Skip to content

add snapshot service keepalive #213

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
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
Open

add snapshot service keepalive #213

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
20 changes: 16 additions & 4 deletions cmd/core_plugin/snapshot/snapshot_linux.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,8 @@ import (
"path/filepath"
"time"

"google.golang.org/grpc/keepalive"

"github.com/GoogleCloudPlatform/galog"
"google.golang.org/grpc"
"google.golang.org/grpc/credentials/insecure"
Expand Down Expand Up @@ -89,7 +91,7 @@ func NewModule(context.Context) *manager.Module {

// moduleSetup runs the actual snapshot handler for linux.
func moduleSetup(ctx context.Context, _ any) error {
galog.Debugf("Initializing linux snapshot module.")
galog.Infof("Initializing linux snapshot module.")
config := cfg.Retrieve().Snapshots

opts := clientOptions{
Expand All @@ -103,13 +105,14 @@ func moduleSetup(ctx context.Context, _ any) error {
if err != nil {
return fmt.Errorf("failed to create snapshot handler: %w", err)
}
galog.Infof("Created snapshot handler.")

// If we don't trigger a new go routine here the snapshot service will block
// the module manager as it Wait()s for all modules to finish their work - and
// this module will keep running forever.
go func() { handler.run(ctx) }()

galog.Debugf("Finished initializing linux snapshot module.")
galog.Infof("Finished creating snapshot handler.")
return nil
}

Expand Down Expand Up @@ -142,6 +145,7 @@ func (s *snapshotClient) run(ctx context.Context) error {
}

if err := s.listen(ctx); err != nil {
galog.Infof("Failed to listen for snapshot requests: %v.", err)
return fmt.Errorf("failed to listen for snapshot requests: %w", err)
}

Expand All @@ -153,10 +157,16 @@ func (s *snapshotClient) listen(ctx context.Context) error {
galog.Infof("Starting to listen for snapshot requests.")

for context.Cause(ctx) == nil {
galog.Debugf("Attempting to connect to snapshot service at %q via %q.", s.options.address, s.options.protocol)
galog.Infof("Attempting to connect to snapshot service at %q via %q.", s.options.address, s.options.protocol)

creds := grpc.WithTransportCredentials(insecure.NewCredentials())
conn, err := grpc.NewClient(s.options.fullAddress(), creds)
keepAlive := grpc.WithKeepaliveParams(keepalive.ClientParameters{
Time: 1 * time.Minute,
Timeout: 20 * time.Second,
PermitWithoutStream: true,
})

conn, err := grpc.NewClient(s.options.fullAddress(), creds, keepAlive)
if err != nil {
return fmt.Errorf("failed to connect to snapshot service: %w", err)
}
Expand All @@ -182,7 +192,9 @@ func (s *snapshotClient) listen(ctx context.Context) error {
}

for {
galog.Infof("Waiting for snapshot request from snapshot service.")
request, err := r.Recv()
galog.Infof("Received snapshot service.")
if err != nil {
galog.Errorf("Error reading snapshot request: %v.", err)
break
Expand Down