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

Cherry-pick #21258 to 7.9: o365input: Restart after fatal error #21386

Merged
merged 2 commits into from
Sep 30, 2020
Merged

Cherry-pick #21258 to 7.9: o365input: Restart after fatal error #21386

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
b1a7e90
o365input: Restart after fatal error (#21258)
adriansr Sep 29, 2020
d26a50f
Fix changelog
adriansr Sep 29, 2020
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 @@ -50,6 +50,7 @@ https://github.com/elastic/beats/compare/v7.0.0-alpha2...master[Check the HEAD d
- Fix `setup.dashboards.index` setting not working. {pull}17749[17749]
- Fix Elasticsearch license endpoint URL referenced in error message. {issue}17880[17880] {pull}18030[18030]
- Change `decode_json_fields` processor, to merge parsed json objects with existing objects in the event instead of fully replacing them. {pull}17958[17958]
- The `o365input` and `o365` module now recover from an authentication problem or other fatal errors, instead of terminating. {pull}21258[21258]

*Auditbeat*

Expand Down
44 changes: 32 additions & 12 deletions x-pack/filebeat/input/o365audit/input.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,9 @@ import (
const (
pluginName = "o365audit"
fieldsPrefix = pluginName

// How long to retry when a fatal error is encountered in the input.
failureRetryInterval = time.Minute * 5
)

type o365input struct {
Expand Down Expand Up @@ -107,6 +110,34 @@ func (inp *o365input) Run(
src cursor.Source,
cursor cursor.Cursor,
publisher cursor.Publisher,
) error {
for ctx.Cancelation.Err() == nil {
err := inp.runOnce(ctx, src, cursor, publisher)
if err == nil {
break
}
if ctx.Cancelation.Err() != err && err != context.Canceled {
msg := common.MapStr{}
msg.Put("error.message", err.Error())
msg.Put("event.kind", "pipeline_error")
event := beat.Event{
Timestamp: time.Now(),
Fields: msg,
}
publisher.Publish(event, nil)
ctx.Logger.Errorf("Input failed: %v", err)
ctx.Logger.Infof("Restarting in %v", failureRetryInterval)
time.Sleep(failureRetryInterval)
}
}
return nil
}

func (inp *o365input) runOnce(
ctx v2.Context,
src cursor.Source,
cursor cursor.Cursor,
publisher cursor.Publisher,
) error {
stream := src.(*stream)
tenantID, contentType := stream.tenantID, stream.contentType
Expand Down Expand Up @@ -156,18 +187,7 @@ func (inp *o365input) Run(
}

log.Infow("Start fetching events", "cursor", start)
err = poller.Run(action)
if err != nil && ctx.Cancelation.Err() != err && err != context.Canceled {
msg := common.MapStr{}
msg.Put("error.message", err.Error())
msg.Put("event.kind", "pipeline_error")
event := beat.Event{
Timestamp: time.Now(),
Fields: msg,
}
publisher.Publish(event, nil)
}
return err
return poller.Run(action)
}

func initCheckpoint(log *logp.Logger, c cursor.Cursor, maxRetention time.Duration) checkpoint {
Expand Down