mirror of
https://github.com/moby/moby.git
synced 2026-01-11 18:51:37 +00:00
The Container.State struct holds the container's state, and most of
its fields are expected to change dynamically. Some o these state-changes
are explicit, for example, setting the container to be "stopped". Other
state changes can be more explicit, for example due to the containers'
process exiting or being "OOM" killed by the kernel.
The distinction between explicit ("desired") state changes and "state"
("actual state") is sometimes vague; for some properties, we clearly
separated them, for example if a user requested the container to be
stopped or restarted, we store state in the Container object itself;
HasBeenManuallyStopped bool // used for unless-stopped restart policy
HasBeenManuallyRestarted bool `json:"-"` // used to distinguish restart caused by restart policy from the manual one
Other properties are more ambiguous. such as "HasBeenStartedBefore" and
"RestartCount", which are stored on the Container (and persisted to
disk), but may be more related to "actual" state, and likely should
not be persisted;
RestartCount int
HasBeenStartedBefore bool
Given that (per the above) concurrency must be taken into account, most
changes to the `container.State` struct should be protected; here's where
things get blurry. While the `State` type provides various accessor methods,
only some of them take concurrency into account; for example, [State.IsRunning]
and [State.GetPID] acquire a lock, whereas [State.ExitCodeValue] does not.
Even the (commonly used) [State.StateString] has no locking at all.
The way to handle this is error-prone; [container.State] contains a mutex,
and it's exported. Given that its embedded in the [container.Container]
struct, it's also exposed as an exported mutex for the container. The
assumption here is that by "merging" the two, the caller to acquire a lock
when either the container _or_ its state must be mutated. However, because
some methods on `container.State` handle their own locking, consumers must
be deeply familiar with the internals; if both changes to the `Container`
AND `Container.State` must be made. This gets amplified more as some
(exported!) methods, such as [container.SetRunning] mutate multiple fields,
but don't acquire a lock (so expect the caller to hold one), but their
(also exported) counterpart (e.g. [State.IsRunning]) do.
It should be clear from the above, that this needs some architectural
changes; a clearer separation between "desired" and "actual" state (opening
the potential to update the container's config without manually touching
its `State`), possibly a method to obtain a read-only copy of the current
state (for those querying state), and reviewing which fields belong where
(and should be persisted to disk, or only remain in memory).
This PR preserves the status quo; it makes no structural changes, other
than exposing where we access the container's state. Where previously the
State fields and methods were referred to as "part of the container"
(e.g. `ctr.IsRunning()` or `ctr.Running`), we now explicitly reference
the embedded `State` (`ctr.State.IsRunning`, `ctr.State.Running`).
The exception (for now) is the mutex, which is still referenced through
the embedded struct (`ctr.Lock()` instead of `ctr.State.Lock()`), as this
is (mostly) by design to protect the container, and what's in it (including
its `State`).
[State.IsRunning]: c4afa77157/daemon/container/state.go (L205-L209)
[State.GetPID]: c4afa77157/daemon/container/state.go (L211-L216)
[State.ExitCodeValue]: c4afa77157/daemon/container/state.go (L218-L228)
[State.StateString]: c4afa77157/daemon/container/state.go (L102-L131)
[container.State]: c4afa77157/daemon/container/state.go (L15-L23)
[container.Container]: c4afa77157/daemon/container/container.go (L67-L75)
[container.SetRunning]: c4afa77157/daemon/container/state.go (L230-L277)
Signed-off-by: Sebastiaan van Stijn <github@gone.nl>
131 lines
4.3 KiB
Go
131 lines
4.3 KiB
Go
package daemon
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"github.com/containerd/log"
|
|
containertypes "github.com/moby/moby/api/types/container"
|
|
"github.com/moby/moby/api/types/events"
|
|
"github.com/moby/moby/v2/daemon/container"
|
|
"github.com/moby/moby/v2/daemon/server/backend"
|
|
"github.com/moby/moby/v2/errdefs"
|
|
"github.com/moby/sys/signal"
|
|
"github.com/pkg/errors"
|
|
)
|
|
|
|
// ContainerStop looks for the given container and stops it.
|
|
// In case the container fails to stop gracefully within a time duration
|
|
// specified by the timeout argument, in seconds, it is forcefully
|
|
// terminated (killed).
|
|
//
|
|
// If the timeout is nil, the container's StopTimeout value is used, if set,
|
|
// otherwise the engine default. A negative timeout value can be specified,
|
|
// meaning no timeout, i.e. no forceful termination is performed.
