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

Add success log message after previous checkin failures #1327

Merged
merged 2 commits into from
Sep 28, 2022
Merged

Add success log message after previous checkin failures #1327

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
9dd8209
Add success log message after previous checkin failures
joshdover Sep 27, 2022
75ebe94
Changelog
joshdover Sep 27, 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
1 change: 1 addition & 0 deletions CHANGELOG.next.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,7 @@
- Remove fleet event reporter and events from checkin body. {issue}993[993]
- Fix unintended reset of source URI when downloading components {pull}1252[1252]
- Create separate status reporter for local only events so that degraded fleet-checkins no longer affect health on successful fleet-checkins. {issue}1157[1157] {pull}1285[1285]
- Add success log message after previous checkin failures {pull}1327[1327]

==== New features

Expand Down
16 changes: 11 additions & 5 deletions internal/pkg/agent/application/gateway/fleet/fleet_gateway.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ func (f *fleetGateway) worker() {
f.statusReporter.Update(state.Failed, errMsg, nil)
} else {
f.statusReporter.Update(state.Healthy, "", nil)
f.localReporter.Update(state.Healthy, "", nil) // we don't need to specifically set the local reporter to failed above, but it needs to be reset to healthy if a checking succeeds
f.localReporter.Update(state.Healthy, "", nil) // we don't need to specifically set the local reporter to failed above, but it needs to be reset to healthy if a checkin succeeds
}

case <-f.bgContext.Done():
Expand Down Expand Up @@ -280,11 +280,11 @@ func (f *fleetGateway) doExecute() (*fleetapi.CheckinResponse, error) {
// Guard if the context is stopped by a out of bound call,
// this mean we are rebooting to change the log level or the system is shutting us down.
for f.bgContext.Err() == nil {
f.log.Debugf("Checking started")
f.log.Debugf("Checkin started")
resp, err := f.execute(f.bgContext)
if err != nil {
f.checkinFailCounter++
f.log.Errorf("Could not communicate with fleet-server Checking API will retry, error: %s", err)
f.log.Errorf("Could not communicate with fleet-server checkin API will retry, error: %s", err)
if !f.backoff.Wait() {
// Something bad has happened and we log it and we should update our current state.
err := errors.New(
Expand All @@ -299,10 +299,16 @@ func (f *fleetGateway) doExecute() (*fleetapi.CheckinResponse, error) {
}
if f.checkinFailCounter > 1 {
f.localReporter.Update(state.Degraded, fmt.Sprintf("checkin failed: %v", err), nil)
f.log.Errorf("checking number %d failed: %s", f.checkinFailCounter, err.Error())
f.log.Errorf("checkin number %d failed: %s", f.checkinFailCounter, err.Error())
}
continue
}

if f.checkinFailCounter > 0 {
// Log at same level as error logs above so subsequent successes are visible when log level is set to 'error'.
f.log.Errorf("Checkin request to fleet-server succeeded after %d failures", f.checkinFailCounter)
}

f.checkinFailCounter = 0
// Request was successful, return the collected actions.
return resp, nil
Expand Down Expand Up @@ -338,7 +344,7 @@ func (f *fleetGateway) execute(ctx context.Context) (*fleetapi.CheckinResponse,
f.unauthCounter++

if f.shouldUnenroll() {
f.log.Warnf("retrieved an invalid api key error '%d' times. Starting to unenroll the elastic agent.", f.unauthCounter)
f.log.Warnf("received an invalid api key error '%d' times. Starting to unenroll the elastic agent.", f.unauthCounter)
return &fleetapi.CheckinResponse{
Actions: []fleetapi.Action{&fleetapi.ActionUnenroll{ActionID: "", ActionType: "UNENROLL", IsDetected: true}},
}, nil
Expand Down