Skip to content

fix: race conditions in gcr agent #1332

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

Open
Angith wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: race conditions in gcr agent #1332

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 16 additions & 6 deletions gcr_agent.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ type gcrAgent struct {
snapshot gcrSnapshot
lastProcessStats processStats

mu sync.Mutex
mu sync.RWMutex
spanQueue []Span

runtimeSnapshot *SnapshotCollector
Expand Down Expand Up @@ -133,20 +133,20 @@ func newGCRAgent(
logger: logger,
}

go func() {
go func(a *gcrAgent) {
for {
for i := 0; i < maximumRetries; i++ {
snapshot, ok := agent.collectSnapshot(context.Background())
snapshot, ok := a.collectSnapshot(context.Background())
if ok {
agent.snapshot = snapshot
a.snapshot = snapshot
break
}

time.Sleep(expDelay(i + 1))
}
time.Sleep(snapshotCollectionInterval)
}
}()
}(agent)
go agent.processStats.Run(context.Background(), time.Second)

return agent
Expand Down Expand Up @@ -208,7 +208,11 @@ func (a *gcrAgent) SendMetrics(data acceptor.Metrics) (err error) {
func (a *gcrAgent) SendEvent(event *EventData) error { return nil }

func (a *gcrAgent) SendSpans(spans []Span) error {
from := newServerlessAgentFromS(a.snapshot.Service.EntityID, "gcp")
a.mu.RLock()
entityID := a.snapshot.Service.EntityID
a.mu.RUnlock()

from := newServerlessAgentFromS(entityID, "gcp")
for i := range spans {
spans[i].From = from
}
Expand Down Expand Up @@ -286,6 +290,9 @@ func (a *gcrAgent) collectSnapshot(ctx context.Context) (gcrSnapshot, bool) {
return gcrSnapshot{}, false
}

a.mu.RLock()
defer a.mu.RUnlock()

snapshot := newGCRSnapshot(a.PID, gcrMetadata{
ComputeMetadata: md,
Service: os.Getenv(kService),
Expand All @@ -294,6 +301,9 @@ func (a *gcrAgent) collectSnapshot(ctx context.Context) (gcrSnapshot, bool) {
Port: os.Getenv("PORT"),
})
snapshot.Service.Zone = a.Zone
// Tags remains unchanged after initialization.
// An RLock alone is not enough if Tags ever becomes mutable.
// Update the locking strategy if this behavior changes.
snapshot.Service.Tags = a.Tags

a.logger.Debug("collected snapshot")
Expand Down