mirror of
https://github.com/moby/moby.git
synced 2022-11-09 12:21:53 -05:00
b6c7becbfe
This PR adds support for user-defined health-check probes for Docker containers. It adds a `HEALTHCHECK` instruction to the Dockerfile syntax plus some corresponding "docker run" options. It can be used with a restart policy to automatically restart a container if the check fails. The `HEALTHCHECK` instruction has two forms: * `HEALTHCHECK [OPTIONS] CMD command` (check container health by running a command inside the container) * `HEALTHCHECK NONE` (disable any healthcheck inherited from the base image) The `HEALTHCHECK` instruction tells Docker how to test a container to check that it is still working. This can detect cases such as a web server that is stuck in an infinite loop and unable to handle new connections, even though the server process is still running. When a container has a healthcheck specified, it has a _health status_ in addition to its normal status. This status is initially `starting`. Whenever a health check passes, it becomes `healthy` (whatever state it was previously in). After a certain number of consecutive failures, it becomes `unhealthy`. The options that can appear before `CMD` are: * `--interval=DURATION` (default: `30s`) * `--timeout=DURATION` (default: `30s`) * `--retries=N` (default: `1`) The health check will first run **interval** seconds after the container is started, and then again **interval** seconds after each previous check completes. If a single run of the check takes longer than **timeout** seconds then the check is considered to have failed. It takes **retries** consecutive failures of the health check for the container to be considered `unhealthy`. There can only be one `HEALTHCHECK` instruction in a Dockerfile. If you list more than one then only the last `HEALTHCHECK` will take effect. The command after the `CMD` keyword can be either a shell command (e.g. `HEALTHCHECK CMD /bin/check-running`) or an _exec_ array (as with other Dockerfile commands; see e.g. `ENTRYPOINT` for details). The command's exit status indicates the health status of the container. The possible values are: - 0: success - the container is healthy and ready for use - 1: unhealthy - the container is not working correctly - 2: starting - the container is not ready for use yet, but is working correctly If the probe returns 2 ("starting") when the container has already moved out of the "starting" state then it is treated as "unhealthy" instead. For example, to check every five minutes or so that a web-server is able to serve the site's main page within three seconds: HEALTHCHECK --interval=5m --timeout=3s \ CMD curl -f http://localhost/ || exit 1 To help debug failing probes, any output text (UTF-8 encoded) that the command writes on stdout or stderr will be stored in the health status and can be queried with `docker inspect`. Such output should be kept short (only the first 4096 bytes are stored currently). When the health status of a container changes, a `health_status` event is generated with the new status. The health status is also displayed in the `docker ps` output. Signed-off-by: Thomas Leonard <thomas.leonard@docker.com> Signed-off-by: Sebastiaan van Stijn <github@gone.nl>
248 lines
8.1 KiB
Go
248 lines
8.1 KiB
Go
package daemon
|
|
|
|
import (
|
|
"fmt"
|
|
"time"
|
|
|
|
"github.com/docker/docker/api/types/backend"
|
|
"github.com/docker/docker/container"
|
|
"github.com/docker/docker/daemon/network"
|
|
"github.com/docker/engine-api/types"
|
|
networktypes "github.com/docker/engine-api/types/network"
|
|
"github.com/docker/engine-api/types/versions"
|
|
"github.com/docker/engine-api/types/versions/v1p20"
|
|
)
|
|
|
|
// ContainerInspect returns low-level information about a
|
|
// container. Returns an error if the container cannot be found, or if
|
|
// there is an error getting the data.
