philipp/uncloud
1
0
Fork 0
mirror of https://github.com/psviderski/uncloud.git synced 2026-08-26 11:03:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support compose stop_grace_period to change timeout before sending SIGKILL

Browse Source
This commit is contained in:
Pasha Sviderski
2026-03-04 14:07:22 +10:00
parent 1f328e99d5
commit d9934b9dba
7 changed files with 125 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pkg/api/service.go
+5 -2
View File
@@ -55,6 +55,8 @@ type ServiceSpec struct {
// Caddy is the optional Caddy reverse proxy configuration for the service.
// Caddy and Ports cannot be specified simultaneously.
Caddy *CaddySpec `json:",omitempty"`
// Configs is list of configuration objects that can be mounted into the container.
Configs []ConfigSpec
// Container defines the desired state of each container in the service.
Container ContainerSpec
// Mode is the replication mode of the service. Default is ServiceModeReplicated if empty.
@@ -67,12 +69,13 @@ type ServiceSpec struct {
Ports []PortSpec
// Replicas is the number of containers to run for the service. Only valid for a replicated service.
Replicas uint `json:",omitempty"`
// StopGracePeriod is how long to wait after SIGTERM before sending SIGKILL when stopping a container.
// Default is 10 seconds if not specified.
StopGracePeriod *time.Duration `json:",omitempty"`
// UpdateConfig configures how the service is updated during a deployment.
UpdateConfig UpdateConfig `json:",omitempty"`
// Volumes is list of data volumes that can be mounted into the container.
Volumes []VolumeSpec
// Configs is list of configuration objects that can be mounted into the container.
Configs []ConfigSpec
}
// CaddyConfig returns the Caddy reverse proxy configuration for the service or an empty string if it's not defined.
pkg/client/compose/service.go
+5
View File
@@ -85,6 +85,11 @@ func ServiceSpecFromCompose(project *types.Project, serviceName string) (api.Ser
}
}
if service.StopGracePeriod != nil {
d := time.Duration(*service.StopGracePeriod)
spec.StopGracePeriod = &d
}
if service.Scale != nil {
spec.Replicas = uint(*service.Scale)
}
pkg/client/compose/service_test.go
+2 -1
View File
@@ -205,7 +205,8 @@ func TestServiceSpecFromCompose(t *testing.T) {
Placement: api.Placement{
Machines: []string{"machine-1", "machine-2"},
},
Replicas: 3,
Replicas: 3,
StopGracePeriod: api.AsPtr(30 * time.Second),
UpdateConfig: api.UpdateConfig{
Order: api.UpdateOrderStopFirst,
MonitorPeriod: &api.DefaultHealthMonitorPeriod,
pkg/client/compose/testdata/compose-full-spec.yaml
Vendored
+1
View File
@@ -37,6 +37,7 @@ services:
privileged: true
pull_policy: always
scale: 3
stop_grace_period: 30s
sysctls:
- net.ipv4.ip_forward=1
ulimits:
pkg/client/deploy/operation/container.go
+28 -12
View File
@@ -3,6 +3,7 @@ package operation
import (
"context"
"fmt"
"time"
"github.com/docker/compose/v2/pkg/progress"
"github.com/docker/docker/api/types/container"
@@ -53,13 +54,14 @@ func (o *RunContainerOperation) String() string {
// StopContainerOperation stops a container on a specific machine.
type StopContainerOperation struct {
ServiceID string
ContainerID string
MachineID string
ServiceID string
ContainerID string
MachineID string
StopGracePeriod *time.Duration
}
func (o *StopContainerOperation) Execute(ctx context.Context, cli Client) error {
if err := cli.StopContainer(ctx, o.ServiceID, o.ContainerID, container.StopOptions{}); err != nil {
if err := cli.StopContainer(ctx, o.ServiceID, o.ContainerID, stopOptions(o.StopGracePeriod)); err != nil {
return fmt.Errorf("stop container: %w", err)
}
return nil
@@ -78,15 +80,18 @@ func (o *StopContainerOperation) String() string {
// RemoveContainerOperation stops and removes a container from a specific machine.
type RemoveContainerOperation struct {
MachineID string
Container api.ServiceContainer
MachineID string
Container api.ServiceContainer
StopGracePeriod *time.Duration
}
func (o *RemoveContainerOperation) Execute(ctx context.Context, cli Client) error {
if err := cli.StopContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.StopOptions{}); err != nil {
err := cli.StopContainer(ctx, o.Container.ServiceID(), o.Container.ID, stopOptions(o.StopGracePeriod))
if err != nil {
return fmt.Errorf("stop container: %w", err)
}
if err := cli.RemoveContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.RemoveOptions{
if err = cli.RemoveContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.RemoveOptions{
// Remove anonymous volumes created by the container.
