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

metrics: fix operator timeout metrics #1541

Merged
merged 2 commits into from
May 21, 2019
Merged

metrics: fix operator timeout metrics #1541

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
f2057fd
fix operator timeout metrics
rleungx May 20, 2019
1583b80
Merge branch 'master' into fix-timeout-metrics
nolouch May 21, 2019
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
2 changes: 1 addition & 1 deletion server/cluster.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,7 +601,7 @@ func (c *RaftCluster) checkOperators() {
log.Info("operator timeout",
zap.Uint64("region-id", op.RegionID()),
zap.Stringer("operator", op))
opController.RemoveOperator(op)
opController.RemoveTimeoutOperator(op)
}
}
}
Expand Down
1 change: 0 additions & 1 deletion server/schedule/operator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,7 +370,6 @@ func (o *Operator) IsTimeout() bool {
timeout = time.Since(o.createTime) > LeaderOperatorWaitTime
}
if timeout {
operatorCounter.WithLabelValues(o.Desc(), "timeout").Inc()
return true
}
return false
Expand Down
10 changes: 9 additions & 1 deletion server/schedule/operator_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ func (oc *OperatorController) Dispatch(region *core.RegionInfo, source string) {
oc.RemoveOperator(op)
} else if timeout {
log.Info("operator timeout", zap.Uint64("region-id", region.GetID()), zap.Reflect("operator", op))
oc.RemoveOperator(op)
oc.RemoveTimeoutOperator(op)
oc.opRecords.Put(op, pdpb.OperatorStatus_TIMEOUT)
}
}
Expand Down Expand Up @@ -238,6 +238,14 @@ func (oc *OperatorController) RemoveOperator(op *Operator) {
oc.removeOperatorLocked(op)
}

// RemoveTimeoutOperator removes a operator which is timeout from the running operators.
func (oc *OperatorController) RemoveTimeoutOperator(op *Operator) {
oc.Lock()
defer oc.Unlock()
operatorCounter.WithLabelValues(op.Desc(), "timeout").Inc()
oc.removeOperatorLocked(op)
}

// GetOperatorStatus gets the operator and its status with the specify id.
func (oc *OperatorController) GetOperatorStatus(id uint64) *OperatorWithStatus {
oc.Lock()
Expand Down