|
|
func (daemon *Daemon) ContainerInspect(name string, size bool, version string) (interface{}, error) {
|
|
switch {
|
|
case versions.LessThan(version, "1.20"):
|
|
return daemon.containerInspectPre120(name)
|
|
case versions.Equal(version, "1.20"):
|
|
return daemon.containerInspect120(name)
|
|
}
|
|
return daemon.containerInspectCurrent(name, size)
|
|
}
|
|
|
|
func (daemon *Daemon) containerInspectCurrent(name string, size bool) (*types.ContainerJSON, error) {
|
|
container, err := daemon.GetContainer(name)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
container.Lock()
|
|
defer container.Unlock()
|
|
|
|
base, err := daemon.getInspectData(container, size)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
mountPoints := addMountPoints(container)
|
|
networkSettings := &types.NetworkSettings{
|
|
NetworkSettingsBase: types.NetworkSettingsBase{
|
|
Bridge: container.NetworkSettings.Bridge,
|
|
SandboxID: container.NetworkSettings.SandboxID,
|
|
HairpinMode: container.NetworkSettings.HairpinMode,
|
|
LinkLocalIPv6Address: container.NetworkSettings.LinkLocalIPv6Address,
|
|
LinkLocalIPv6PrefixLen: container.NetworkSettings.LinkLocalIPv6PrefixLen,
|
|
Ports: container.NetworkSettings.Ports,
|
|
SandboxKey: container.NetworkSettings.SandboxKey,
|
|
SecondaryIPAddresses: container.NetworkSettings.SecondaryIPAddresses,
|
|
SecondaryIPv6Addresses: container.NetworkSettings.SecondaryIPv6Addresses,
|
|
},
|
|
DefaultNetworkSettings: daemon.getDefaultNetworkSettings(container.NetworkSettings.Networks),
|
|
Networks: container.NetworkSettings.Networks,
|
|
}
|
|
|
|
return &types.ContainerJSON{
|
|
ContainerJSONBase: base,
|
|
Mounts: mountPoints,
|
|
Config: container.Config,
|
|
NetworkSettings: networkSettings,
|
|
}, nil
|
|
}
|
|
|
|
// containerInspect120 serializes the master version of a container into a json type.
|
|
func (daemon *Daemon) containerInspect120(name string) (*v1p20.ContainerJSON, error) {
|
|
container, err := daemon.GetContainer(name)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
container.Lock()
|
|
defer container.Unlock()
|
|
|
|
base, err := daemon.getInspectData(container, false)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
mountPoints := addMountPoints(container)
|
|
config := &v1p20.ContainerConfig{
|
|
Config: container.Config,
|
|
MacAddress: container.Config.MacAddress,
|
|
NetworkDisabled: container.Config.NetworkDisabled,
|
|
ExposedPorts: container.Config.ExposedPorts,
|
|
VolumeDriver: container.HostConfig.VolumeDriver,
|
|
}
|
|
networkSettings := daemon.getBackwardsCompatibleNetworkSettings(container.NetworkSettings)
|
|
|
|
return &v1p20.ContainerJSON{
|
|
ContainerJSONBase: base,
|
|
Mounts: mountPoints,
|
|
Config: config,
|
|
NetworkSettings: networkSettings,
|
|
}, nil
|
|
}
|
|
|
|
func (daemon *Daemon) getInspectData(container *container.Container, size bool) (*types.ContainerJSONBase, error) {
|
|
// make a copy to play with
|
|
hostConfig := *container.HostConfig
|
|
|
|
children := daemon.children(container)
|
|
hostConfig.Links = nil // do not expose the internal structure
|
|
for linkAlias, child := range children {
|
|
hostConfig.Links = append(hostConfig.Links, fmt.Sprintf("%s:%s", child.Name, linkAlias))
|
|
}
|
|
|
|
var containerHealth *types.Health
|
|
if container.State.Health != nil {
|
|
containerHealth = &types.Health{
|
|
Status: container.State.Health.Status,
|
|
FailingStreak: container.State.Health.FailingStreak,
|
|
Log: append([]*types.HealthcheckResult{}, container.State.Health.Log...),
|
|
}
|
|
}
|
|
|
|
containerState := &types.ContainerState{
|
|
Status: container.State.StateString(),
|
|
Running: container.State.Running,
|
|
Paused: container.State.Paused,
|
|
Restarting: container.State.Restarting,
|
|
OOMKilled: container.State.OOMKilled,
|
|
Dead: container.State.Dead,
|
|
Pid: container.State.Pid,
|
|
ExitCode: container.State.ExitCode,
|
|
Error: container.State.Error,
|
|
StartedAt: container.State.StartedAt.Format(time.RFC3339Nano),
|
|
FinishedAt: container.State.FinishedAt.Format(time.RFC3339Nano),
|
|
Health: containerHealth,
|
|
}
|
|
|
|
contJSONBase := &types.ContainerJSONBase{
|
|
ID: container.ID,
|
|
Created: container.Created.Format(time.RFC3339Nano),
|
|
Path: container.Path,
|
|
Args: container.Args,
|
|
State: containerState,
|
|
Image: container.ImageID.String(),
|
|
LogPath: container.LogPath,
|
|
Name: container.Name,
|
|
RestartCount: container.RestartCount,
|
|
Driver: container.Driver,
|
|
MountLabel: container.MountLabel,
|
|
ProcessLabel: container.ProcessLabel,
|
|
ExecIDs: container.GetExecIDs(),
|
|
HostConfig: &hostConfig,
|
|
}
|
|
|
|
var (
|
|
sizeRw int64
|
|
sizeRootFs int64
|
|
)
|
|
if size {
|
|
sizeRw, sizeRootFs = daemon.getSize(container)
|
|
contJSONBase.SizeRw = &sizeRw
|
|
contJSONBase.SizeRootFs = &sizeRootFs
|
|
}
|
|
|
|
// Now set any platform-specific fields
|
|
contJSONBase = setPlatformSpecificContainerFields(container, contJSONBase)
|
|
|
|
contJSONBase.GraphDriver.Name = container.Driver
|
|
|
|
graphDriverData, err := container.RWLayer.Metadata()
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
contJSONBase.GraphDriver.Data = graphDriverData
|
|
|
|
return contJSONBase, nil
|
|
}
|
|
|
|
// ContainerExecInspect returns low-level information about the exec
|
|
// command. An error is returned if the exec cannot be found.
