Add DNSRegistrar that creates/updates/deletes A records in MCNS during deploy and stop. When a service has routes, the agent ensures an A record exists in the configured zone pointing to the node's address. On stop, the record is removed. - Add MCNSConfig to agent config (server_url, ca_cert, token_path, zone, node_addr) with defaults and env overrides - Add DNSRegistrar (internal/agent/dns.go): REST client for MCNS record CRUD, nil-receiver safe - Wire into deploy flow (EnsureRecord after route registration) - Wire into stop flow (RemoveRecord before container stop) - 7 new tests, make all passes with 0 issues Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
175 lines
5.7 KiB
Go
175 lines
5.7 KiB
Go
package agent
|
|
|
|
import (
|
|
"context"
|
|
"database/sql"
|
|
"fmt"
|
|
|
|
mcpv1 "git.wntrmute.dev/mc/mcp/gen/mcp/v1"
|
|
"git.wntrmute.dev/mc/mcp/internal/registry"
|
|
"git.wntrmute.dev/mc/mcp/internal/runtime"
|
|
"google.golang.org/grpc/codes"
|
|
"google.golang.org/grpc/status"
|
|
)
|
|
|
|
// StopService stops all components of a service.
|
|
func (a *Agent) StopService(ctx context.Context, req *mcpv1.StopServiceRequest) (*mcpv1.StopServiceResponse, error) {
|
|
a.Logger.Info("StopService", "service", req.GetName())
|
|
|
|
if req.GetName() == "" {
|
|
return nil, status.Error(codes.InvalidArgument, "service name is required")
|
|
}
|
|
|
|
components, err := registry.ListComponents(a.DB, req.GetName())
|
|
if err != nil {
|
|
return nil, status.Errorf(codes.Internal, "list components: %v", err)
|
|
}
|
|
|
|
var results []*mcpv1.ComponentResult
|
|
for _, c := range components {
|
|
containerName := ContainerNameFor(req.GetName(), c.Name)
|
|
r := &mcpv1.ComponentResult{Name: c.Name, Success: true}
|
|
|
|
// Remove routes from mc-proxy before stopping the container.
|
|
if len(c.Routes) > 0 && a.Proxy != nil {
|
|
if err := a.Proxy.RemoveRoutes(ctx, req.GetName(), c.Routes); err != nil {
|
|
a.Logger.Warn("failed to remove routes", "service", req.GetName(), "component", c.Name, "err", err)
|
|
}
|
|
}
|
|
|
|
// Remove DNS record when stopping the service.
|
|
if len(c.Routes) > 0 && a.DNS != nil {
|
|
if err := a.DNS.RemoveRecord(ctx, req.GetName()); err != nil {
|
|
a.Logger.Warn("failed to remove DNS record", "service", req.GetName(), "err", err)
|
|
}
|
|
}
|
|
|
|
if err := a.Runtime.Stop(ctx, containerName); err != nil {
|
|
a.Logger.Info("stop container (ignored)", "container", containerName, "error", err)
|
|
}
|
|
|
|
if err := registry.UpdateComponentState(a.DB, req.GetName(), c.Name, "stopped", "stopped"); err != nil {
|
|
r.Success = false
|
|
r.Error = fmt.Sprintf("update state: %v", err)
|
|
}
|
|
|
|
results = append(results, r)
|
|
}
|
|
|
|
return &mcpv1.StopServiceResponse{Results: results}, nil
|
|
}
|
|
|
|
// StartService starts all components of a service. If a container already
|
|
// exists but is stopped, it is removed first so a fresh one can be created.
|
|
func (a *Agent) StartService(ctx context.Context, req *mcpv1.StartServiceRequest) (*mcpv1.StartServiceResponse, error) {
|
|
a.Logger.Info("StartService", "service", req.GetName())
|
|
|
|
if req.GetName() == "" {
|
|
return nil, status.Error(codes.InvalidArgument, "service name is required")
|
|
}
|
|
|
|
components, err := registry.ListComponents(a.DB, req.GetName())
|
|
if err != nil {
|
|
return nil, status.Errorf(codes.Internal, "list components: %v", err)
|
|
}
|
|
|
|
var results []*mcpv1.ComponentResult
|
|
for _, c := range components {
|
|
r := startComponent(ctx, a, req.GetName(), &c)
|
|
results = append(results, r)
|
|
}
|
|
|
|
return &mcpv1.StartServiceResponse{Results: results}, nil
|
|
}
|
|
|
|
// RestartService restarts all components of a service by stopping, removing,
|
|
// and re-creating each container. The desired_state is not changed.