RemoveVolumes: true,
}); err != nil {
@@ -119,6 +124,7 @@ type ReplaceContainerOperation struct {
Order string
// SkipHealthMonitor skips the monitoring period and health checks after starting a new container.
SkipHealthMonitor bool
StopGracePeriod *time.Duration
}
func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) error {
@@ -133,7 +139,8 @@ func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) err
}
wasRunning = ctr.Container.State.Running
if wasRunning {
if err = cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, container.StopOptions{}); err != nil {
err = cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, stopOptions(o.StopGracePeriod))
if err != nil {
return fmt.Errorf("stop old container: %w", err)
}
}
@@ -156,7 +163,7 @@ func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) err
// Use context without progress to not overwrite the container Unhealthy status with Stopped.
ctxWithoutProgress := progress.WithContextWriter(ctx, nil)
_ = cli.StopContainer(ctxWithoutProgress, o.ServiceID, resp.ID, container.StopOptions{})
_ = cli.StopContainer(ctxWithoutProgress, o.ServiceID, resp.ID, stopOptions(o.StopGracePeriod))
newCtr := fmt.Sprintf("%s/%s", o.Spec.Name, stringid.TruncateID(resp.ID))
healthErr := fmt.Errorf(
@@ -186,12 +193,12 @@ func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) err
// There still might be a brief downtime (for a 1 replica service) when Caddy doesn't know about
// the new container but we're stopping the old container. We should somehow ensure Caddy is updated
// with the new container before we stop the old one to avoid this downtime.
if err := cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, container.StopOptions{}); err != nil {
if err = cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, stopOptions(o.StopGracePeriod)); err != nil {
return fmt.Errorf("stop old container: %w", err)
}
}
if err := cli.RemoveContainer(ctx, o.ServiceID, o.OldContainer.ID, container.RemoveOptions{
if err = cli.RemoveContainer(ctx, o.ServiceID, o.OldContainer.ID, container.RemoveOptions{
RemoveVolumes: true,
}); err != nil {
return fmt.Errorf("remove old container: %w", err)
@@ -209,3 +216,12 @@ func (o *ReplaceContainerOperation) String() string {
return fmt.Sprintf("ReplaceContainerOperation[machine_id=%s service_id=%s old_container_id=%s order=%s]",
o.MachineID, o.ServiceID, o.OldContainer.ID, o.Order)
}
// stopOptions converts a stop grace period duration to Docker container stop options.
func stopOptions(gracePeriod *time.Duration) container.StopOptions {
if gracePeriod == nil {
return container.StopOptions{}
}
t := int(gracePeriod.Seconds())
return container.StopOptions{Timeout: &t}
}
pkg/client/deploy/strategy.go
+21 -13
View File
@@ -175,6 +175,7 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
OldContainer: ctr,
Order: order,
SkipHealthMonitor: s.SkipHealthMonitor,
StopGracePeriod: spec.StopGracePeriod,
})
}
@@ -182,8 +183,9 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
for mid, containers := range containersOnMachine {
for _, c := range containers {
plan.Operations = append(plan.Operations, &operation.RemoveContainerOperation{
MachineID: mid,
Container: c,
MachineID: mid,
Container: c,
StopGracePeriod: spec.StopGracePeriod,
})
}
}
@@ -234,8 +236,9 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
for _, containers := range containersOnMachine {
for _, c := range containers {
plan.Operations = append(plan.Operations, &operation.RemoveContainerOperation{
MachineID: c.MachineID,
Container: c.Container,
MachineID: c.MachineID,
Container: c.Container,
StopGracePeriod: spec.StopGracePeriod,
})
}
}
@@ -286,8 +289,9 @@ func reconcileGlobalContainer(
continue
}
ops = append(ops, &operation.RemoveContainerOperation{
MachineID: old.MachineID,
Container: old.Container,
MachineID: old.MachineID,
Container: old.Container,
StopGracePeriod: spec.StopGracePeriod,
})
}
break
@@ -319,9 +323,10 @@ func reconcileGlobalContainer(
conflictingPorts, err := c.Container.ConflictingServicePorts(spec.Ports)
if err != nil || len(conflictingPorts) > 0 {
ops = append(ops, &operation.StopContainerOperation{
ServiceID: serviceID,
ContainerID: c.Container.ID,
MachineID: machineID,
ServiceID: serviceID,
ContainerID: c.Container.ID,
MachineID: machineID,
StopGracePeriod: spec.StopGracePeriod,
})
}
}
@@ -335,6 +340,7 @@ func reconcileGlobalContainer(
OldContainer: containerToReplace.Container,
Order: order,
SkipHealthMonitor: skipHealthCheck,
StopGracePeriod: spec.StopGracePeriod,
})
// Remove any other containers (there shouldn't be any in normal operation).