|
|
func (daemon *Daemon) ContainerExecInspect(id string) (*backend.ExecInspect, error) {
|
|
e, err := daemon.getExecConfig(id)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
pc := inspectExecProcessConfig(e)
|
|
|
|
return &backend.ExecInspect{
|
|
ID: e.ID,
|
|
Running: e.Running,
|
|
ExitCode: e.ExitCode,
|
|
ProcessConfig: pc,
|
|
OpenStdin: e.OpenStdin,
|
|
OpenStdout: e.OpenStdout,
|
|
OpenStderr: e.OpenStderr,
|
|
CanRemove: e.CanRemove,
|
|
ContainerID: e.ContainerID,
|
|
DetachKeys: e.DetachKeys,
|
|
}, nil
|
|
}
|
|
|
|
// VolumeInspect looks up a volume by name. An error is returned if
|
|
// the volume cannot be found.
|
|
func (daemon *Daemon) VolumeInspect(name string) (*types.Volume, error) {
|
|
v, err := daemon.volumes.Get(name)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
apiV := volumeToAPIType(v)
|
|
apiV.Mountpoint = v.Path()
|
|
apiV.Status = v.Status()
|
|
return apiV, nil
|
|
}
|
|
|
|
func (daemon *Daemon) getBackwardsCompatibleNetworkSettings(settings *network.Settings) *v1p20.NetworkSettings {
|
|
result := &v1p20.NetworkSettings{
|
|
NetworkSettingsBase: types.NetworkSettingsBase{
|
|
Bridge: settings.Bridge,
|
|
SandboxID: settings.SandboxID,
|
|
HairpinMode: settings.HairpinMode,
|
|
LinkLocalIPv6Address: settings.LinkLocalIPv6Address,
|
|
LinkLocalIPv6PrefixLen: settings.LinkLocalIPv6PrefixLen,
|
|
Ports: settings.Ports,
|
|
SandboxKey: settings.SandboxKey,
|
|
SecondaryIPAddresses: settings.SecondaryIPAddresses,
|
|
SecondaryIPv6Addresses: settings.SecondaryIPv6Addresses,
|
|
},
|
|
DefaultNetworkSettings: daemon.getDefaultNetworkSettings(settings.Networks),
|
|
}
|
|
|
|
return result
|
|
}
|
|
|
|
// getDefaultNetworkSettings creates the deprecated structure that holds the information
|
|
// about the bridge network for a container.
|
|
func (daemon *Daemon) getDefaultNetworkSettings(networks map[string]*networktypes.EndpointSettings) types.DefaultNetworkSettings {
|
|
var settings types.DefaultNetworkSettings
|
|
|
|
if defaultNetwork, ok := networks["bridge"]; ok {
|
|
settings.EndpointID = defaultNetwork.EndpointID
|
|
settings.Gateway = defaultNetwork.Gateway
|
|
settings.GlobalIPv6Address = defaultNetwork.GlobalIPv6Address
|
|
settings.GlobalIPv6PrefixLen = defaultNetwork.GlobalIPv6PrefixLen
|
|
settings.IPAddress = defaultNetwork.IPAddress
|
|
settings.IPPrefixLen = defaultNetwork.IPPrefixLen
|
|
settings.IPv6Gateway = defaultNetwork.IPv6Gateway
|
|
settings.MacAddress = defaultNetwork.MacAddress
|
|
}
|
|
return settings
|
|
}
|