kubernetes/pkg/cloudprovider/providers/gce/gce_op.go
Bowei Du ee847ebf8a Add metrics to all major gce operations {latency, errors}
The new metrics is:

  cloudprovider_gce_api_request_duration_seconds{request, region, zone}
  cloudprovider_gce_api_request_errors{request, region, zone}

`request` is the specific function that is used.
`region` is the target region (Will be "<n/a>" if not applicable)
`zone` is the target zone (Will be "<n/a>" if not applicable)

Note: this fixes some issues with the previous implementation of
metrics for disks:
- Time duration tracked was of the initial API call, not the entire
  operation.
- Metrics label tuple would have resulted in many independent
  histograms stored, one for each disk. (Did not aggregate well).
2017-04-27 12:49:30 -07:00

109 lines
3.2 KiB
Go

/*
Copyright 2017 The Kubernetes Authors.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
package gce
import (
"fmt"
"time"
"k8s.io/apimachinery/pkg/util/wait"
"github.com/golang/glog"
compute "google.golang.org/api/compute/v1"
"google.golang.org/api/googleapi"
)
func (gce *GCECloud) waitForOp(op *compute.Operation, getOperation func(operationName string) (*compute.Operation, error), mc *metricContext) error {
if op == nil {
return mc.Observe(fmt.Errorf("operation must not be nil"))
}
if opIsDone(op) {
return getErrorFromOp(op)
}
opStart := time.Now()
opName := op.Name
return wait.Poll(operationPollInterval, operationPollTimeoutDuration, func() (bool, error) {
start := time.Now()
gce.operationPollRateLimiter.Accept()
duration := time.Now().Sub(start)
if duration > 5*time.Second {
glog.V(2).Infof("pollOperation: throttled %v for %v", duration, opName)
}
pollOp, err := getOperation(opName)
if err != nil {
glog.Warningf("GCE poll operation %s failed: pollOp: [%v] err: [%v] getErrorFromOp: [%v]",
opName, pollOp, err, getErrorFromOp(pollOp))
}
done := opIsDone(pollOp)
if done {
duration := time.Now().Sub(opStart)
if duration > 1*time.Minute {
// Log the JSON. It's cleaner than the %v structure.
enc, err := pollOp.MarshalJSON()
if err != nil {
glog.Warningf("waitForOperation: long operation (%v): %v (failed to encode to JSON: %v)",
duration, pollOp, err)
} else {
glog.V(2).Infof("waitForOperation: long operation (%v): %v",
duration, string(enc))
}
}
}
return done, mc.Observe(getErrorFromOp(pollOp))
})
}
func opIsDone(op *compute.Operation) bool {
return op != nil && op.Status == "DONE"
}
func getErrorFromOp(op *compute.Operation) error {
if op != nil && op.Error != nil && len(op.Error.Errors) > 0 {
err := &googleapi.Error{
Code: int(op.HttpErrorStatusCode),
Message: op.Error.Errors[0].Message,
}
glog.Errorf("GCE operation failed: %v", err)
return err
}
return nil
}
func (gce *GCECloud) waitForGlobalOp(op *compute.Operation, mc *metricContext) error {
return gce.waitForOp(op, func(operationName string) (*compute.Operation, error) {
return gce.service.GlobalOperations.Get(gce.projectID, operationName).Do()
}, mc)
}
func (gce *GCECloud) waitForRegionOp(op *compute.Operation, region string, mc *metricContext) error {
return gce.waitForOp(op, func(operationName string) (*compute.Operation, error) {
return gce.service.RegionOperations.Get(gce.projectID, region, operationName).Do()
}, mc)
}
func (gce *GCECloud) waitForZoneOp(op *compute.Operation, zone string, mc *metricContext) error {
return gce.waitForOp(op, func(operationName string) (*compute.Operation, error) {
return gce.service.ZoneOperations.Get(gce.projectID, zone, operationName).Do()
}, mc)
}