@@ -343,8 +349,9 @@ func reconcileGlobalContainer(
continue
}
ops = append(ops, &operation.RemoveContainerOperation{
MachineID: c.MachineID,
Container: c.Container,
MachineID: c.MachineID,
Container: c.Container,
StopGracePeriod: spec.StopGracePeriod,
})
}
} else {
@@ -357,8 +364,9 @@ func reconcileGlobalContainer(
})
for _, c := range containers {
ops = append(ops, &operation.RemoveContainerOperation{
MachineID: c.MachineID,
Container: c.Container,
MachineID: c.MachineID,
Container: c.Container,
StopGracePeriod: spec.StopGracePeriod,
})
}
}
website/docs/8-compose-file-reference/1-support-matrix.md
+63 -62
View File
@@ -3,68 +3,69 @@
Uncloud supports a subset of the [Compose specification](https://compose-spec.io/) with some extensions and limitations.
The following table shows the support status for main Compose features:
| Feature | Support Status | Notes |
|--------------------|--------------------|----------------------------------------------------------------------------------------------------------------|
| **Services** | | |
| `build` | ✅ Supported | Build context and Dockerfile |
| `cap_add` | ✅ Supported | Additional kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) |
| `cap_drop` | ✅ Supported | Which kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) to drop |
| `command` | ✅ Supported | Override container command |
| `configs` | ✅ Supported | File-based and inline configs |
| `cpus` | ✅ Supported | CPU limit |
| `depends_on` | ⚠️ Limited | Services deployed in order but conditions not checked |
| `devices` | ✅ Supported | Device mappings |
| `dns` | ❌ Not supported | Built-in service discovery |
| `dns_search` | ❌ Not supported | Built-in service discovery |
| `entrypoint` | ✅ Supported | Override container entrypoint |
| `env_file` | ✅ Supported | Environment file |
| `environment` | ✅ Supported | Environment variables |
| `gpus` | ✅ Supported | GPU device access |
| `healthcheck` | ✅ Supported | Health check configuration |
| `image` | ✅ Supported | Container image specification |
| `init` | ✅ Supported | Run init process in container |
| `labels` | ❌ Not supported | |
| `links` | ❌ Not supported | Use service names for communication |
| `logging` | ✅ Supported | Defaults to [local](https://docs.docker.com/engine/logging/drivers/local/) log driver |
| `mem_limit` | ✅ Supported | Memory limit |
| `mem_reservation` | ✅ Supported | Memory reservation |
| `mem_swappiness` | ❌ Not supported | |
| `memswap_limit` | ❌ Not supported | |
| `networks` | ❌ Not supported | All containers share cluster network |
| `ports` | ⚠️ Limited | `mode: host` only, use [`x-ports`](#x-ports) for HTTP/HTTPS |
| `privileged` | ✅ Supported | Run containers in privileged mode |
| `pull_policy` | ✅ Supported | `always`, `missing`, `never` |
| `secrets` | ❌ Not supported | Use configs or environment variables |
| `security_opt` | ❌ Not supported | |
| `storage_opt` | ❌ Not supported | |
| `sysctls` | ✅ Supported | Namespaced kernel parameters |
| `user` | ✅ Supported | Set container user |
| `volumes` | ✅ Supported | Named volumes, bind mounts, tmpfs |
| **Deploy** | | |
| `labels` | ❌ Not supported | |
| `mode` | ✅ Supported | Either `global` or `replicated` |
| `placement` | ❌ Not supported | Use [`x-machines`](#x-machines) extension |
| `replicas` | ✅ Supported | Number of container replicas |
| `resources` | ⚠️ Limited | CPU, memory limits and device reservations |
| `restart_policy` | ❌ Not supported | Defaults to `unless-stopped` |
| `rollback_config` | ❌ Not supported | See [#151](https://github.com/psviderski/uncloud/issues/151) |
| `update_config` | ⚠️ Limited | `order` and `monitor` supported. See [rolling deployments](../4-guides/1-deployments/4-rolling-deployments.md) |
| **Volumes** | | |
| Named volumes | ✅ Supported | Docker volumes |
| Bind mounts | ✅ Supported | Host path binding |
| Tmpfs mounts | ✅ Supported | In-memory filesystems |
| Volume labels | ✅ Supported | Custom labels |
| External volumes | ✅ Supported | Must exist before deployment |
| Volume drivers | ⚠️ Limited | Local driver only |
| **Configs** | | |
| File-based configs | ✅ Supported | Read from file |