|
|
func (a *Agent) RestartService(ctx context.Context, req *mcpv1.RestartServiceRequest) (*mcpv1.RestartServiceResponse, error) {
|
|
a.Logger.Info("RestartService", "service", req.GetName())
|
|
|
|
if req.GetName() == "" {
|
|
return nil, status.Error(codes.InvalidArgument, "service name is required")
|
|
}
|
|
|
|
components, err := registry.ListComponents(a.DB, req.GetName())
|
|
if err != nil {
|
|
return nil, status.Errorf(codes.Internal, "list components: %v", err)
|
|
}
|
|
|
|
var results []*mcpv1.ComponentResult
|
|
for _, c := range components {
|
|
r := restartComponent(ctx, a, req.GetName(), &c)
|
|
results = append(results, r)
|
|
}
|
|
|
|
return &mcpv1.RestartServiceResponse{Results: results}, nil
|
|
}
|
|
|
|
// startComponent removes any existing container and runs a fresh one from
|
|
// the registry spec, then updates state to running.
|
|
func startComponent(ctx context.Context, a *Agent, service string, c *registry.Component) *mcpv1.ComponentResult {
|
|
containerName := ContainerNameFor(service, c.Name)
|
|
r := &mcpv1.ComponentResult{Name: c.Name, Success: true}
|
|
|
|
// Remove any pre-existing container; ignore errors for non-existent ones.
|
|
_ = a.Runtime.Stop(ctx, containerName)
|
|
_ = a.Runtime.Remove(ctx, containerName)
|
|
|
|
spec := componentToSpec(service, c)
|
|
if err := a.Runtime.Run(ctx, spec); err != nil {
|
|
r.Success = false
|
|
r.Error = fmt.Sprintf("run container: %v", err)
|
|
return r
|
|
}
|
|
|
|
if err := registry.UpdateComponentState(a.DB, service, c.Name, "running", "running"); err != nil {
|
|
r.Success = false
|
|
r.Error = fmt.Sprintf("update state: %v", err)
|
|
}
|
|
return r
|
|
}
|
|
|
|
// restartComponent stops, removes, and re-creates a container without
|
|
// changing the desired_state in the registry.
|
|
func restartComponent(ctx context.Context, a *Agent, service string, c *registry.Component) *mcpv1.ComponentResult {
|
|
containerName := ContainerNameFor(service, c.Name)
|
|
r := &mcpv1.ComponentResult{Name: c.Name, Success: true}
|
|
|
|
_ = a.Runtime.Stop(ctx, containerName)
|
|
_ = a.Runtime.Remove(ctx, containerName)
|
|
|
|
spec := componentToSpec(service, c)
|
|
if err := a.Runtime.Run(ctx, spec); err != nil {
|
|
r.Success = false
|
|
r.Error = fmt.Sprintf("run container: %v", err)
|
|
_ = registry.UpdateComponentState(a.DB, service, c.Name, "", "stopped")
|
|
return r
|
|
}
|
|
|
|
if err := registry.UpdateComponentState(a.DB, service, c.Name, "", "running"); err != nil {
|
|
r.Success = false
|
|
r.Error = fmt.Sprintf("update state: %v", err)
|
|
}
|
|
return r
|
|
}
|
|
|
|
// componentToSpec builds a runtime.ContainerSpec from a registry Component.
|
|
func componentToSpec(service string, c *registry.Component) runtime.ContainerSpec {
|
|
return runtime.ContainerSpec{
|
|
Name: ContainerNameFor(service, c.Name),
|
|
Image: c.Image,
|
|
Network: c.Network,
|
|
User: c.UserSpec,
|
|
Restart: c.Restart,
|
|
Ports: c.Ports,
|
|
Volumes: c.Volumes,
|
|
Cmd: c.Cmd,
|
|
}
|
|
}
|
|
|
|
// componentExists checks whether a component already exists in the registry.
|
|
func componentExists(db *sql.DB, service, name string) bool {
|
|
_, err := registry.GetComponent(db, service, name)
|
|
return err == nil
|
|
}
|