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

schedule: fix datarace in operator.check #8264

Merged
merged 2 commits into from
Jun 7, 2024
Merged

schedule: fix datarace in operator.check #8264

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
849163a
schedule: fix datarace in `operator.check`
lhy1024 Jun 6, 2024
1665065
Merge branch 'master' into fix-datarace5
lhy1024 Jun 7, 2024
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
5 changes: 3 additions & 2 deletions pkg/schedule/operator/operator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,10 +376,11 @@ func (o *Operator) Check(region *core.RegionInfo) OpStep {
defer func() { _ = o.CheckTimeout() }()
for step := atomic.LoadInt32(&o.currentStep); int(step) < len(o.steps); step++ {
if o.steps[int(step)].IsFinish(region) {
if atomic.CompareAndSwapInt64(&(o.stepsTime[step]), 0, time.Now().UnixNano()) {
current := time.Now()
if atomic.CompareAndSwapInt64(&(o.stepsTime[step]), 0, current.UnixNano()) {
startTime, _ := o.getCurrentTimeAndStep()
operatorStepDuration.WithLabelValues(reflect.TypeOf(o.steps[int(step)]).Name()).
Observe(time.Unix(0, o.stepsTime[step]).Sub(startTime).Seconds())
Copy link
Member

Choose a reason for hiding this comment

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

Is stepsTime useless?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

If the code goes into this branch, it means that o.stepsTime[step]) is now time.Now()

Observe(current.Sub(startTime).Seconds())
}
atomic.StoreInt32(&o.currentStep, step+1)
} else {
Expand Down
2 changes: 1 addition & 1 deletion pkg/schedule/operator/operator_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,7 +461,7 @@ func (oc *Controller) checkAddOperator(isPromoting bool, ops ...*Operator) (bool
return false, NotInCreateStatus
}
if !isPromoting && oc.wopStatus.getCount(op.Desc()) >= oc.config.GetSchedulerMaxWaitingOperator() {
log.Debug("exceed max return false", zap.Uint64("waiting", oc.wopStatus.ops[op.Desc()]), zap.String("desc", op.Desc()), zap.Uint64("max", oc.config.GetSchedulerMaxWaitingOperator()))
log.Debug("exceed max return false", zap.Uint64("waiting", oc.wopStatus.getCount(op.Desc())), zap.String("desc", op.Desc()), zap.Uint64("max", oc.config.GetSchedulerMaxWaitingOperator()))
operatorCounter.WithLabelValues(op.Desc(), "exceed-max-waiting").Inc()
return false, ExceedWaitLimit
}
Expand Down
25 changes: 25 additions & 0 deletions pkg/schedule/operator/operator_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ package operator
import (
"context"
"encoding/json"
"sync"
"sync/atomic"
"testing"
"time"
Expand Down Expand Up @@ -570,3 +571,27 @@ func (suite *operatorTestSuite) TestToJSONObject() {
obj = op.ToJSONObject()
suite.Equal(TIMEOUT, obj.Status)
}

func TestOperatorCheckConcurrently(t *testing.T) {
re := require.New(t)
region := newTestRegion(1, 1, [2]uint64{1, 1}, [2]uint64{2, 2})
// addPeer1, transferLeader1, removePeer3
steps := []OpStep{
AddPeer{ToStore: 1, PeerID: 1},
TransferLeader{FromStore: 3, ToStore: 1},
RemovePeer{FromStore: 3},
}
op := NewTestOperator(1, &metapb.RegionEpoch{}, OpAdmin|OpLeader|OpRegion, steps...)
re.Equal(constant.Urgent, op.GetPriorityLevel())
checkSteps(re, op, steps)
op.Start()
var wg sync.WaitGroup
for i := 0; i < 10; i++ {
wg.Add(1)
go func() {
defer wg.Done()
re.Nil(op.Check(region))
}()
}
wg.Wait()
}