| Inline configs | ✅ Supported | Defined in compose file |
| External configs | ❌ Not supported | Not supported |
| Short syntax | ❌ Not supported | Use long syntax only |
| **Extensions** | | |
| `x-caddy` | ✅ Uncloud-specific | Custom Caddy configuration |
| `x-machines` | ✅ Uncloud-specific | Machine placement constraints |
| `x-ports` | ✅ Uncloud-specific | Service port publishing |
| Feature | Support Status | Notes |
|---------------------|--------------------|----------------------------------------------------------------------------------------------------------------|
| **Services** | | |
| `build` | ✅ Supported | Build context and Dockerfile |
| `cap_add` | ✅ Supported | Additional kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) |
| `cap_drop` | ✅ Supported | Which kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) to drop |
| `command` | ✅ Supported | Override container command |
| `configs` | ✅ Supported | File-based and inline configs |
| `cpus` | ✅ Supported | CPU limit |
| `depends_on` | ⚠️ Limited | Services deployed in order but conditions not checked |
| `devices` | ✅ Supported | Device mappings |
| `dns` | ❌ Not supported | Built-in service discovery |
| `dns_search` | ❌ Not supported | Built-in service discovery |
| `entrypoint` | ✅ Supported | Override container entrypoint |
| `env_file` | ✅ Supported | Environment file |
| `environment` | ✅ Supported | Environment variables |
| `gpus` | ✅ Supported | GPU device access |
| `healthcheck` | ✅ Supported | Health check configuration |
| `image` | ✅ Supported | Container image specification |
| `init` | ✅ Supported | Run init process in container |
| `labels` | ❌ Not supported | |
| `links` | ❌ Not supported | Use service names for communication |
| `logging` | ✅ Supported | Defaults to [local](https://docs.docker.com/engine/logging/drivers/local/) log driver |
| `mem_limit` | ✅ Supported | Memory limit |
| `mem_reservation` | ✅ Supported | Memory reservation |
| `mem_swappiness` | ❌ Not supported | |
| `memswap_limit` | ❌ Not supported | |
| `networks` | ❌ Not supported | All containers share cluster network |
| `ports` | ⚠️ Limited | `mode: host` only, use [`x-ports`](#x-ports) for HTTP/HTTPS |
| `privileged` | ✅ Supported | Run containers in privileged mode |
| `pull_policy` | ✅ Supported | `always`, `missing`, `never` |
| `secrets` | ❌ Not supported | Use configs or environment variables |
| `security_opt` | ❌ Not supported | |
| `stop_grace_period` | ✅ Supported | Time to wait after SIGTERM before SIGKILL |
| `storage_opt` | ❌ Not supported | |
| `sysctls` | ✅ Supported | Namespaced kernel parameters |
| `user` | ✅ Supported | Set container user |
| `volumes` | ✅ Supported | Named volumes, bind mounts, tmpfs |
| **Deploy** | | |
| `labels` | ❌ Not supported | |
| `mode` | ✅ Supported | Either `global` or `replicated` |
| `placement` | ❌ Not supported | Use [`x-machines`](#x-machines) extension |
| `replicas` | ✅ Supported | Number of container replicas |
| `resources` | ⚠️ Limited | CPU, memory limits and device reservations |
| `restart_policy` | ❌ Not supported | Defaults to `unless-stopped` |
| `rollback_config` | ❌ Not supported | See [#151](https://github.com/psviderski/uncloud/issues/151) |
| `update_config` | ⚠️ Limited | `order` and `monitor` supported. See [rolling deployments](../4-guides/1-deployments/4-rolling-deployments.md) |
| **Volumes** | | |
| Named volumes | ✅ Supported | Docker volumes |
| Bind mounts | ✅ Supported | Host path binding |
| Tmpfs mounts | ✅ Supported | In-memory filesystems |
| Volume labels | ✅ Supported | Custom labels |
| External volumes | ✅ Supported | Must exist before deployment |
| Volume drivers | ⚠️ Limited | Local driver only |
| **Configs** | | |
| File-based configs | ✅ Supported | Read from file |
| Inline configs | ✅ Supported | Defined in compose file |
| External configs | ❌ Not supported | Not supported |
| Short syntax | ❌ Not supported | Use long syntax only |
| **Extensions** | | |
| `x-caddy` | ✅ Uncloud-specific | Custom Caddy configuration |
| `x-machines` | ✅ Uncloud-specific | Machine placement constraints |
| `x-ports` | ✅ Uncloud-specific | Service port publishing |
### Legend