 @@ func (p *PhysicalStreamAgg) attach2Task(tasks ...task) task {
partialAgg.SetChildren(cop.indexPlan)
cop.indexPlan = partialAgg
}
cop.addCost(partialAgg.(*PhysicalStreamAgg).GetCost(inputRows, false, 0))
cop.addCost(partialAgg.(*PhysicalStreamAgg).GetCost(inputRows, false, false, 0))
partialAgg.SetCost(cop.cost())
}
t = cop.convertToRootTask(p.ctx)
Expand All @@ -1678,7 +1678,7 @@ func (p *PhysicalStreamAgg) attach2Task(tasks ...task) task {
} else {
attachPlan2Task(p, t)
}
t.addCost(final.GetCost(inputRows, true, 0))
t.addCost(final.GetCost(inputRows, true, false, 0))
t.plan().SetCost(t.cost())
return t
}
Expand Down