1
0
Fork 0
mirror of https://github.com/moby/moby.git synced 2022-11-09 12:21:53 -05:00
moby--moby/daemon/monitor.go

213 lines
5.6 KiB
Go
Raw Normal View History

package daemon // import "github.com/docker/docker/daemon"
import (
"context"
"errors"
"fmt"
"runtime"
"strconv"
"time"
"github.com/docker/docker/api/types"
"github.com/docker/docker/container"
"github.com/docker/docker/libcontainerd"
"github.com/docker/docker/restartmanager"
"github.com/sirupsen/logrus"
)
func (daemon *Daemon) setStateCounter(c *container.Container) {
switch c.StateString() {
case "paused":
stateCtr.set(c.ID, "paused")
case "running":
stateCtr.set(c.ID, "running")
default:
stateCtr.set(c.ID, "stopped")
}
}
// ProcessEvent is called by libcontainerd whenever an event occurs
func (daemon *Daemon) ProcessEvent(id string, e libcontainerd.EventType, ei libcontainerd.EventInfo) error {
c, err := daemon.GetContainer(id)
if c == nil || err != nil {
return fmt.Errorf("no such container: %s", id)
}
switch e {
case libcontainerd.EventOOM:
// StateOOM is Linux specific and should never be hit on Windows
if runtime.GOOS == "windows" {
return errors.New("received StateOOM from libcontainerd on Windows. This should never happen")
}
c.Lock()
defer c.Unlock()
Add support for user-defined healthchecks 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>
2016-04-18 05:48:13 -04:00
daemon.updateHealthMonitor(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
return err
}
daemon.LogContainerEvent(c, "oom")
case libcontainerd.EventExit:
if int(ei.Pid) == c.Pid {
c.Lock()
_, _, err := daemon.containerd.DeleteTask(context.Background(), c.ID)
if err != nil {
logrus.WithError(err).Warnf("failed to delete container %s from containerd", c.ID)
}
c.StreamConfig.Wait()
c.Reset(false)
exitStatus := container.ExitStatus{
ExitCode: int(ei.ExitCode),
ExitedAt: ei.ExitedAt,
OOMKilled: ei.OOMKilled,
}
restart, wait, err := c.RestartManager().ShouldRestart(ei.ExitCode, daemon.IsShuttingDown() || c.HasBeenManuallyStopped, time.Since(c.StartedAt))
if err == nil && restart {
c.RestartCount++
c.SetRestarting(&exitStatus)
} else {
Windows: Pass back system errors on container exit Signed-off-by: John Howard <jhoward@microsoft.com> While debugging #32838, it was found (https://github.com/moby/moby/issues/32838#issuecomment-356005845) that the utility VM in some circumstances was crashing. Unfortunately, this was silently thrown away, and as far as the build step (also applies to docker run) was concerned, the exit code was zero and the error was thrown away. Windows containers operate differently to containers on Linux, and there can be legitimate system errors during container shutdown after the init process exits. This PR handles this and passes the error all the way back to the client, and correctly causes a build step running a container which hits a system error to fail, rather than blindly trying to keep going, assuming all is good, and get a subsequent failure on a commit. With this change, assuming an error occurs, here's an example of a failure which previous was reported as a commit error: ``` The command 'powershell -Command $ErrorActionPreference = 'Stop'; $ProgressPreference = 'SilentlyContinue'; Install-WindowsFeature -Name Web-App-Dev ; Install-WindowsFeature -Name ADLDS; Install-WindowsFeature -Name Web-Mgmt-Compat; Install-WindowsFeature -Name Web-Mgmt-Service; Install-WindowsFeature -Name Web-Metabase; Install-WindowsFeature -Name Web-Lgcy-Scripting; Install-WindowsFeature -Name Web-WMI; Install-WindowsFeature -Name Web-WHC; Install-WindowsFeature -Name Web-Scripting-Tools; Install-WindowsFeature -Name Web-Net-Ext45; Install-WindowsFeature -Name Web-ASP; Install-WindowsFeature -Name Web-ISAPI-Ext; Install-WindowsFeature -Name Web-ISAPI-Filter; Install-WindowsFeature -Name Web-Default-Doc; Install-WindowsFeature -Name Web-Dir-Browsing; Install-WindowsFeature -Name Web-Http-Errors; Install-WindowsFeature -Name Web-Static-Content; Install-WindowsFeature -Name Web-Http-Redirect; Install-WindowsFeature -Name Web-DAV-Publishing; Install-WindowsFeature -Name Web-Health; Install-WindowsFeature -Name Web-Http-Logging; Install-WindowsFeature -Name Web-Custom-Logging; Install-WindowsFeature -Name Web-Log-Libraries; Install-WindowsFeature -Name Web-Request-Monitor; Install-WindowsFeature -Name Web-Http-Tracing; Install-WindowsFeature -Name Web-Stat-Compression; Install-WindowsFeature -Name Web-Dyn-Compression; Install-WindowsFeature -Name Web-Security; Install-WindowsFeature -Name Web-Windows-Auth; Install-WindowsFeature -Name Web-Basic-Auth; Install-WindowsFeature -Name Web-Url-Auth; Install-WindowsFeature -Name Web-WebSockets; Install-WindowsFeature -Name Web-AppInit; Install-WindowsFeature -Name NET-WCF-HTTP-Activation45; Install-WindowsFeature -Name NET-WCF-Pipe-Activation45; Install-WindowsFeature -Name NET-WCF-TCP-Activation45;' returned a non-zero code: 4294967295: container shutdown failed: container ba9c65054d42d4830fb25ef55e4ab3287550345aa1a2bb265df4e5bfcd79c78a encountered an error during WaitTimeout: failure in a Windows system call: The compute system exited unexpectedly. (0xc0370106) ``` Without this change, it would be incorrectly reported such as in this comment: https://github.com/moby/moby/issues/32838#issuecomment-309621097 ``` Step 3/8 : ADD buildtools C:/buildtools re-exec error: exit status 1: output: time="2017-06-20T11:37:38+10:00" level=error msg="hcsshim::ImportLayer failed in Win32: The system cannot find the path specified. (0x3) layerId=\\\\?\\C:\\ProgramData\\docker\\windowsfilter\\b41d28c95f98368b73fc192cb9205700e21 6691495c1f9ac79b9b04ec4923ea2 flavour=1 folder=C:\\Windows\\TEMP\\hcs232661915" hcsshim::ImportLayer failed in Win32: The system cannot find the path specified. (0x3) layerId=\\?\C:\ProgramData\docker\windowsfilter\b41d28c95f98368b73fc192cb9205700e216691495c1f9ac79b9b04ec4923ea2 flavour=1 folder=C:\Windows\TEMP\hcs232661915 ```
2018-01-09 14:46:29 -05:00
if ei.Error != nil {
c.SetError(ei.Error)
}
c.SetStopped(&exitStatus)
defer daemon.autoRemove(c)
}
defer c.Unlock() // needs to be called before autoRemove
// cancel healthcheck here, they will be automatically
// restarted if/when the container is started again
daemon.stopHealthchecks(c)
attributes := map[string]string{
"exitCode": strconv.Itoa(int(ei.ExitCode)),
}
daemon.LogContainerEventWithAttributes(c, "die", attributes)
daemon.Cleanup(c)
if err == nil && restart {
go func() {
err := <-wait
if err == nil {
// daemon.netController is initialized when daemon is restoring containers.
// But containerStart will use daemon.netController segment.
// So to avoid panic at startup process, here must wait util daemon restore done.
daemon.waitForStartupDone()
if err = daemon.containerStart(c, "", "", false); err != nil {
logrus.Debugf("failed to restart container: %+v", err)
}
}
if err != nil {
c.Lock()
c.SetStopped(&exitStatus)
c.Unlock()
defer daemon.autoRemove(c)
if err != restartmanager.ErrRestartCanceled {
logrus.Errorf("restartmanger wait error: %+v", err)
}
}
}()
}
daemon.setStateCounter(c)
return c.CheckpointTo(daemon.containersReplica)
}
if execConfig := c.ExecCommands.Get(ei.ProcessID); execConfig != nil {
ec := int(ei.ExitCode)
execConfig.Lock()
defer execConfig.Unlock()
execConfig.ExitCode = &ec
execConfig.Running = false
execConfig.StreamConfig.Wait()
if err := execConfig.CloseStreams(); err != nil {
logrus.Errorf("failed to cleanup exec %s streams: %s", c.ID, err)
}
// remove the exec command from the container's store only and not the
// daemon's store so that the exec command can be inspected.
c.ExecCommands.Delete(execConfig.ID, execConfig.Pid)
attributes := map[string]string{
"execID": execConfig.ID,
"exitCode": strconv.Itoa(ec),
}
daemon.LogContainerEventWithAttributes(c, "exec_die", attributes)
} else {
logrus.WithFields(logrus.Fields{
"container": c.ID,
"exec-id": ei.ProcessID,
"exec-pid": ei.Pid,
}).Warnf("Ignoring Exit Event, no such exec command found")
}
case libcontainerd.EventStart:
c.Lock()
defer c.Unlock()
// This is here to handle start not generated by docker
if !c.Running {
c.SetRunning(int(ei.Pid), false)
c.HasBeenManuallyStopped = false
c.HasBeenStartedBefore = true
daemon.setStateCounter(c)
daemon.initHealthMonitor(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
return err
}
daemon.LogContainerEvent(c, "start")
}
case libcontainerd.EventPaused:
c.Lock()
defer c.Unlock()
if !c.Paused {
c.Paused = true
daemon.setStateCounter(c)
daemon.updateHealthMonitor(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
return err
}
daemon.LogContainerEvent(c, "pause")
}
case libcontainerd.EventResumed:
c.Lock()
defer c.Unlock()
if c.Paused {
c.Paused = false
daemon.setStateCounter(c)
daemon.updateHealthMonitor(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
return err
}
daemon.LogContainerEvent(c, "unpause")
}
}
return nil
}
func (daemon *Daemon) autoRemove(c *container.Container) {
c.Lock()
ar := c.HostConfig.AutoRemove
c.Unlock()
if !ar {
return
}
var err error
if err = daemon.ContainerRm(c.ID, &types.ContainerRmConfig{ForceRemove: true, RemoveVolume: true}); err == nil {
return
}
if c := daemon.containers.Get(c.ID); c == nil {
return
}
if err != nil {
logrus.WithError(err).WithField("container", c.ID).Error("error removing container")
}
}