|
|
func (daemon *Daemon) ContainerStop(ctx context.Context, name string, options backend.ContainerStopOptions) error {
|
|
ctr, err := daemon.GetContainer(name)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if !ctr.State.IsRunning() {
|
|
// This is not an actual error, but produces a 304 "not modified"
|
|
// when returned through the API to indicates the container is
|
|
// already in the desired state. It's implemented as an error
|
|
// to make the code calling this function terminate early (as
|
|
// no further processing is needed).
|
|
return errdefs.NotModified(errors.New("container is already stopped"))
|
|
}
|
|
err = daemon.containerStop(ctx, ctr, options)
|
|
if err != nil {
|
|
return errdefs.System(errors.Wrapf(err, "cannot stop container: %s", name))
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// containerStop sends a stop signal, waits, sends a kill signal. It uses
|
|
// a [context.WithoutCancel], so cancelling the context does not cancel
|
|
// the request to stop the container.
|
|
func (daemon *Daemon) containerStop(ctx context.Context, ctr *container.Container, options backend.ContainerStopOptions) (retErr error) {
|
|
// Cancelling the request should not cancel the stop.
|
|
ctx = context.WithoutCancel(ctx)
|
|
|
|
if !ctr.State.IsRunning() {
|
|
return nil
|
|
}
|
|
|
|
var (
|
|
stopSignal = ctr.StopSignal()
|
|
stopTimeout = ctr.StopTimeout()
|
|
)
|
|
if options.Signal != "" {
|
|
sig, err := signal.ParseSignal(options.Signal)
|
|
if err != nil {
|
|
return errdefs.InvalidParameter(err)
|
|
}
|
|
stopSignal = sig
|
|
}
|
|
if options.Timeout != nil {
|
|
stopTimeout = *options.Timeout
|
|
}
|
|
|
|
var wait time.Duration
|
|
if stopTimeout >= 0 {
|
|
wait = time.Duration(stopTimeout) * time.Second
|
|
}
|
|
defer func() {
|
|
if retErr == nil {
|
|
daemon.LogContainerEvent(ctr, events.ActionStop)
|
|
// Ensure container status changes are committed by handler of container exit before returning control to the caller
|
|
ctr.Lock()
|
|
defer ctr.Unlock()
|
|
}
|
|
}()
|
|
|
|
// 1. Send a stop signal
|
|
err := daemon.killPossiblyDeadProcess(ctr, stopSignal)
|
|
if err != nil {
|
|
wait = 2 * time.Second
|
|
}
|
|
|
|
var subCtx context.Context
|
|
var cancel context.CancelFunc
|
|
if stopTimeout >= 0 {
|
|
subCtx, cancel = context.WithTimeout(ctx, wait)
|
|
} else {
|
|
subCtx, cancel = context.WithCancel(ctx)
|
|
}
|
|
defer cancel()
|
|
|
|
if status := <-ctr.State.Wait(subCtx, containertypes.WaitConditionNotRunning); status.Err() == nil {
|
|
// container did exit, so ignore any previous errors and return
|
|
return nil
|
|
}
|
|
|
|
if err != nil {
|
|
// the container has still not exited, and the kill function errored, so log the error here:
|
|
log.G(ctx).WithError(err).WithField("container", ctr.ID).Errorf("Error sending stop (signal %d) to container", stopSignal)
|
|
}
|
|
if stopTimeout < 0 {
|
|
// if the client requested that we never kill / wait forever, but container.Wait was still
|
|
// interrupted (parent context cancelled, for example), we should propagate the signal failure
|
|
return err
|
|
}
|
|
|
|
log.G(ctx).WithField("container", ctr.ID).Infof("Container failed to exit within %s of signal %d - using the force", wait, stopSignal)
|
|
|
|
// Stop either failed or container didn't exit, so fallback to kill.
|
|
if err := daemon.Kill(ctr); err != nil {
|
|
// got a kill error, but give container 2 more seconds to exit just in case
|
|
subCtx, cancel := context.WithTimeout(ctx, 2*time.Second)
|
|
defer cancel()
|
|
status := <-ctr.State.Wait(subCtx, containertypes.WaitConditionNotRunning)
|
|
if status.Err() != nil {
|
|
log.G(ctx).WithError(err).WithField("container", ctr.ID).Errorf("error killing container: %v", status.Err())
|
|
return err
|
|
}
|
|
// container did exit, so ignore previous errors and continue
|
|
}
|
|
|
|
return nil
|
|
}
|